Token |
|
Token ID | 198 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ONE | +1.126 |
rigging | +1.122 |
sparing | +1.098 |
Problem | +1.063 |
THING | +1.050 |
Neg logit contributions | |
verts | -1.575 |
ements | -1.560 |
enhagen | -1.554 |
uez | -1.542 |
nces | -1.485 |
Token | Links |
Token ID | 31815 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
ONE | +1.273 |
rigging | +1.238 |
Problem | +1.233 |
THING | +1.187 |
sparing | +1.181 |
Neg logit contributions | |
verts | -1.608 |
ements | -1.598 |
uez | -1.593 |
enhagen | -1.576 |
nces | -1.512 |
Token | mentioned |
Token ID | 4750 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
verts | +0.260 |
ements | +0.256 |
uez | +0.252 |
enhagen | +0.243 |
nces | +0.236 |
Neg logit contributions | |
rigging | -0.257 |
sparing | -0.254 |
ONE | -0.252 |
discord | -0.242 |
Problem | -0.240 |
Token | in |
Token ID | 287 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
sparing | +2.380 |
rigging | +2.356 |
ONE | +2.314 |
discord | +2.211 |
orally | +2.198 |
Neg logit contributions | |
verts | -3.831 |
ements | -3.774 |
uez | -3.757 |
enhagen | -3.587 |
verages | -3.527 |
Token | this |
Token ID | 428 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
rigging | +1.976 |
sparing | +1.964 |
ONE | +1.946 |
discord | +1.896 |
centre | +1.844 |
Neg logit contributions | |
uez | -2.277 |
ements | -2.247 |
verts | -2.234 |
enhagen | -2.159 |
bats | -2.099 |
Token | show |
Token ID | 905 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
rigging | +0.550 |
sparing | +0.545 |
ONE | +0.545 |
discord | +0.512 |
THING | +0.497 |
Neg logit contributions | |
verts | -1.344 |
ements | -1.337 |
uez | -1.333 |
enhagen | -1.294 |
nces | -1.280 |
Token | include |
Token ID | 2291 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
resonate | +6.946 |
sparing | +6.766 |
centre | +6.696 |
underestimate | +6.613 |
discord | +6.520 |
Neg logit contributions | |
uez | -12.693 |
ements | -12.547 |
verts | -12.371 |
inventoryQuantity | -12.142 |
verages | -12.050 |
Token | : |
Token ID | 25 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
rigging | +2.005 |
sparing | +1.941 |
ONE | +1.930 |
discord | +1.861 |
Problem | +1.836 |
Neg logit contributions | |
verts | -2.770 |
ements | -2.756 |
uez | -2.723 |
enhagen | -2.647 |
bats | -2.555 |
Token |
|
Token ID | 198 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
rigging | +1.495 |
ONE | +1.454 |
sparing | +1.454 |
discord | +1.396 |
Problem | +1.385 |
Neg logit contributions | |
verts | -1.880 |
ements | -1.866 |
uez | -1.830 |
enhagen | -1.779 |
nces | -1.727 |
Token |
|
Token ID | 198 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
ONE | +2.398 |
rigging | +2.332 |
sparing | +2.276 |
Problem | +2.251 |
discord | +2.211 |
Neg logit contributions | |
enhagen | -3.990 |
verts | -3.884 |
ements | -3.883 |
uez | -3.826 |
nces | -3.759 |
Token | Did |
Token ID | 11633 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
ONE | +1.449 |
rigging | +1.409 |
Problem | +1.385 |
sparing | +1.354 |
THING | +1.349 |
Neg logit contributions | |
verts | -1.998 |
ements | -1.994 |
uez | -1.971 |
enhagen | -1.944 |
nces | -1.870 |
Token | Taylor |
Token ID | 8121 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
sparing | +0.735 |
rigging | +0.724 |
ONE | +0.720 |
discord | +0.684 |
centre | +0.678 |
Neg logit contributions | |
verts | -1.103 |
ements | -1.102 |
uez | -1.072 |
enhagen | -1.054 |
nces | -1.040 |
Token | - |
Token ID | 12 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
verts | +1.837 |
ements | +1.807 |
uez | +1.776 |
enhagen | +1.726 |
nesses | +1.670 |
Neg logit contributions | |
rigging | -1.441 |
sparing | -1.414 |
ONE | -1.410 |
THING | -1.342 |
Problem | -1.336 |
Token | Johnson |
Token ID | 25378 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
verts | +2.695 |
ements | +2.639 |
uez | +2.610 |
enhagen | +2.521 |
nesses | +2.477 |
Neg logit contributions | |
rigging | -1.560 |
sparing | -1.526 |
ONE | -1.503 |
underestimate | -1.423 |
discord | -1.419 |
Token | ( |
Token ID | 357 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
rigging | +0.680 |
sparing | +0.670 |
ONE | +0.665 |
discord | +0.634 |
centre | +0.628 |
Neg logit contributions | |
verts | -0.735 |
ements | -0.723 |
uez | -0.706 |
enhagen | -0.691 |
nces | -0.673 |
Token | Kick |
Token ID | 45390 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
ONE | +1.545 |
rigging | +1.483 |
sparing | +1.473 |
Problem | +1.441 |
THING | +1.435 |
Neg logit contributions | |
ements | -1.944 |
verts | -1.927 |
uez | -1.912 |
enhagen | -1.876 |
nces | -1.845 |
Token | - |
Token ID | 12 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
rigging | +3.123 |
ONE | +3.111 |
sparing | +3.047 |
centre | +2.998 |
Problem | +2.956 |
Neg logit contributions | |
verts | -4.025 |
uez | -4.015 |
ements | -3.980 |
nces | -3.978 |
enhagen | -3.879 |
Token | Ass |
Token ID | 8021 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
rigging | +3.957 |
Problem | +3.922 |
ONE | +3.922 |
strap | +3.516 |
Neg | +3.358 |
Neg logit contributions | |
nces | -16.588 |
enhagen | -15.603 |
uyomi | -15.534 |
uez | -15.340 |
ements | -15.128 |
Token | ), |
Token ID | 828 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
rigging | +1.635 |
sparing | +1.606 |
ONE | +1.591 |
centre | +1.513 |
discord | +1.512 |
Neg logit contributions | |
verts | -2.258 |
ements | -2.243 |
uez | -2.223 |
enhagen | -2.188 |
nces | -2.111 |
Token | and |
Token ID | 290 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
rigging | +2.112 |
sparing | +2.103 |
ONE | +2.065 |
centre | +1.987 |
discord | +1.970 |
Neg logit contributions | |
verts | -2.191 |
ements | -2.148 |
uez | -2.113 |
enhagen | -2.084 |
nces | -2.047 |
Token | now |
Token ID | 783 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
rigging | +1.631 |
sparing | +1.619 |
ONE | +1.613 |
centre | +1.542 |
discord | +1.527 |
Neg logit contributions | |
verts | -1.965 |
ements | -1.963 |
uez | -1.919 |
enhagen | -1.892 |
nces | -1.833 |
Token | just |
Token ID | 655 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
rigging | +1.344 |
ONE | +1.336 |
sparing | +1.334 |
centre | +1.272 |
discord | +1.272 |
Neg logit contributions | |
ements | -1.537 |
verts | -1.537 |
uez | -1.502 |
enhagen | -1.459 |
nces | -1.416 |
Token | " |
Token ID | 1 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
ONE | +0.468 |
rigging | +0.460 |
sparing | +0.447 |
Problem | +0.440 |
THING | +0.438 |
Neg logit contributions | |
verts | -0.714 |
ements | -0.708 |
uez | -0.695 |
enhagen | -0.694 |
nces | -0.665 |
Token | Mom |
Token ID | 29252 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
ONE | +1.153 |
Problem | +1.086 |
rigging | +1.086 |
THING | +1.069 |
sparing | +1.045 |
Neg logit contributions | |
verts | -1.751 |
ements | -1.735 |
enhagen | -1.731 |
uez | -1.716 |
nces | -1.661 |
Token | ? |
Token ID | 30 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
rigging | +3.722 |
sparing | +3.691 |
ONE | +3.685 |
discord | +3.490 |
centre | +3.469 |
Neg logit contributions | |
verts | -5.567 |
ements | -5.530 |
enhagen | -5.367 |
uez | -5.363 |
nesses | -5.301 |
Token | Dad |
Token ID | 17415 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
verts | +0.241 |
ements | +0.236 |
uez | +0.232 |
enhagen | +0.230 |
nces | +0.219 |
Neg logit contributions | |
rigging | -0.232 |
ONE | -0.231 |
sparing | -0.227 |
THING | -0.221 |
Problem | -0.219 |
Token | ? |
Token ID | 30 |
Feature activation | +9.49e-02 |
Pos logit contributions | |
rigging | +2.947 |
sparing | +2.931 |
ONE | +2.882 |
discord | +2.766 |
underestimate | +2.743 |
Neg logit contributions | |
verts | -3.735 |
ements | -3.702 |
uez | -3.604 |
enhagen | -3.530 |
nesses | -3.469 |
Token | Ol |
Token ID | 6544 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ONE | +0.511 |
rigging | +0.511 |
sparing | +0.500 |
THING | +0.491 |
Problem | +0.484 |
Neg logit contributions | |
verts | -0.558 |
ements | -0.547 |
enhagen | -0.540 |
uez | -0.538 |
nces | -0.510 |
Token | af |
Token ID | 1878 |
Feature activation | -7.82e-02 |
Pos logit contributions | |
sparing | +7.446 |
ONE | +7.008 |
centre | +6.828 |
rigging | +6.778 |
THING | +6.513 |
Neg logit contributions | |
ements | -11.586 |
nces | -11.375 |
enhagen | -11.279 |
verts | -11.238 |
inventoryQuantity | -11.065 |
Token | ?" |
Token ID | 1701 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
verts | +0.470 |
ements | +0.464 |
uez | +0.453 |
enhagen | +0.439 |
nces | +0.429 |
Neg logit contributions | |
rigging | -0.416 |
sparing | -0.410 |
ONE | -0.407 |
discord | -0.388 |
THING | -0.386 |
Token | I |
Token ID | 314 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
rigging | +3.069 |
sparing | +3.017 |
ONE | +2.977 |
centre | +2.852 |
discord | +2.846 |
Neg logit contributions | |
verts | -4.351 |
ements | -4.244 |
uez | -4.190 |
enhagen | -4.186 |
verages | -3.999 |
Token | stood |
Token ID | 6204 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
rigging | +1.882 |
sparing | +1.830 |
ONE | +1.776 |
centre | +1.739 |
underestimate | +1.738 |
Neg logit contributions | |
verts | -3.029 |
ements | -2.999 |
uez | -2.912 |
enhagen | -2.907 |
bats | -2.831 |
Token | still |
Token ID | 991 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
verts | +2.611 |
ements | +2.576 |
uez | +2.524 |
enhagen | +2.438 |
nces | +2.380 |
Neg logit contributions | |
rigging | -2.046 |
ONE | -2.043 |
sparing | -2.009 |
Problem | -1.950 |
THING | -1.938 |
Token | later |
Token ID | 1568 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
verts | +0.118 |
ements | +0.116 |
uez | +0.114 |
enhagen | +0.111 |
nces | +0.108 |
Neg logit contributions | |
rigging | -0.089 |
sparing | -0.087 |
ONE | -0.086 |
discord | -0.083 |
underestimate | -0.082 |
Token | by |
Token ID | 416 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
rigging | +1.212 |
sparing | +1.196 |
ONE | +1.180 |
discord | +1.140 |
centre | +1.116 |
Neg logit contributions | |
verts | -1.496 |
ements | -1.466 |
uez | -1.451 |
enhagen | -1.411 |
nces | -1.352 |
Token | a |
Token ID | 257 |
Feature activation | +7.74e-02 |
Pos logit contributions | |
verts | +0.223 |
ements | +0.221 |
uez | +0.216 |
enhagen | +0.211 |
nesses | +0.204 |
Neg logit contributions | |
rigging | -0.189 |
sparing | -0.185 |
ONE | -0.183 |
discord | -0.177 |
THING | -0.173 |
Token | deaf |
Token ID | 21815 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
rigging | +0.363 |
sparing | +0.355 |
ONE | +0.353 |
discord | +0.341 |
centre | +0.333 |
Neg logit contributions | |
verts | -0.517 |
ements | -0.511 |
uez | -0.498 |
enhagen | -0.493 |
nces | -0.479 |
Token | ening |
Token ID | 3101 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
rigging | +3.922 |
sparing | +3.879 |
discord | +3.841 |
ONE | +3.839 |
underestimate | +3.698 |
Neg logit contributions | |
verts | -4.711 |
ements | -4.674 |
uez | -4.414 |
nces | -4.396 |
verages | -4.300 |
Token | th |
Token ID | 294 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
rigging | +2.451 |
sparing | +2.354 |
discord | +2.348 |
ONE | +2.298 |
centre | +2.222 |
Neg logit contributions | |
verts | -4.057 |
ements | -4.005 |
enhagen | -3.865 |
uez | -3.843 |
nces | -3.801 |
Token | ud |
Token ID | 463 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
ONE | +6.495 |
discord | +6.062 |
uzzle | +6.043 |
rigging | +5.811 |
resonate | +5.792 |
Neg logit contributions | |
verts | -12.822 |
enhagen | -12.533 |
verages | -12.122 |
nces | -12.075 |
nesses | -12.031 |
Token | from |
Token ID | 422 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
rigging | +2.046 |
sparing | +2.030 |
ONE | +1.981 |
discord | +1.929 |
resonate | +1.886 |
Neg logit contributions | |
verts | -2.548 |
ements | -2.479 |
uez | -2.397 |
enhagen | -2.372 |
verages | -2.303 |
Token | the |
Token ID | 262 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
verts | +0.127 |
ements | +0.125 |
uez | +0.122 |
enhagen | +0.119 |
nesses | +0.115 |
Neg logit contributions | |
rigging | -0.119 |
sparing | -0.117 |
ONE | -0.116 |
discord | -0.112 |
centre | -0.110 |
Token | collapsing |
Token ID | 30792 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
rigging | +2.331 |
sparing | +2.239 |
ONE | +2.179 |
centre | +2.169 |
discord | +2.166 |
Neg logit contributions | |
verts | -3.137 |
ements | -3.105 |
uez | -3.047 |
enhagen | -2.992 |
nces | -2.914 |
Token | monster |
Token ID | 9234 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
rigging | +0.567 |
sparing | +0.544 |
ONE | +0.539 |
centre | +0.525 |
discord | +0.523 |
Neg logit contributions | |
verts | -0.773 |
ements | -0.761 |
uez | -0.742 |
enhagen | -0.736 |
nces | -0.713 |
Token | the |
Token ID | 262 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
verts | +0.786 |
ements | +0.774 |
uez | +0.760 |
enhagen | +0.734 |
nesses | +0.713 |
Neg logit contributions | |
rigging | -0.735 |
ONE | -0.722 |
sparing | -0.720 |
discord | -0.688 |
THING | -0.685 |
Token | original |
Token ID | 2656 |
Feature activation | +2.57e-03 |
Pos logit contributions | |
verts | +0.649 |
ements | +0.638 |
uez | +0.627 |
enhagen | +0.609 |
nces | +0.591 |
Neg logit contributions | |
rigging | -0.549 |
sparing | -0.536 |
ONE | -0.535 |
discord | -0.512 |
THING | -0.507 |
Token | development |
Token ID | 2478 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
rigging | +0.013 |
ONE | +0.012 |
sparing | +0.012 |
discord | +0.012 |
THING | +0.012 |
Neg logit contributions | |
verts | -0.017 |
ements | -0.016 |
uez | -0.016 |
enhagen | -0.016 |
nces | -0.015 |
Token | teams |
Token ID | 3466 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
verts | +0.409 |
ements | +0.403 |
uez | +0.397 |
enhagen | +0.389 |
nesses | +0.376 |
Neg logit contributions | |
rigging | -0.368 |
ONE | -0.358 |
sparing | -0.358 |
discord | -0.346 |
centre | -0.341 |
Token | and |
Token ID | 290 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
rigging | +2.924 |
sparing | +2.848 |
ONE | +2.808 |
discord | +2.760 |
orally | +2.648 |
Neg logit contributions | |
verts | -3.578 |
uez | -3.471 |
ements | -3.437 |
enhagen | -3.341 |
nesses | -3.275 |
Token | hear |
Token ID | 3285 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
rigging | +1.811 |
ONE | +1.734 |
sparing | +1.733 |
discord | +1.671 |
underestimate | +1.657 |
Neg logit contributions | |
verts | -2.561 |
ements | -2.527 |
uez | -2.483 |
enhagen | -2.392 |
nces | -2.367 |
Token | their |
Token ID | 511 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
rigging | +7.453 |
sparing | +7.348 |
discord | +7.340 |
talking | +6.888 |
orally | +6.864 |
Neg logit contributions | |
verts | -11.698 |
uez | -11.614 |
inventoryQuantity | -11.577 |
uyomi | -11.433 |
ements | -11.124 |
Token | thoughts |
Token ID | 6066 |
Feature activation | +2.50e-03 |
Pos logit contributions | |
rigging | +4.535 |
sparing | +4.405 |
discord | +4.362 |
ONE | +4.228 |
resonate | +4.092 |
Neg logit contributions | |
verts | -7.010 |
uez | -6.776 |
ements | -6.641 |
enhagen | -6.529 |
nces | -6.442 |
Token | on |
Token ID | 319 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
rigging | +0.012 |
sparing | +0.012 |
ONE | +0.012 |
discord | +0.012 |
THING | +0.011 |
Neg logit contributions | |
verts | -0.016 |
ements | -0.016 |
uez | -0.015 |
enhagen | -0.015 |
nces | -0.015 |
Token | which |
Token ID | 543 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
rigging | +0.753 |
sparing | +0.734 |
ONE | +0.718 |
discord | +0.692 |
THING | +0.684 |
Neg logit contributions | |
verts | -0.834 |
ements | -0.822 |
uez | -0.811 |
enhagen | -0.783 |
nces | -0.768 |
Token | maps |
Token ID | 8739 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
verts | +3.074 |
ements | +3.016 |
uez | +2.940 |
enhagen | +2.857 |
nesses | +2.759 |
Neg logit contributions | |
rigging | -3.278 |
sparing | -3.227 |
ONE | -3.217 |
Problem | -3.090 |
THING | -3.077 |
Token | Obama |
Token ID | 2486 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
rigging | +0.442 |
sparing | +0.431 |
ONE | +0.425 |
discord | +0.411 |
centre | +0.404 |
Neg logit contributions | |
verts | -0.613 |
ements | -0.604 |
uez | -0.598 |
enhagen | -0.583 |
nesses | -0.564 |
Token | administration |
Token ID | 3662 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
verts | +2.088 |
ements | +2.055 |
uez | +2.021 |
enhagen | +1.967 |
nces | +1.904 |
Neg logit contributions | |
rigging | -1.650 |
sparing | -1.618 |
ONE | -1.617 |
THING | -1.533 |
discord | -1.529 |
Token | has |
Token ID | 468 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
rigging | +1.546 |
sparing | +1.519 |
ONE | +1.447 |
discord | +1.446 |
underestimate | +1.428 |
Neg logit contributions | |
verts | -1.839 |
ements | -1.828 |
uez | -1.824 |
enhagen | -1.768 |
nces | -1.707 |
Token | shown |
Token ID | 3402 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
rigging | +0.344 |
sparing | +0.339 |
ONE | +0.328 |
discord | +0.319 |
underestimate | +0.314 |
Neg logit contributions | |
verts | -0.479 |
ements | -0.473 |
uez | -0.470 |
enhagen | -0.457 |
nces | -0.444 |
Token | a |
Token ID | 257 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
verts | +1.076 |
ements | +1.064 |
uez | +1.045 |
enhagen | +1.019 |
nces | +0.981 |
Neg logit contributions | |
rigging | -0.910 |
sparing | -0.894 |
ONE | -0.880 |
discord | -0.849 |
underestimate | -0.838 |
Token | th |
Token ID | 294 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
verts | +3.207 |
ements | +3.154 |
uez | +3.104 |
enhagen | +3.013 |
nesses | +2.943 |
Neg logit contributions | |
rigging | -2.166 |
ONE | -2.140 |
sparing | -2.111 |
THING | -2.022 |
Problem | -2.010 |
Token | uggish |
Token ID | 36295 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
rigging | +6.421 |
ONE | +6.269 |
uzzle | +6.064 |
centre | +6.056 |
ousing | +5.971 |
Neg logit contributions | |
enhagen | -12.284 |
verts | -11.717 |
nesses | -11.555 |
nces | -11.540 |
inventoryQuantity | -11.507 |
Token | streak |
Token ID | 15113 |
Feature activation | +3.68e-03 |
Pos logit contributions | |
verts | +0.506 |
ements | +0.499 |
uez | +0.493 |
enhagen | +0.482 |
nces | +0.467 |
Neg logit contributions | |
rigging | -0.334 |
sparing | -0.326 |
ONE | -0.321 |
discord | -0.307 |
underestimate | -0.305 |
Token | , |
Token ID | 11 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
rigging | +0.020 |
sparing | +0.019 |
ONE | +0.019 |
discord | +0.018 |
underestimate | +0.018 |
Neg logit contributions | |
verts | -0.022 |
ements | -0.022 |
uez | -0.022 |
enhagen | -0.021 |
nces | -0.020 |
Token | involving |
Token ID | 7411 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
verts | +1.186 |
ements | +1.170 |
uez | +1.152 |
enhagen | +1.124 |
nces | +1.086 |
Neg logit contributions | |
rigging | -0.927 |
sparing | -0.908 |
ONE | -0.899 |
discord | -0.857 |
THING | -0.849 |
Token | everything |
Token ID | 2279 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
verts | +0.834 |
ements | +0.827 |
uez | +0.814 |
enhagen | +0.797 |
nesses | +0.767 |
Neg logit contributions | |
rigging | -0.660 |
sparing | -0.645 |
ONE | -0.631 |
discord | -0.611 |
underestimate | -0.600 |
Token | for |
Token ID | 329 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
verts | +1.175 |
ements | +1.157 |
uez | +1.136 |
enhagen | +1.105 |
nces | +1.066 |
Neg logit contributions | |
rigging | -1.070 |
sparing | -1.054 |
ONE | -1.049 |
discord | -0.998 |
THING | -0.998 |
Token | a |
Token ID | 257 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
rigging | +1.290 |
sparing | +1.274 |
ONE | +1.219 |
discord | +1.194 |
centre | +1.188 |
Neg logit contributions | |
verts | -1.884 |
ements | -1.869 |
uez | -1.837 |
enhagen | -1.810 |
nces | -1.759 |
Token | heavy |
Token ID | 4334 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
verts | +0.275 |
ements | +0.272 |
uez | +0.266 |
enhagen | +0.263 |
nces | +0.254 |
Neg logit contributions | |
rigging | -0.222 |
sparing | -0.219 |
ONE | -0.215 |
discord | -0.208 |
centre | -0.207 |
Token | , |
Token ID | 11 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
verts | +1.159 |
ements | +1.146 |
uez | +1.125 |
enhagen | +1.103 |
nces | +1.073 |
Neg logit contributions | |
rigging | -0.706 |
sparing | -0.691 |
ONE | -0.686 |
discord | -0.645 |
THING | -0.645 |
Token | knee |
Token ID | 10329 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
sparing | +2.077 |
rigging | +2.073 |
centre | +1.993 |
ONE | +1.978 |
discord | +1.960 |
Neg logit contributions | |
verts | -2.857 |
ements | -2.840 |
enhagen | -2.784 |
uez | -2.756 |
nces | -2.666 |
Token | - |
Token ID | 12 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
sparing | +4.628 |
rigging | +4.518 |
centre | +4.258 |
ONE | +4.113 |
discord | +4.051 |
Neg logit contributions | |
verts | -8.770 |
enhagen | -8.674 |
nces | -8.421 |
ements | -8.396 |
uez | -8.188 |
Token | high |
Token ID | 8929 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
sparing | +7.613 |
strap | +7.511 |
rigging | +7.497 |
lining | +7.485 |
ONE | +7.378 |
Neg logit contributions | |
enhagen | -10.719 |
verts | -10.679 |
ements | -10.617 |
uez | -10.466 |
nces | -10.332 |
Token | , |
Token ID | 11 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
verts | +0.759 |
ements | +0.748 |
uez | +0.734 |
enhagen | +0.724 |
nces | +0.710 |
Neg logit contributions | |
rigging | -0.407 |
sparing | -0.399 |
ONE | -0.394 |
centre | -0.370 |
discord | -0.369 |
Token | tackle |
Token ID | 9761 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
sparing | +2.333 |
rigging | +2.332 |
centre | +2.266 |
ONE | +2.239 |
discord | +2.193 |
Neg logit contributions | |
verts | -3.205 |
ements | -3.166 |
enhagen | -3.120 |
uez | -3.087 |
nces | -3.035 |
Token | on |
Token ID | 319 |
Feature activation | +7.11e-02 |
Pos logit contributions | |
rigging | +1.053 |
sparing | +1.050 |
ONE | +1.015 |
centre | +0.994 |
discord | +0.975 |
Neg logit contributions | |
verts | -1.290 |
ements | -1.276 |
uez | -1.256 |
enhagen | -1.244 |
nces | -1.194 |
Token | Vladimir |
Token ID | 14840 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
rigging | +0.373 |
sparing | +0.366 |
ONE | +0.364 |
centre | +0.353 |
discord | +0.348 |
Neg logit contributions | |
verts | -0.429 |
ements | -0.426 |
uez | -0.418 |
enhagen | -0.413 |
nces | -0.400 |
Token |
|
Token ID | 198 |
Feature activation | +2.47e-03 |
Pos logit contributions | |
rigging | +0.746 |
sparing | +0.739 |
ONE | +0.734 |
discord | +0.707 |
Problem | +0.706 |
Neg logit contributions | |
verts | -1.055 |
ements | -1.042 |
uez | -1.014 |
enhagen | -1.005 |
verages | -0.976 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
rigging | +0.012 |
ONE | +0.012 |
sparing | +0.012 |
Problem | +0.012 |
THING | +0.011 |
Neg logit contributions | |
verts | -0.016 |
ements | -0.015 |
uez | -0.015 |
enhagen | -0.015 |
nces | -0.014 |
Token | Email |
Token ID | 15333 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ONE | +0.348 |
rigging | +0.336 |
sparing | +0.325 |
Problem | +0.319 |
THING | +0.310 |
Neg logit contributions | |
verts | -0.830 |
ements | -0.823 |
uez | -0.808 |
enhagen | -0.803 |
nces | -0.774 |
Token | This |
Token ID | 770 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
ONE | +4.395 |
discord | +4.241 |
centre | +4.057 |
sparing | +4.014 |
HI | +3.974 |
Neg logit contributions | |
ements | -6.922 |
uez | -6.912 |
nces | -6.792 |
enhagen | -6.533 |
inventoryQuantity | -6.478 |
Token | Story |
Token ID | 8362 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
sparing | +0.791 |
rigging | +0.787 |
ONE | +0.782 |
discord | +0.759 |
Problem | +0.751 |
Neg logit contributions | |
verts | -0.894 |
ements | -0.894 |
uez | -0.862 |
enhagen | -0.857 |
nces | -0.828 |
Token | Send |
Token ID | 16290 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ONE | +1.701 |
rigging | +1.658 |
sparing | +1.657 |
Problem | +1.656 |
discord | +1.641 |
Neg logit contributions | |
ements | -1.839 |
uez | -1.793 |
verts | -1.791 |
enhagen | -1.777 |
nces | -1.709 |
Token | email |
Token ID | 3053 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
orally | +3.120 |
sparing | +2.954 |
discord | +2.591 |
HI | +2.345 |
underestimate | +2.248 |
Neg logit contributions | |
uez | -16.419 |
itton | -16.269 |
enhagen | -16.262 |
verts | -16.130 |
nces | -16.108 |
Token | to |
Token ID | 284 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
discord | +4.844 |
rigging | +4.630 |
orally | +4.628 |
centre | +4.625 |
captcha | +4.581 |
Neg logit contributions | |
uez | -7.003 |
ements | -6.835 |
enhagen | -6.700 |
nces | -6.585 |
itton | -6.395 |
Token | this |
Token ID | 428 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
ONE | +3.541 |
sparing | +3.504 |
centre | +3.498 |
discord | +3.461 |
rigging | +3.442 |
Neg logit contributions | |
ements | -5.281 |
verts | -4.973 |
uez | -4.960 |
nces | -4.944 |
bats | -4.925 |
Token | address |
Token ID | 2209 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
verts | +0.846 |
ements | +0.835 |
uez | +0.826 |
enhagen | +0.808 |
nesses | +0.790 |
Neg logit contributions | |
rigging | -0.292 |
sparing | -0.282 |
ONE | -0.281 |
THING | -0.256 |
discord | -0.253 |
Token | Enter |
Token ID | 6062 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
ONE | +2.177 |
rigging | +2.119 |
discord | +2.096 |
sparing | +2.079 |
centre | +2.040 |
Neg logit contributions | |
ements | -4.367 |
enhagen | -4.297 |
uez | -4.272 |
verts | -4.262 |
nces | -4.205 |
Token | enthusiasm |
Token ID | 17131 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
verts | +1.695 |
ements | +1.671 |
uez | +1.643 |
enhagen | +1.602 |
nces | +1.553 |
Neg logit contributions | |
rigging | -1.218 |
sparing | -1.192 |
ONE | -1.190 |
THING | -1.124 |
discord | -1.123 |
Token | ; |
Token ID | 26 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
rigging | +0.148 |
sparing | +0.145 |
ONE | +0.143 |
discord | +0.137 |
centre | +0.135 |
Neg logit contributions | |
verts | -0.164 |
ements | -0.162 |
uez | -0.160 |
enhagen | -0.156 |
nces | -0.150 |
Token | annoyed |
Token ID | 25602 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
rigging | +2.402 |
sparing | +2.392 |
ONE | +2.305 |
discord | +2.246 |
centre | +2.233 |
Neg logit contributions | |
verts | -3.438 |
ements | -3.412 |
uez | -3.378 |
enhagen | -3.361 |
nces | -3.215 |
Token | by |
Token ID | 416 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
verts | +1.408 |
ements | +1.385 |
uez | +1.363 |
enhagen | +1.325 |
nces | +1.278 |
Neg logit contributions | |
rigging | -1.284 |
sparing | -1.259 |
ONE | -1.255 |
discord | -1.196 |
THING | -1.192 |
Token | the |
Token ID | 262 |
Feature activation | -9.09e-03 |
Pos logit contributions | |
rigging | +1.187 |
sparing | +1.170 |
ONE | +1.140 |
discord | +1.111 |
centre | +1.091 |
Neg logit contributions | |
verts | -1.420 |
ements | -1.403 |
uez | -1.386 |
enhagen | -1.348 |
nces | -1.303 |
Token | th |
Token ID | 294 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
verts | +0.061 |
ements | +0.060 |
uez | +0.059 |
enhagen | +0.058 |
nces | +0.056 |
Neg logit contributions | |
rigging | -0.043 |
sparing | -0.042 |
ONE | -0.041 |
discord | -0.039 |
underestimate | -0.039 |
Token | umping |
Token ID | 25218 |
Feature activation | +7.15e-02 |
Pos logit contributions | |
rigging | +7.967 |
ONE | +7.867 |
uzzle | +7.691 |
centre | +7.568 |
ousing | +7.495 |
Neg logit contributions | |
enhagen | -10.175 |
verts | -9.809 |
inventoryQuantity | -9.421 |
verages | -9.231 |
uyomi | -9.072 |
Token | , |
Token ID | 11 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
rigging | +0.354 |
sparing | +0.341 |
ONE | +0.335 |
discord | +0.329 |
centre | +0.321 |
Neg logit contributions | |
verts | -0.466 |
ements | -0.459 |
uez | -0.448 |
enhagen | -0.444 |
nces | -0.428 |
Token | the |
Token ID | 262 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
rigging | +3.574 |
sparing | +3.458 |
discord | +3.392 |
centre | +3.265 |
ONE | +3.254 |
Neg logit contributions | |
verts | -4.452 |
ements | -4.425 |
uez | -4.289 |
enhagen | -4.270 |
nces | -4.120 |
Token | small |
Token ID | 1402 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
rigging | +1.539 |
sparing | +1.486 |
ONE | +1.465 |
discord | +1.431 |
centre | +1.416 |
Neg logit contributions | |
verts | -2.126 |
ements | -2.124 |
uez | -2.079 |
enhagen | -2.045 |
nces | -1.975 |
Token | man |
Token ID | 582 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
rigging | +0.859 |
ONE | +0.830 |
sparing | +0.828 |
discord | +0.792 |
centre | +0.791 |
Neg logit contributions | |
verts | -1.138 |
ements | -1.134 |
uez | -1.111 |
enhagen | -1.089 |
nces | -1.059 |
Token | Thomas |
Token ID | 5658 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
ONE | +0.165 |
rigging | +0.164 |
sparing | +0.160 |
Problem | +0.156 |
THING | +0.156 |
Neg logit contributions | |
verts | -0.195 |
ements | -0.192 |
uez | -0.188 |
enhagen | -0.187 |
nces | -0.179 |
Token | called |
Token ID | 1444 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
rigging | +2.084 |
sparing | +2.069 |
ONE | +2.027 |
discord | +1.957 |
centre | +1.951 |
Neg logit contributions | |
verts | -2.229 |
ements | -2.176 |
uez | -2.141 |
enhagen | -2.116 |
nces | -2.041 |
Token | it |
Token ID | 340 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
verts | +2.066 |
ements | +2.031 |
uez | +1.990 |
enhagen | +1.939 |
nces | +1.873 |
Neg logit contributions | |
rigging | -1.929 |
sparing | -1.898 |
ONE | -1.890 |
THING | -1.802 |
discord | -1.800 |
Token | the |
Token ID | 262 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
verts | +4.414 |
ements | +4.357 |
uez | +4.278 |
enhagen | +4.129 |
nces | +3.972 |
Neg logit contributions | |
rigging | -4.209 |
ONE | -4.146 |
sparing | -4.129 |
Problem | -3.961 |
THING | -3.955 |
Token | Brew |
Token ID | 9702 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
verts | +1.651 |
ements | +1.619 |
uez | +1.590 |
enhagen | +1.542 |
nces | +1.487 |
Neg logit contributions | |
rigging | -1.718 |
sparing | -1.689 |
ONE | -1.687 |
THING | -1.613 |
discord | -1.609 |
Token | Th |
Token ID | 536 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
verts | +1.157 |
ements | +1.135 |
uez | +1.120 |
enhagen | +1.087 |
nces | +1.054 |
Neg logit contributions | |
rigging | -0.946 |
ONE | -0.934 |
sparing | -0.932 |
THING | -0.888 |
Problem | -0.885 |
Token | ru |
Token ID | 622 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
ONE | +7.910 |
rigging | +7.599 |
uzzle | +7.483 |
centre | +7.418 |
leneck | +7.297 |
Neg logit contributions | |
inventoryQuantity | -9.761 |
enhagen | -9.743 |
verts | -9.487 |
ements | -9.485 |
nces | -9.177 |
Token | . |
Token ID | 13 |
Feature activation | -6.82e-02 |
Pos logit contributions | |
sparing | +2.740 |
rigging | +2.736 |
ONE | +2.693 |
centre | +2.656 |
THING | +2.644 |
Neg logit contributions | |
verts | -3.325 |
ements | -3.255 |
uez | -3.223 |
enhagen | -3.147 |
inventoryQuantity | -3.109 |
Token |
|
Token ID | 198 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
verts | +0.418 |
ements | +0.411 |
uez | +0.404 |
enhagen | +0.397 |
nces | +0.384 |
Neg logit contributions | |
rigging | -0.351 |
ONE | -0.349 |
sparing | -0.344 |
Problem | -0.332 |
THING | -0.331 |
Token |
|
Token ID | 198 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
ONE | +0.297 |
rigging | +0.297 |
sparing | +0.290 |
Problem | +0.281 |
THING | +0.280 |
Neg logit contributions | |
verts | -0.382 |
ements | -0.378 |
uez | -0.371 |
enhagen | -0.368 |
nces | -0.354 |
Token | Thomas |
Token ID | 22405 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
ONE | +1.023 |
rigging | +0.973 |
Problem | +0.971 |
THING | +0.951 |
sparing | +0.935 |
Neg logit contributions | |
verts | -1.428 |
ements | -1.418 |
enhagen | -1.408 |
uez | -1.392 |
nces | -1.346 |
Token | , |
Token ID | 11 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
rigging | +3.194 |
sparing | +3.123 |
ONE | +2.993 |
centre | +2.952 |
discord | +2.907 |
Neg logit contributions | |
ements | -3.491 |
verts | -3.476 |
uez | -3.453 |
enhagen | -3.310 |
nces | -3.292 |
Token | so |
Token ID | 523 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
rigging | +2.835 |
sparing | +2.769 |
ONE | +2.683 |
centre | +2.594 |
discord | +2.578 |
Neg logit contributions | |
verts | -3.572 |
ements | -3.563 |
uez | -3.511 |
enhagen | -3.392 |
nces | -3.376 |
Token | he |
Token ID | 339 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
rigging | +1.406 |
sparing | +1.383 |
ONE | +1.348 |
discord | +1.286 |
centre | +1.285 |
Neg logit contributions | |
verts | -1.649 |
ements | -1.635 |
uez | -1.610 |
enhagen | -1.566 |
nces | -1.524 |
Token | 's |
Token ID | 338 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
rigging | +0.664 |
sparing | +0.653 |
ONE | +0.631 |
underestimate | +0.615 |
discord | +0.612 |
Neg logit contributions | |
verts | -0.822 |
ements | -0.809 |
uez | -0.802 |
enhagen | -0.774 |
nces | -0.757 |
Token | kicking |
Token ID | 17997 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
rigging | +3.759 |
sparing | +3.654 |
ONE | +3.440 |
discord | +3.359 |
centre | +3.342 |
Neg logit contributions | |
verts | -5.430 |
ements | -5.379 |
uez | -5.328 |
enhagen | -5.153 |
nesses | -5.072 |
Token | and |
Token ID | 290 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
rigging | +1.035 |
sparing | +1.012 |
ONE | +0.987 |
discord | +0.960 |
centre | +0.951 |
Neg logit contributions | |
verts | -1.221 |
ements | -1.212 |
uez | -1.200 |
enhagen | -1.178 |
nces | -1.133 |
Token | tw |
Token ID | 665 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
rigging | +4.241 |
sparing | +3.789 |
talking | +3.509 |
discord | +3.485 |
whispering | +3.414 |
Neg logit contributions | |
ements | -15.238 |
enhagen | -15.094 |
uez | -14.893 |
verts | -14.707 |
ortium | -14.404 |
Token | itching |
Token ID | 19811 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
restling | +7.029 |
ONE | +6.922 |
rigging | +6.834 |
arning | +6.746 |
ousing | +6.677 |
Neg logit contributions | |
inventoryQuantity | -9.411 |
verts | -9.116 |
verages | -8.981 |
enhagen | -8.942 |
nces | -8.741 |
Token | away |
Token ID | 1497 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
verts | +0.793 |
ements | +0.781 |
uez | +0.770 |
enhagen | +0.748 |
nces | +0.720 |
Neg logit contributions | |
rigging | -0.702 |
sparing | -0.692 |
ONE | -0.681 |
discord | -0.653 |
THING | -0.649 |
Token | . |
Token ID | 13 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
verts | +0.992 |
ements | +0.980 |
uez | +0.965 |
enhagen | +0.936 |
nesses | +0.904 |
Neg logit contributions | |
rigging | -0.868 |
sparing | -0.853 |
ONE | -0.846 |
THING | -0.807 |
discord | -0.807 |
Token | There |
Token ID | 1318 |
Feature activation | -5.91e-02 |
Pos logit contributions | |
ONE | +2.115 |
rigging | +2.060 |
Problem | +1.996 |
sparing | +1.992 |
THING | +1.992 |
Neg logit contributions | |
verts | -2.795 |
ements | -2.773 |
uez | -2.732 |
enhagen | -2.695 |
nces | -2.610 |
Token | the |
Token ID | 262 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
verts | +0.954 |
ements | +0.935 |
uez | +0.916 |
enhagen | +0.901 |
nces | +0.868 |
Neg logit contributions | |
rigging | -0.857 |
sparing | -0.838 |
ONE | -0.826 |
discord | -0.791 |
orally | -0.786 |
Token | existence |
Token ID | 6224 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
verts | +2.959 |
ements | +2.911 |
uez | +2.858 |
enhagen | +2.776 |
nces | +2.682 |
Neg logit contributions | |
rigging | -2.638 |
sparing | -2.590 |
ONE | -2.590 |
THING | -2.465 |
discord | -2.456 |
Token | of |
Token ID | 286 |
Feature activation | +6.52e-02 |
Pos logit contributions | |
verts | +1.604 |
ements | +1.601 |
uez | +1.547 |
enhagen | +1.503 |
nesses | +1.456 |
Neg logit contributions | |
rigging | -1.742 |
sparing | -1.726 |
ONE | -1.718 |
Problem | -1.646 |
underestimate | -1.641 |
Token | video |
Token ID | 2008 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
rigging | +0.329 |
sparing | +0.315 |
ONE | +0.311 |
discord | +0.305 |
THING | +0.298 |
Neg logit contributions | |
verts | -0.417 |
ements | -0.408 |
uez | -0.401 |
enhagen | -0.393 |
nesses | -0.382 |
Token | or |
Token ID | 393 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
rigging | +2.257 |
sparing | +2.147 |
ONE | +2.117 |
discord | +2.028 |
centre | +1.957 |
Neg logit contributions | |
verts | -3.706 |
uez | -3.660 |
enhagen | -3.623 |
ements | -3.607 |
nces | -3.491 |
Token | aud |
Token ID | 2709 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
rigging | +1.793 |
sparing | +1.727 |
ONE | +1.707 |
orally | +1.663 |
discord | +1.654 |
Neg logit contributions | |
verts | -2.730 |
ements | -2.675 |
uez | -2.647 |
enhagen | -2.602 |
nesses | -2.535 |
Token | iot |
Token ID | 5151 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
rigging | +6.462 |
ONE | +6.252 |
sparing | +6.135 |
orally | +5.774 |
centre | +5.761 |
Neg logit contributions | |
verages | -10.691 |
verts | -10.470 |
uyomi | -10.462 |
enhagen | -10.441 |
uez | -10.426 |
Token | apes |
Token ID | 7916 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
rigging | +2.815 |
sparing | +2.738 |
ONE | +2.728 |
discord | +2.652 |
centre | +2.623 |
Neg logit contributions | |
verts | -3.460 |
uez | -3.421 |
ements | -3.314 |
bats | -3.208 |
inventoryQuantity | -3.207 |
Token | of |
Token ID | 286 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
rigging | +3.456 |
sparing | +3.394 |
ONE | +3.273 |
discord | +3.177 |
orally | +3.171 |
Neg logit contributions | |
verts | -4.429 |
uez | -4.383 |
enhagen | -4.357 |
ements | -4.317 |
nces | -4.175 |
Token | interviews |
Token ID | 9299 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
rigging | +2.536 |
sparing | +2.436 |
ONE | +2.383 |
discord | +2.366 |
orally | +2.296 |
Neg logit contributions | |
verts | -2.976 |
ements | -2.926 |
uez | -2.895 |
enhagen | -2.843 |
verages | -2.771 |
Token | of |
Token ID | 286 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
rigging | +0.999 |
sparing | +0.975 |
ONE | +0.974 |
discord | +0.929 |
orally | +0.924 |
Neg logit contributions | |
verts | -1.180 |
ements | -1.157 |
uez | -1.150 |
enhagen | -1.121 |
nces | -1.095 |
Token | , |
Token ID | 11 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
verts | +0.153 |
ements | +0.151 |
uez | +0.150 |
enhagen | +0.146 |
nces | +0.141 |
Neg logit contributions | |
rigging | -0.144 |
sparing | -0.141 |
ONE | -0.141 |
THING | -0.134 |
discord | -0.134 |
Token | Racing |
Token ID | 14954 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
verts | +0.847 |
ements | +0.838 |
uez | +0.825 |
enhagen | +0.805 |
nesses | +0.777 |
Neg logit contributions | |
rigging | -0.704 |
sparing | -0.692 |
ONE | -0.687 |
THING | -0.653 |
discord | -0.652 |
Token | Apex |
Token ID | 49440 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
rigging | +1.158 |
ONE | +1.148 |
sparing | +1.144 |
discord | +1.106 |
THING | +1.100 |
Neg logit contributions | |
verts | -0.904 |
ements | -0.888 |
uez | -0.877 |
enhagen | -0.858 |
nces | -0.818 |
Token | has |
Token ID | 468 |
Feature activation | +5.40e-02 |
Pos logit contributions | |
rigging | +2.683 |
sparing | +2.614 |
ONE | +2.552 |
centre | +2.511 |
discord | +2.493 |
Neg logit contributions | |
ements | -2.729 |
uez | -2.719 |
verts | -2.691 |
enhagen | -2.683 |
bats | -2.554 |
Token | a |
Token ID | 257 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
rigging | +0.266 |
sparing | +0.259 |
ONE | +0.254 |
discord | +0.243 |
centre | +0.241 |
Neg logit contributions | |
verts | -0.347 |
ements | -0.346 |
uez | -0.340 |
enhagen | -0.332 |
bats | -0.321 |
Token | th |
Token ID | 294 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
verts | +1.069 |
ements | +1.055 |
uez | +1.037 |
enhagen | +1.018 |
nces | +0.982 |
Neg logit contributions | |
rigging | -0.791 |
sparing | -0.776 |
ONE | -0.769 |
discord | -0.731 |
THING | -0.727 |
Token | umping |
Token ID | 25218 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
rigging | +8.207 |
centre | +8.198 |
ONE | +8.001 |
sparing | +7.907 |
underestimate | +7.623 |
Neg logit contributions | |
enhagen | -9.529 |
verts | -9.227 |
verages | -8.653 |
ements | -8.606 |
uez | -8.595 |
Token | original |
Token ID | 2656 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
rigging | +0.610 |
sparing | +0.579 |
ONE | +0.554 |
discord | +0.545 |
centre | +0.530 |
Neg logit contributions | |
verts | -1.813 |
ements | -1.791 |
uez | -1.755 |
enhagen | -1.753 |
nces | -1.708 |
Token | soundtrack |
Token ID | 21751 |
Feature activation | +6.05e-02 |
Pos logit contributions | |
rigging | +0.070 |
sparing | +0.066 |
ONE | +0.065 |
discord | +0.060 |
centre | +0.058 |
Neg logit contributions | |
verts | -0.278 |
ements | -0.276 |
uez | -0.271 |
enhagen | -0.268 |
verages | -0.262 |
Token | featuring |
Token ID | 9593 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
rigging | +0.329 |
sparing | +0.326 |
ONE | +0.320 |
discord | +0.309 |
centre | +0.306 |
Neg logit contributions | |
verts | -0.358 |
ements | -0.356 |
uez | -0.349 |
enhagen | -0.341 |
nesses | -0.331 |
Token | tracks |
Token ID | 8339 |
Feature activation | -4.40e-03 |
Pos logit contributions | |
rigging | +1.532 |
sparing | +1.512 |
ONE | +1.466 |
discord | +1.442 |
centre | +1.410 |
Neg logit contributions | |
verts | -1.785 |
ements | -1.773 |
uez | -1.743 |
enhagen | -1.695 |
nesses | -1.661 |
Token | draw |
Token ID | 3197 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
verts | +1.017 |
ements | +1.004 |
uez | +0.985 |
enhagen | +0.970 |
nces | +0.937 |
Neg logit contributions | |
rigging | -0.675 |
sparing | -0.667 |
ONE | -0.652 |
underestimate | -0.623 |
discord | -0.621 |
Token | us |
Token ID | 514 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
sparing | +3.410 |
rigging | +3.398 |
discord | +3.248 |
ONE | +3.242 |
centre | +3.200 |
Neg logit contributions | |
verts | -4.316 |
enhagen | -4.295 |
ements | -4.262 |
uez | -4.199 |
inventoryQuantity | -4.024 |
Token | out |
Token ID | 503 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
rigging | +2.055 |
sparing | +2.034 |
ONE | +1.973 |
discord | +1.922 |
centre | +1.919 |
Neg logit contributions | |
verts | -2.336 |
ements | -2.286 |
uez | -2.257 |
enhagen | -2.216 |
nces | -2.162 |
Token | of |
Token ID | 286 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
verts | +3.114 |
ements | +3.057 |
uez | +2.965 |
enhagen | +2.897 |
nesses | +2.788 |
Neg logit contributions | |
rigging | -3.366 |
ONE | -3.318 |
sparing | -3.311 |
THING | -3.179 |
Problem | -3.177 |
Token | the |
Token ID | 262 |
Feature activation | -8.02e-02 |
Pos logit contributions | |
verts | +0.703 |
ements | +0.697 |
uez | +0.684 |
enhagen | +0.668 |
nces | +0.648 |
Neg logit contributions | |
rigging | -0.563 |
sparing | -0.551 |
ONE | -0.549 |
discord | -0.527 |
THING | -0.522 |
Token | Great |
Token ID | 3878 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
verts | +0.557 |
ements | +0.550 |
uez | +0.542 |
enhagen | +0.534 |
nces | +0.519 |
Neg logit contributions | |
rigging | -0.355 |
ONE | -0.342 |
sparing | -0.342 |
discord | -0.328 |
Problem | -0.322 |
Token | Depression |
Token ID | 22483 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
rigging | +2.373 |
discord | +2.284 |
Problem | +2.186 |
ONE | +2.029 |
centre | +2.020 |
Neg logit contributions | |
enhagen | -15.120 |
verts | -15.066 |
ements | -14.937 |
nces | -14.834 |
inventoryQuantity | -14.675 |
Token | . |
Token ID | 13 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
verts | +0.997 |
ements | +0.982 |
uez | +0.963 |
enhagen | +0.934 |
nces | +0.905 |
Neg logit contributions | |
rigging | -0.911 |
sparing | -0.895 |
ONE | -0.892 |
discord | -0.850 |
THING | -0.849 |
Token | I |
Token ID | 314 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
ONE | +1.550 |
rigging | +1.539 |
sparing | +1.501 |
Problem | +1.476 |
THING | +1.465 |
Neg logit contributions | |
verts | -1.844 |
ements | -1.820 |
enhagen | -1.796 |
uez | -1.786 |
nces | -1.701 |
Token | see |
Token ID | 766 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
verts | +0.372 |
ements | +0.367 |
uez | +0.359 |
enhagen | +0.354 |
verages | +0.342 |
Neg logit contributions | |
rigging | -0.234 |
sparing | -0.231 |
ONE | -0.229 |
underestimate | -0.219 |
discord | -0.216 |
Token | one |
Token ID | 530 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
verts | +1.421 |
ements | +1.398 |
uez | +1.375 |
enhagen | +1.340 |
nces | +1.289 |
Neg logit contributions | |
rigging | -1.281 |
sparing | -1.258 |
ONE | -1.253 |
discord | -1.194 |
THING | -1.193 |
Token | eating |
Token ID | 6600 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
sparing | +1.883 |
rigging | +1.874 |
ONE | +1.782 |
centre | +1.726 |
discord | +1.726 |
Neg logit contributions | |
verts | -2.790 |
ements | -2.774 |
enhagen | -2.740 |
uez | -2.722 |
nces | -2.626 |
Token | anything |
Token ID | 1997 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
verts | +1.115 |
ements | +1.098 |
uez | +1.070 |
enhagen | +1.054 |
nces | +1.010 |
Neg logit contributions | |
rigging | -1.022 |
sparing | -1.017 |
ONE | -1.005 |
THING | -0.963 |
discord | -0.962 |
Token | else |
Token ID | 2073 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
verts | +1.037 |
ements | +1.021 |
uez | +0.998 |
enhagen | +0.982 |
nces | +0.942 |
Neg logit contributions | |
rigging | -0.889 |
sparing | -0.888 |
ONE | -0.878 |
THING | -0.843 |
discord | -0.840 |
Token | than |
Token ID | 621 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
verts | +1.646 |
ements | +1.623 |
uez | +1.593 |
enhagen | +1.555 |
nces | +1.501 |
Neg logit contributions | |
rigging | -1.347 |
sparing | -1.329 |
ONE | -1.324 |
THING | -1.259 |
discord | -1.255 |
Token | Red |
Token ID | 2297 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
sparing | +0.915 |
rigging | +0.908 |
ONE | +0.899 |
THING | +0.862 |
discord | +0.859 |
Neg logit contributions | |
verts | -1.022 |
ements | -1.014 |
enhagen | -1.000 |
uez | -0.987 |
nces | -0.942 |
Token | th |
Token ID | 294 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
sparing | +4.155 |
rigging | +4.128 |
ONE | +4.111 |
centre | +3.977 |
THING | +3.946 |
Neg logit contributions | |
ements | -6.005 |
verts | -5.948 |
uez | -5.797 |
enhagen | -5.762 |
nces | -5.577 |
Token | ai |
Token ID | 1872 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
ONE | +2.702 |
centre | +2.261 |
sparing | +2.083 |
strap | +1.992 |
ousing | +1.975 |
Neg logit contributions | |
verts | -14.723 |
verages | -14.495 |
ements | -14.424 |
enhagen | -14.311 |
nesses | -14.122 |
Token | curry |
Token ID | 34611 |
Feature activation | +9.18e-02 |
Pos logit contributions | |
sparing | +1.841 |
rigging | +1.798 |
ONE | +1.756 |
centre | +1.727 |
discord | +1.691 |
Neg logit contributions | |
verts | -2.866 |
ements | -2.844 |
uez | -2.802 |
enhagen | -2.797 |
nces | -2.670 |
Token | for |
Token ID | 329 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
sparing | +0.459 |
rigging | +0.458 |
ONE | +0.449 |
discord | +0.428 |
centre | +0.428 |
Neg logit contributions | |
verts | -0.577 |
ements | -0.572 |
uez | -0.563 |
enhagen | -0.553 |
nces | -0.530 |
Token | the |
Token ID | 262 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
sparing | +1.358 |
rigging | +1.350 |
ONE | +1.316 |
discord | +1.273 |
centre | +1.266 |
Neg logit contributions | |
verts | -1.558 |
ements | -1.551 |
uez | -1.527 |
enhagen | -1.499 |
verages | -1.443 |
Token | rest |
Token ID | 1334 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
verts | +2.685 |
ements | +2.653 |
uez | +2.615 |
enhagen | +2.559 |
nces | +2.491 |
Neg logit contributions | |
rigging | -1.290 |
sparing | -1.258 |
ONE | -1.253 |
THING | -1.166 |
discord | -1.162 |
Token | army |
Token ID | 5428 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
rigging | +0.413 |
sparing | +0.410 |
ONE | +0.402 |
underestimate | +0.389 |
discord | +0.386 |
Neg logit contributions | |
verts | -0.609 |
ements | -0.595 |
uez | -0.583 |
enhagen | -0.575 |
nesses | -0.558 |
Token | of |
Token ID | 286 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
verts | +1.744 |
ements | +1.710 |
uez | +1.680 |
enhagen | +1.633 |
nces | +1.574 |
Neg logit contributions | |
rigging | -1.747 |
sparing | -1.720 |
ONE | -1.709 |
discord | -1.634 |
THING | -1.633 |
Token | Hu |
Token ID | 11256 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
verts | +0.896 |
ements | +0.880 |
uez | +0.871 |
enhagen | +0.849 |
nces | +0.819 |
Neg logit contributions | |
rigging | -0.802 |
sparing | -0.790 |
ONE | -0.780 |
discord | -0.750 |
underestimate | -0.742 |
Token | orns |
Token ID | 19942 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ONE | +1.526 |
rigging | +1.521 |
sparing | +1.512 |
THING | +1.442 |
discord | +1.433 |
Neg logit contributions | |
verts | -1.573 |
ements | -1.571 |
uez | -1.529 |
enhagen | -1.521 |
nces | -1.469 |
Token | to |
Token ID | 284 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
rigging | +0.755 |
sparing | +0.751 |
ONE | +0.734 |
discord | +0.708 |
underestimate | +0.699 |
Neg logit contributions | |
verts | -0.794 |
ements | -0.774 |
uez | -0.759 |
enhagen | -0.749 |
nces | -0.721 |
Token | Th |
Token ID | 536 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
rigging | +1.533 |
sparing | +1.507 |
ONE | +1.425 |
discord | +1.402 |
centre | +1.396 |
Neg logit contributions | |
verts | -2.346 |
ements | -2.327 |
uez | -2.260 |
enhagen | -2.242 |
nces | -2.188 |
Token | é |
Token ID | 2634 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
ONE | +5.218 |
centre | +4.869 |
rigging | +4.853 |
restling | +4.585 |
ousing | +4.522 |
Neg logit contributions | |
verts | -11.981 |
bats | -11.449 |
inventoryQuantity | -11.443 |
nces | -11.342 |
enhagen | -11.318 |
Token | od |
Token ID | 375 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
ONE | +0.857 |
rigging | +0.855 |
sparing | +0.839 |
THING | +0.807 |
discord | +0.798 |
Neg logit contributions | |
verts | -0.987 |
ements | -0.980 |
uez | -0.952 |
enhagen | -0.944 |
nesses | -0.906 |
Token | en |
Token ID | 268 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
rigging | +2.097 |
ONE | +2.094 |
sparing | +2.074 |
centre | +1.997 |
discord | +1.985 |
Neg logit contributions | |
verts | -2.503 |
ements | -2.448 |
uez | -2.416 |
enhagen | -2.359 |
verages | -2.336 |
Token | 's |
Token ID | 338 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
sparing | +1.892 |
rigging | +1.889 |
ONE | +1.820 |
discord | +1.750 |
centre | +1.742 |
Neg logit contributions | |
verts | -2.212 |
ements | -2.189 |
uez | -2.144 |
enhagen | -2.084 |
nesses | -2.045 |
Token | aid |
Token ID | 6133 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
rigging | +1.204 |
sparing | +1.167 |
ONE | +1.141 |
discord | +1.098 |
centre | +1.096 |
Neg logit contributions | |
verts | -2.071 |
uez | -2.040 |
ements | -2.038 |
enhagen | -1.989 |
nces | -1.940 |
Token | States |
Token ID | 1829 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
verts | +0.908 |
ements | +0.889 |
uez | +0.875 |
enhagen | +0.860 |
nces | +0.827 |
Neg logit contributions | |
rigging | -0.797 |
ONE | -0.785 |
sparing | -0.784 |
discord | -0.748 |
THING | -0.747 |
Token | Air |
Token ID | 3701 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
verts | +1.758 |
ements | +1.729 |
uez | +1.699 |
enhagen | +1.657 |
nces | +1.597 |
Neg logit contributions | |
rigging | -1.469 |
sparing | -1.447 |
ONE | -1.442 |
THING | -1.376 |
discord | -1.370 |
Token | Force |
Token ID | 5221 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
verts | +0.784 |
ements | +0.775 |
uez | +0.771 |
enhagen | +0.743 |
nesses | +0.702 |
Neg logit contributions | |
rigging | -0.943 |
sparing | -0.929 |
ONE | -0.928 |
centre | -0.902 |
discord | -0.896 |
Token | in |
Token ID | 287 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
verts | +3.343 |
ements | +3.282 |
uez | +3.230 |
enhagen | +3.156 |
nces | +3.044 |
Neg logit contributions | |
rigging | -2.817 |
sparing | -2.748 |
ONE | -2.745 |
THING | -2.621 |
Problem | -2.614 |
Token | Dayton |
Token ID | 24450 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
rigging | +1.392 |
sparing | +1.351 |
ONE | +1.349 |
discord | +1.317 |
centre | +1.313 |
Neg logit contributions | |
ements | -1.402 |
verts | -1.396 |
uez | -1.390 |
enhagen | -1.335 |
nesses | -1.308 |
Token | , |
Token ID | 11 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
ONE | +4.123 |
rigging | +3.989 |
sparing | +3.934 |
discord | +3.824 |
centre | +3.815 |
Neg logit contributions | |
ements | -5.634 |
verts | -5.617 |
uez | -5.528 |
inventoryQuantity | -5.251 |
nesses | -5.182 |
Token | Ohio |
Token ID | 6835 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
sparing | +5.312 |
ONE | +5.243 |
discord | +4.817 |
rigging | +4.665 |
centre | +4.586 |
Neg logit contributions | |
verts | -12.656 |
uez | -12.394 |
ements | -12.381 |
inventoryQuantity | -12.180 |
acters | -11.745 |
Token | . |
Token ID | 13 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
rigging | +3.771 |
sparing | +3.750 |
ONE | +3.682 |
centre | +3.564 |
discord | +3.532 |
Neg logit contributions | |
verts | -5.046 |
ements | -4.985 |
uez | -4.922 |
verages | -4.633 |
enhagen | -4.626 |
Token | By |
Token ID | 2750 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
verts | +0.936 |
ements | +0.923 |
uez | +0.903 |
enhagen | +0.878 |
nces | +0.850 |
Neg logit contributions | |
rigging | -0.834 |
ONE | -0.825 |
sparing | -0.818 |
THING | -0.783 |
Problem | -0.781 |
Token | 1986 |
Token ID | 12113 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
verts | +2.617 |
ements | +2.574 |
uez | +2.525 |
enhagen | +2.457 |
nces | +2.373 |
Neg logit contributions | |
rigging | -2.277 |
ONE | -2.237 |
sparing | -2.236 |
THING | -2.129 |
Problem | -2.121 |
Token | , |
Token ID | 11 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
rigging | +1.657 |
sparing | +1.619 |
ONE | +1.619 |
orally | +1.536 |
underestimate | +1.533 |
Neg logit contributions | |
verts | -1.936 |
ements | -1.927 |
uez | -1.870 |
enhagen | -1.785 |
nesses | -1.753 |
Token | O |
Token ID | 440 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
ONE | +5.489 |
THING | +5.174 |
rigging | +5.133 |
sparing | +4.960 |
SQU | +4.823 |
Neg logit contributions | |
verts | -7.180 |
ements | -7.165 |
enhagen | -6.978 |
uez | -6.975 |
inventoryQuantity | -6.733 |
Token | SC |
Token ID | 6173 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
verts | +2.083 |
ements | +2.054 |
uez | +2.023 |
enhagen | +1.975 |
nces | +1.919 |
Neg logit contributions | |
rigging | -1.271 |
ONE | -1.243 |
sparing | -1.242 |
THING | -1.168 |
discord | -1.162 |
Token | ILL |
Token ID | 8267 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
verts | +1.411 |
ements | +1.392 |
uez | +1.371 |
enhagen | +1.343 |
nces | +1.309 |
Neg logit contributions | |
rigging | -0.678 |
ONE | -0.665 |
sparing | -0.659 |
THING | -0.617 |
discord | -0.611 |
Token | ATION |
Token ID | 6234 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
ONE | +0.471 |
rigging | +0.464 |
sparing | +0.451 |
THING | +0.438 |
discord | +0.429 |
Neg logit contributions | |
verts | -0.778 |
ements | -0.768 |
uez | -0.749 |
enhagen | -0.740 |
nces | -0.722 |
Token | , |
Token ID | 11 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
rigging | +0.947 |
ONE | +0.947 |
sparing | +0.924 |
THING | +0.893 |
Problem | +0.882 |
Neg logit contributions | |
verts | -1.235 |
ements | -1.222 |
uez | -1.199 |
enhagen | -1.178 |
nces | -1.137 |
Token | TH |
Token ID | 2320 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
rigging | +1.708 |
ONE | +1.708 |
sparing | +1.667 |
THING | +1.611 |
discord | +1.587 |
Neg logit contributions | |
verts | -2.105 |
ements | -2.079 |
uez | -2.046 |
enhagen | -2.012 |
nces | -1.959 |
Token | ER |
Token ID | 1137 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
ONE | +7.255 |
INK | +6.349 |
THING | +6.339 |
rigging | +6.006 |
HI | +5.943 |
Neg logit contributions | |
enhagen | -11.174 |
verts | -10.899 |
ements | -10.676 |
uyomi | -10.583 |
nces | -10.578 |
Token | MAL |
Token ID | 42126 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
verts | +4.653 |
ements | +4.579 |
uez | +4.475 |
enhagen | +4.192 |
nesses | +4.181 |
Neg logit contributions | |
rigging | -4.213 |
sparing | -4.158 |
underestimate | -3.909 |
ONE | -3.898 |
discord | -3.864 |
Token | BRE |
Token ID | 29377 |
Feature activation | -7.50e-02 |
Pos logit contributions | |
ONE | +3.520 |
rigging | +3.368 |
THING | +3.285 |
sparing | +3.213 |
Problem | +3.138 |
Neg logit contributions | |
verts | -4.658 |
ements | -4.604 |
enhagen | -4.530 |
uez | -4.481 |
nces | -4.402 |
Token | ATH |
Token ID | 12599 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
verts | +0.527 |
ements | +0.522 |
uez | +0.513 |
enhagen | +0.507 |
nces | +0.490 |
Neg logit contributions | |
rigging | -0.320 |
ONE | -0.320 |
sparing | -0.308 |
THING | -0.302 |
Problem | -0.296 |
Token | ING |
Token ID | 2751 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
ONE | +2.708 |
rigging | +2.583 |
THING | +2.550 |
sparing | +2.478 |
Problem | +2.442 |
Neg logit contributions | |
verts | -3.612 |
uez | -3.496 |
ements | -3.494 |
enhagen | -3.440 |
verages | -3.349 |
Token | fortunate |
Token ID | 20200 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
rigging | +1.428 |
sparing | +1.421 |
ONE | +1.401 |
discord | +1.357 |
centre | +1.331 |
Neg logit contributions | |
verts | -1.917 |
uez | -1.870 |
ements | -1.870 |
enhagen | -1.845 |
bats | -1.770 |
Token | conditions |
Token ID | 3403 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
verts | +0.564 |
ements | +0.546 |
uez | +0.542 |
enhagen | +0.528 |
nces | +0.502 |
Neg logit contributions | |
rigging | -0.639 |
sparing | -0.628 |
ONE | -0.626 |
discord | -0.603 |
THING | -0.596 |
Token | . |
Token ID | 13 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
verts | +0.853 |
ements | +0.837 |
uez | +0.825 |
enhagen | +0.798 |
nesses | +0.773 |
Neg logit contributions | |
rigging | -0.770 |
sparing | -0.759 |
ONE | -0.755 |
discord | -0.718 |
THING | -0.718 |
Token | As |
Token ID | 1081 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
rigging | +0.086 |
sparing | +0.085 |
ONE | +0.085 |
discord | +0.081 |
THING | +0.081 |
Neg logit contributions | |
verts | -0.096 |
ements | -0.095 |
uez | -0.093 |
enhagen | -0.091 |
nces | -0.088 |
Token | you |
Token ID | 345 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
rigging | +0.574 |
sparing | +0.570 |
ONE | +0.567 |
discord | +0.539 |
THING | +0.535 |
Neg logit contributions | |
verts | -0.750 |
ements | -0.732 |
uez | -0.731 |
enhagen | -0.711 |
nesses | -0.689 |
Token | may |
Token ID | 743 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
sparing | +2.753 |
rigging | +2.641 |
underestimate | +2.602 |
ONE | +2.601 |
centre | +2.543 |
Neg logit contributions | |
verts | -5.289 |
ements | -5.222 |
uez | -5.181 |
enhagen | -5.040 |
bats | -4.955 |
Token | know |
Token ID | 760 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
underestimate | +4.974 |
sparing | +4.958 |
orally | +4.858 |
rigging | +4.676 |
resonate | +4.642 |
Neg logit contributions | |
verts | -12.772 |
uez | -12.344 |
ements | -12.180 |
enhagen | -12.018 |
inventoryQuantity | -11.917 |
Token | I |
Token ID | 314 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
rigging | +4.533 |
ONE | +4.437 |
sparing | +4.425 |
discord | +4.238 |
orally | +4.229 |
Neg logit contributions | |
verts | -6.060 |
ements | -5.929 |
uez | -5.850 |
enhagen | -5.741 |
verages | -5.614 |
Token | � |
Token ID | 447 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
rigging | +1.566 |
sparing | +1.562 |
ONE | +1.556 |
underestimate | +1.486 |
centre | +1.478 |
Neg logit contributions | |
verts | -2.412 |
ements | -2.384 |
uez | -2.324 |
enhagen | -2.295 |
bats | -2.225 |
Token | � |
Token ID | 247 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
verts | +1.451 |
ements | +1.426 |
uez | +1.400 |
enhagen | +1.359 |
nces | +1.311 |
Neg logit contributions | |
rigging | -1.382 |
sparing | -1.357 |
ONE | -1.356 |
THING | -1.294 |
discord | -1.290 |
Token | m |
Token ID | 76 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
verts | +0.543 |
ements | +0.537 |
uez | +0.529 |
enhagen | +0.519 |
nces | +0.504 |
Neg logit contributions | |
rigging | -0.244 |
ONE | -0.238 |
sparing | -0.237 |
THING | -0.220 |
discord | -0.219 |
Token |
|
Token ID | 198 |
Feature activation | +5.43e-03 |
Pos logit contributions | |
verts | +0.097 |
ements | +0.097 |
uez | +0.095 |
enhagen | +0.094 |
nces | +0.090 |
Neg logit contributions | |
ONE | -0.076 |
rigging | -0.076 |
sparing | -0.074 |
Problem | -0.072 |
THING | -0.072 |
Token | P |
Token ID | 47 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
ONE | +0.026 |
rigging | +0.026 |
sparing | +0.025 |
Problem | +0.025 |
THING | +0.025 |
Neg logit contributions | |
verts | -0.035 |
ements | -0.035 |
uez | -0.034 |
enhagen | -0.034 |
nces | -0.033 |
Token | AS |
Token ID | 1921 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
ONE | +1.313 |
rigging | +1.292 |
sparing | +1.252 |
THING | +1.204 |
Problem | +1.202 |
Neg logit contributions | |
verts | -1.629 |
ements | -1.599 |
uez | -1.548 |
nces | -1.531 |
enhagen | -1.528 |
Token | AD |
Token ID | 2885 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
ONE | +1.505 |
rigging | +1.393 |
THING | +1.327 |
sparing | +1.307 |
discord | +1.255 |
Neg logit contributions | |
verts | -5.132 |
ements | -5.076 |
uez | -5.056 |
enhagen | -5.053 |
nces | -4.949 |
Token | ENA |
Token ID | 45510 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ONE | +0.898 |
rigging | +0.673 |
THING | +0.666 |
sparing | +0.568 |
HI | +0.552 |
Neg logit contributions | |
ements | -4.912 |
verts | -4.903 |
enhagen | -4.882 |
nces | -4.788 |
uez | -4.780 |
Token | , |
Token ID | 11 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ONE | +5.549 |
rigging | +5.282 |
sparing | +5.109 |
discord | +5.086 |
THING | +5.044 |
Neg logit contributions | |
ements | -7.921 |
verts | -7.856 |
nces | -7.727 |
uez | -7.671 |
inventoryQuantity | -7.463 |
Token | Calif |
Token ID | 3192 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
ONE | +5.767 |
sparing | +5.425 |
rigging | +5.381 |
centre | +5.351 |
discord | +5.117 |
Neg logit contributions | |
inventoryQuantity | -11.993 |
enhagen | -11.976 |
verts | -11.855 |
nces | -11.840 |
ements | -11.502 |
Token | . |
Token ID | 13 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
ONE | +2.957 |
rigging | +2.856 |
sparing | +2.838 |
Problem | +2.771 |
THING | +2.751 |
Neg logit contributions | |
verts | -3.393 |
ements | -3.329 |
uez | -3.275 |
enhagen | -3.192 |
nces | -3.162 |
Token | -- |
Token ID | 1377 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
ONE | +1.908 |
rigging | +1.858 |
sparing | +1.848 |
Problem | +1.764 |
THING | +1.759 |
Neg logit contributions | |
verts | -3.677 |
ements | -3.616 |
uez | -3.589 |
enhagen | -3.520 |
nces | -3.498 |
Token | The |
Token ID | 383 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
verts | +1.853 |
ements | +1.818 |
uez | +1.783 |
enhagen | +1.726 |
nces | +1.662 |
Neg logit contributions | |
rigging | -1.969 |
sparing | -1.936 |
ONE | -1.932 |
THING | -1.849 |
discord | -1.844 |
Token | first |
Token ID | 717 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
verts | +1.114 |
ements | +1.097 |
uez | +1.076 |
enhagen | +1.045 |
nces | +1.017 |
Neg logit contributions | |
rigging | -1.063 |
sparing | -1.042 |
ONE | -1.036 |
discord | -0.991 |
THING | -0.985 |
Token | Obama |
Token ID | 2486 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
rigging | +0.716 |
sparing | +0.696 |
ONE | +0.696 |
discord | +0.664 |
THING | +0.663 |
Neg logit contributions | |
verts | -0.785 |
ements | -0.772 |
uez | -0.757 |
enhagen | -0.742 |
nces | -0.717 |
Token | , |
Token ID | 11 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
verts | +2.503 |
ements | +2.456 |
uez | +2.405 |
enhagen | +2.342 |
nesses | +2.257 |
Neg logit contributions | |
rigging | -2.473 |
ONE | -2.449 |
sparing | -2.437 |
THING | -2.332 |
Problem | -2.324 |
Token | they |
Token ID | 484 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
rigging | +0.908 |
sparing | +0.896 |
ONE | +0.872 |
discord | +0.847 |
centre | +0.843 |
Neg logit contributions | |
verts | -0.950 |
ements | -0.947 |
uez | -0.924 |
enhagen | -0.915 |
nesses | -0.878 |
Token | in |
Token ID | 287 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
rigging | +2.618 |
sparing | +2.610 |
underestimate | +2.489 |
centre | +2.466 |
resonate | +2.442 |
Neg logit contributions | |
verts | -4.365 |
ements | -4.329 |
enhagen | -4.235 |
uez | -4.224 |
verages | -4.105 |
Token | |
Token ID | 3907 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
verts | +2.137 |
ements | +2.062 |
uez | +2.011 |
enhagen | +1.937 |
nces | +1.874 |
Neg logit contributions | |
rigging | -2.634 |
sparing | -2.597 |
ONE | -2.596 |
THING | -2.500 |
discord | -2.476 |
Token | v |
Token ID | 85 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
verts | +9.187 |
ements | +8.690 |
uez | +8.425 |
bats | +8.223 |
enhagen | +8.205 |
Neg logit contributions | |
rigging | -5.883 |
sparing | -5.785 |
ONE | -5.724 |
THING | -5.552 |
Problem | -5.406 |
Token | oke |
Token ID | 2088 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
verts | +10.100 |
ements | +9.829 |
uez | +9.713 |
ellig | +9.474 |
enhagen | +9.028 |
Neg logit contributions | |
rigging | -11.503 |
sparing | -11.431 |
juggling | -10.852 |
THING | -10.523 |
Nebula | -10.444 |
Token | him |
Token ID | 683 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
verts | +0.791 |
ements | +0.781 |
uez | +0.769 |
enhagen | +0.751 |
nesses | +0.724 |
Neg logit contributions | |
rigging | -0.653 |
sparing | -0.639 |
ONE | -0.633 |
discord | -0.610 |
THING | -0.601 |
Token | . |
Token ID | 13 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
verts | +0.907 |
ements | +0.893 |
uez | +0.878 |
enhagen | +0.853 |
nesses | +0.822 |
Neg logit contributions | |
rigging | -0.834 |
sparing | -0.822 |
ONE | -0.811 |
discord | -0.778 |
THING | -0.775 |
Token | � |
Token ID | 564 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
verts | +0.322 |
ements | +0.320 |
uez | +0.314 |
enhagen | +0.310 |
nces | +0.296 |
Neg logit contributions | |
rigging | -0.276 |
ONE | -0.275 |
sparing | -0.270 |
Problem | -0.262 |
THING | -0.261 |
Token | � |
Token ID | 250 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
rigging | +0.977 |
sparing | +0.961 |
ONE | +0.960 |
Problem | +0.913 |
discord | +0.906 |
Neg logit contributions | |
verts | -1.163 |
ements | -1.151 |
uez | -1.128 |
enhagen | -1.106 |
nces | -1.061 |
Token | registered |
Token ID | 6823 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
rigging | +0.952 |
sparing | +0.933 |
ONE | +0.912 |
discord | +0.885 |
centre | +0.874 |
Neg logit contributions | |
verts | -1.062 |
ements | -1.056 |
uez | -1.039 |
enhagen | -1.024 |
nces | -0.987 |
Token | voters |
Token ID | 4446 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
verts | +2.519 |
ements | +2.477 |
uez | +2.432 |
enhagen | +2.362 |
nces | +2.279 |
Neg logit contributions | |
rigging | -2.422 |
sparing | -2.378 |
ONE | -2.375 |
THING | -2.264 |
discord | -2.261 |
Token | , |
Token ID | 11 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
verts | +1.138 |
ements | +1.121 |
uez | +1.105 |
enhagen | +1.071 |
nesses | +1.037 |
Neg logit contributions | |
rigging | -1.041 |
sparing | -1.022 |
ONE | -1.018 |
discord | -0.971 |
THING | -0.964 |
Token | i |
Token ID | 1312 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
verts | +2.620 |
ements | +2.577 |
uez | +2.531 |
enhagen | +2.460 |
nces | +2.378 |
Neg logit contributions | |
rigging | -2.290 |
sparing | -2.247 |
ONE | -2.246 |
THING | -2.138 |
discord | -2.130 |
Token | . |
Token ID | 13 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
verts | +4.428 |
ements | +4.362 |
uez | +4.236 |
enhagen | +4.057 |
nesses | +3.905 |
Neg logit contributions | |
rigging | -5.068 |
sparing | -5.008 |
ONE | -4.983 |
THING | -4.823 |
discord | -4.799 |
Token | e |
Token ID | 68 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
verts | +3.516 |
ements | +3.492 |
uez | +3.371 |
enhagen | +3.227 |
nesses | +3.180 |
Neg logit contributions | |
rigging | -2.623 |
sparing | -2.565 |
ONE | -2.512 |
underestimate | -2.407 |
discord | -2.405 |
Token | . |
Token ID | 13 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
verts | +7.186 |
ements | +7.104 |
uez | +6.717 |
enhagen | +6.471 |
nces | +6.339 |
Neg logit contributions | |
rigging | -12.247 |
sparing | -12.097 |
ONE | -11.992 |
THING | -11.821 |
discord | -11.754 |
Token | those |
Token ID | 883 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
verts | +3.144 |
ements | +3.085 |
uez | +3.029 |
enhagen | +2.935 |
nces | +2.839 |
Neg logit contributions | |
rigging | -2.888 |
ONE | -2.838 |
sparing | -2.836 |
THING | -2.714 |
Problem | -2.702 |
Token | who |
Token ID | 508 |
Feature activation | +8.55e-02 |
Pos logit contributions | |
verts | +1.338 |
ements | +1.318 |
uez | +1.295 |
enhagen | +1.258 |
nesses | +1.207 |
Neg logit contributions | |
rigging | -1.461 |
sparing | -1.437 |
ONE | -1.433 |
discord | -1.373 |
THING | -1.362 |
Token | voted |
Token ID | 7052 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
rigging | +0.366 |
sparing | +0.356 |
ONE | +0.352 |
underestimate | +0.341 |
discord | +0.339 |
Neg logit contributions | |
verts | -0.600 |
ements | -0.598 |
uez | -0.584 |
enhagen | -0.576 |
nces | -0.558 |
Token | in |
Token ID | 287 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
verts | +3.904 |
ements | +3.823 |
uez | +3.749 |
enhagen | +3.642 |
nces | +3.527 |
Neg logit contributions | |
rigging | -3.191 |
ONE | -3.152 |
sparing | -3.120 |
Problem | -3.024 |
THING | -3.005 |
Token | improvis |
Token ID | 47833 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
rigging | +2.513 |
sparing | +2.473 |
ONE | +2.354 |
discord | +2.322 |
underestimate | +2.260 |
Neg logit contributions | |
verts | -3.876 |
ements | -3.834 |
uez | -3.769 |
enhagen | -3.676 |
nces | -3.638 |
Token | ation |
Token ID | 341 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
verts | +0.854 |
ements | +0.839 |
uez | +0.825 |
enhagen | +0.803 |
nces | +0.777 |
Neg logit contributions | |
rigging | -0.721 |
sparing | -0.708 |
ONE | -0.707 |
THING | -0.672 |
discord | -0.670 |
Token | ( |
Token ID | 357 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
rigging | +1.295 |
sparing | +1.270 |
ONE | +1.244 |
discord | +1.205 |
underestimate | +1.185 |
Neg logit contributions | |
verts | -1.526 |
ements | -1.505 |
uez | -1.483 |
enhagen | -1.435 |
nces | -1.402 |
Token | e |
Token ID | 68 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ONE | +1.069 |
rigging | +1.061 |
sparing | +1.046 |
Problem | +1.016 |
THING | +0.999 |
Neg logit contributions | |
verts | -1.319 |
ements | -1.308 |
uez | -1.288 |
enhagen | -1.262 |
nces | -1.214 |
Token | . |
Token ID | 13 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
verts | +5.397 |
ements | +5.214 |
uez | +5.046 |
enhagen | +4.644 |
nesses | +4.615 |
Neg logit contributions | |
rigging | -6.888 |
sparing | -6.704 |
ONE | -6.534 |
THING | -6.437 |
resonate | -6.399 |
Token | g |
Token ID | 70 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
verts | +4.591 |
ements | +4.504 |
uez | +4.359 |
enhagen | +4.109 |
nesses | +4.084 |
Neg logit contributions | |
rigging | -4.860 |
sparing | -4.779 |
ONE | -4.739 |
discord | -4.538 |
resonate | -4.532 |
Token | ., |
Token ID | 1539 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
verts | +5.207 |
uez | +5.085 |
ements | +4.992 |
enhagen | +4.640 |
ellig | +4.513 |
Neg logit contributions | |
rigging | -14.214 |
sparing | -14.035 |
captcha | -13.767 |
ONE | -13.718 |
THING | -13.705 |
Token | Berlin |
Token ID | 11307 |
Feature activation | -7.12e-03 |
Pos logit contributions | |
verts | +2.151 |
ements | +2.119 |
uez | +2.083 |
enhagen | +2.029 |
nces | +1.966 |
Neg logit contributions | |
rigging | -1.613 |
sparing | -1.583 |
ONE | -1.578 |
THING | -1.493 |
discord | -1.492 |
Token | er |
Token ID | 263 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
verts | +0.044 |
ements | +0.043 |
uez | +0.042 |
enhagen | +0.041 |
nces | +0.040 |
Neg logit contributions | |
rigging | -0.037 |
sparing | -0.036 |
ONE | -0.036 |
discord | -0.034 |
Problem | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
verts | +3.445 |
ements | +3.379 |
uez | +3.307 |
enhagen | +3.229 |
nces | +3.100 |
Neg logit contributions | |
rigging | -3.061 |
ONE | -3.017 |
sparing | -2.992 |
THING | -2.879 |
Problem | -2.846 |
Token | 1994 |
Token ID | 9162 |
Feature activation | +9.95e-02 |
Pos logit contributions | |
verts | +4.274 |
ements | +4.187 |
uez | +4.100 |
enhagen | +3.944 |
nesses | +3.775 |
Neg logit contributions | |
rigging | -4.831 |
ONE | -4.753 |
sparing | -4.715 |
THING | -4.574 |
Problem | -4.535 |
Token | was |
Token ID | 373 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
verts | +1.507 |
ements | +1.481 |
uez | +1.458 |
enhagen | +1.427 |
nesses | +1.383 |
Neg logit contributions | |
rigging | -1.132 |
sparing | -1.117 |
ONE | -1.096 |
discord | -1.050 |
centre | -1.042 |
Token | named |
Token ID | 3706 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
verts | +1.709 |
ements | +1.682 |
uez | +1.653 |
enhagen | +1.608 |
nces | +1.555 |
Neg logit contributions | |
rigging | -1.419 |
sparing | -1.392 |
ONE | -1.391 |
THING | -1.322 |
discord | -1.317 |
Token | to |
Token ID | 284 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
verts | +0.563 |
ements | +0.554 |
uez | +0.547 |
enhagen | +0.531 |
nesses | +0.512 |
Neg logit contributions | |
rigging | -0.476 |
sparing | -0.469 |
ONE | -0.468 |
discord | -0.443 |
THING | -0.443 |
Token | the |
Token ID | 262 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
verts | +0.647 |
ements | +0.635 |
uez | +0.626 |
enhagen | +0.604 |
nesses | +0.583 |
Neg logit contributions | |
rigging | -0.643 |
ONE | -0.632 |
sparing | -0.632 |
THING | -0.602 |
discord | -0.601 |
Token | John |
Token ID | 1757 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
verts | +0.290 |
ements | +0.284 |
uez | +0.281 |
enhagen | +0.272 |
nces | +0.264 |
Neg logit contributions | |
rigging | -0.259 |
ONE | -0.255 |
sparing | -0.255 |
discord | -0.242 |
THING | -0.240 |
Token | R |
Token ID | 371 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
sparing | +1.492 |
rigging | +1.490 |
ONE | +1.474 |
discord | +1.419 |
centre | +1.392 |
Neg logit contributions | |
verts | -1.888 |
ements | -1.883 |
enhagen | -1.841 |
uez | -1.834 |
nces | -1.764 |
Token | . |
Token ID | 13 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
ements | +7.413 |
uez | +7.335 |
verts | +7.125 |
ellig | +6.544 |
nesses | +6.220 |
Neg logit contributions | |
rigging | -12.202 |
captcha | -11.970 |
sparing | -11.949 |
resonate | -11.502 |
THING | -11.446 |
Token | Wooden |
Token ID | 40143 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
verts | +3.813 |
ements | +3.741 |
uez | +3.691 |
enhagen | +3.528 |
nesses | +3.392 |
Neg logit contributions | |
rigging | -4.177 |
sparing | -4.120 |
ONE | -4.078 |
THING | -3.935 |
Problem | -3.911 |
Token | Award |
Token ID | 11289 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
rigging | +0.137 |
ONE | +0.134 |
sparing | +0.134 |
discord | +0.119 |
Problem | +0.118 |
Neg logit contributions | |
verts | -0.496 |
ements | -0.491 |
uez | -0.484 |
enhagen | -0.474 |
nces | -0.466 |
Token | Mid |
Token ID | 7215 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
rigging | +0.333 |
sparing | +0.329 |
ONE | +0.326 |
Problem | +0.310 |
discord | +0.310 |
Neg logit contributions | |
verts | -0.408 |
ements | -0.406 |
uez | -0.398 |
enhagen | -0.384 |
nces | -0.376 |
Token | season |
Token ID | 6230 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
verts | +1.291 |
ements | +1.273 |
uez | +1.255 |
enhagen | +1.222 |
nces | +1.184 |
Neg logit contributions | |
rigging | -0.910 |
ONE | -0.893 |
sparing | -0.891 |
THING | -0.842 |
Problem | -0.840 |
Token | , |
Token ID | 11 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
verts | +4.130 |
ements | +4.101 |
uez | +4.015 |
enhagen | +3.827 |
nces | +3.734 |
Neg logit contributions | |
rigging | -4.353 |
sparing | -4.343 |
ONE | -4.254 |
THING | -4.087 |
discord | -4.074 |
Token | 500 |
Token ID | 4059 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
rigging | +1.709 |
sparing | +1.688 |
ONE | +1.682 |
discord | +1.579 |
centre | +1.576 |
Neg logit contributions | |
verts | -2.406 |
ements | -2.348 |
uez | -2.321 |
enhagen | -2.283 |
nesses | -2.199 |
Token | of |
Token ID | 286 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
verts | +2.677 |
ements | +2.636 |
uez | +2.593 |
enhagen | +2.528 |
nces | +2.446 |
Neg logit contributions | |
rigging | -2.015 |
ONE | -1.973 |
sparing | -1.972 |
THING | -1.867 |
discord | -1.863 |
Token | them |
Token ID | 606 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
verts | +2.218 |
ements | +2.180 |
uez | +2.138 |
enhagen | +2.074 |
nces | +1.996 |
Neg logit contributions | |
rigging | -2.418 |
sparing | -2.373 |
ONE | -2.371 |
discord | -2.270 |
THING | -2.267 |
Token | — |
Token ID | 960 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
verts | +2.868 |
ements | +2.822 |
uez | +2.776 |
enhagen | +2.699 |
nces | +2.617 |
Neg logit contributions | |
rigging | -2.194 |
sparing | -2.155 |
ONE | -2.150 |
THING | -2.043 |
Problem | -2.028 |
Token | con |
Token ID | 1102 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
verts | +2.501 |
ements | +2.455 |
uez | +2.405 |
enhagen | +2.345 |
nesses | +2.269 |
Neg logit contributions | |
rigging | -2.129 |
sparing | -2.093 |
ONE | -2.079 |
THING | -1.981 |
discord | -1.973 |
Token | cern |
Token ID | 30903 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
verts | +11.430 |
ements | +10.172 |
uez | +9.701 |
ellig | +9.678 |
enhagen | +9.494 |
Neg logit contributions | |
sparing | -9.065 |
ONE | -9.061 |
rigging | -8.974 |
THING | -8.597 |
orally | -8.315 |
Token | mortgage |
Token ID | 13682 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
verts | +1.590 |
ements | +1.564 |
uez | +1.541 |
enhagen | +1.499 |
nces | +1.451 |
Neg logit contributions | |
rigging | -1.342 |
ONE | -1.308 |
sparing | -1.307 |
THING | -1.245 |
discord | -1.242 |
Token | practices |
Token ID | 6593 |
Feature activation | -7.18e-02 |
Pos logit contributions | |
rigging | +0.056 |
ONE | +0.054 |
sparing | +0.054 |
discord | +0.052 |
centre | +0.051 |
Neg logit contributions | |
verts | -0.075 |
ements | -0.074 |
uez | -0.073 |
enhagen | -0.072 |
nces | -0.070 |
Token | , |
Token ID | 11 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
verts | +0.428 |
ements | +0.420 |
uez | +0.414 |
enhagen | +0.401 |
nces | +0.392 |
Neg logit contributions | |
rigging | -0.393 |
sparing | -0.380 |
ONE | -0.380 |
Problem | -0.361 |
discord | -0.361 |
Token | including |
Token ID | 1390 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
verts | +0.261 |
ements | +0.258 |
uez | +0.254 |
enhagen | +0.248 |
nces | +0.241 |
Neg logit contributions | |
rigging | -0.216 |
sparing | -0.208 |
ONE | -0.205 |
discord | -0.196 |
Problem | -0.195 |
Token | the |
Token ID | 262 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
verts | +3.821 |
ements | +3.705 |
uez | +3.686 |
enhagen | +3.365 |
nesses | +3.337 |
Neg logit contributions | |
rigging | -4.925 |
ONE | -4.861 |
sparing | -4.847 |
THING | -4.670 |
underestimate | -4.629 |
Token | Dan |
Token ID | 6035 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
verts | +2.290 |
ements | +2.247 |
uez | +2.210 |
enhagen | +2.132 |
nces | +2.054 |
Neg logit contributions | |
rigging | -2.405 |
ONE | -2.364 |
sparing | -2.364 |
THING | -2.260 |
Problem | -2.248 |
Token | ie |
Token ID | 494 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
verts | +2.129 |
ements | +2.086 |
uez | +2.066 |
enhagen | +1.985 |
nces | +1.921 |
Neg logit contributions | |
rigging | -1.822 |
sparing | -1.776 |
ONE | -1.761 |
THING | -1.692 |
discord | -1.683 |
Token | ll |
Token ID | 297 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
verts | +2.934 |
ements | +2.885 |
uez | +2.864 |
enhagen | +2.719 |
nesses | +2.663 |
Neg logit contributions | |
rigging | -2.230 |
sparing | -2.180 |
ONE | -2.167 |
THING | -2.047 |
discord | -2.042 |
Token | cell |
Token ID | 2685 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
verts | +1.852 |
ements | +1.819 |
uez | +1.794 |
enhagen | +1.714 |
nesses | +1.659 |
Neg logit contributions | |
rigging | -2.077 |
ONE | -2.043 |
sparing | -2.040 |
THING | -1.959 |
Problem | -1.949 |
Token | battery |
Token ID | 6555 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
verts | +3.812 |
uez | +3.748 |
ements | +3.748 |
enhagen | +3.423 |
bats | +3.422 |
Neg logit contributions | |
rigging | -3.842 |
ONE | -3.784 |
sparing | -3.737 |
THING | -3.674 |
Problem | -3.631 |
Token | is |
Token ID | 318 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
verts | +6.504 |
uez | +6.004 |
ements | +5.906 |
nesses | +5.270 |
bats | +5.156 |
Neg logit contributions | |
ONE | -12.650 |
THING | -12.427 |
sparing | -12.327 |
rigging | -12.284 |
underestimate | -12.000 |
Token | constructed |
Token ID | 12006 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
verts | +2.778 |
ements | +2.746 |
uez | +2.695 |
enhagen | +2.534 |
verages | +2.448 |
Neg logit contributions | |
rigging | -3.957 |
ONE | -3.941 |
sparing | -3.918 |
THING | -3.792 |
underestimate | -3.791 |
Token | . |
Token ID | 13 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
verts | +2.182 |
ements | +2.139 |
uez | +2.099 |
enhagen | +2.021 |
nesses | +1.959 |
Neg logit contributions | |
rigging | -2.268 |
sparing | -2.231 |
ONE | -2.225 |
THING | -2.130 |
discord | -2.121 |
Token | How |
Token ID | 1374 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
verts | +2.433 |
ements | +2.392 |
uez | +2.351 |
enhagen | +2.276 |
nces | +2.201 |
Neg logit contributions | |
rigging | -2.362 |
sparing | -2.325 |
ONE | -2.309 |
THING | -2.212 |
discord | -2.202 |
Token | St |
Token ID | 1273 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
verts | +1.800 |
ements | +1.762 |
uez | +1.721 |
enhagen | +1.635 |
nesses | +1.569 |
Neg logit contributions | |
rigging | -2.661 |
sparing | -2.621 |
ONE | -2.606 |
discord | -2.503 |
underestimate | -2.502 |
Token | Kam |
Token ID | 12670 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
verts | +0.603 |
ements | +0.593 |
uez | +0.585 |
enhagen | +0.568 |
nces | +0.548 |
Neg logit contributions | |
rigging | -0.510 |
sparing | -0.503 |
ONE | -0.501 |
discord | -0.475 |
THING | -0.473 |
Token | insky |
Token ID | 19870 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
rigging | +0.965 |
ONE | +0.962 |
sparing | +0.947 |
Problem | +0.915 |
discord | +0.882 |
Neg logit contributions | |
verts | -1.586 |
ements | -1.566 |
uez | -1.537 |
enhagen | -1.526 |
nces | -1.489 |
Token | in |
Token ID | 287 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
verts | +0.945 |
ements | +0.932 |
uez | +0.915 |
enhagen | +0.889 |
nesses | +0.860 |
Neg logit contributions | |
rigging | -0.802 |
sparing | -0.788 |
ONE | -0.784 |
discord | -0.744 |
THING | -0.742 |
Token | the |
Token ID | 262 |
Feature activation | -9.37e-02 |
Pos logit contributions | |
verts | +0.745 |
ements | +0.737 |
uez | +0.730 |
enhagen | +0.710 |
nces | +0.680 |
Neg logit contributions | |
rigging | -0.664 |
sparing | -0.650 |
ONE | -0.645 |
discord | -0.614 |
centre | -0.612 |
Token | John |
Token ID | 1757 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
verts | +0.606 |
ements | +0.597 |
uez | +0.590 |
enhagen | +0.574 |
nces | +0.557 |
Neg logit contributions | |
rigging | -0.460 |
sparing | -0.448 |
ONE | -0.446 |
discord | -0.423 |
centre | -0.421 |
Token | R |
Token ID | 371 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
sparing | +1.998 |
rigging | +1.991 |
ONE | +1.956 |
discord | +1.888 |
centre | +1.873 |
Neg logit contributions | |
verts | -2.577 |
ements | -2.574 |
enhagen | -2.543 |
uez | -2.485 |
nces | -2.436 |
Token | . |
Token ID | 13 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
ements | +7.179 |
uez | +7.172 |
verts | +6.986 |
ellig | +6.361 |
nesses | +6.093 |
Neg logit contributions | |
rigging | -11.966 |
captcha | -11.736 |
sparing | -11.726 |
resonate | -11.298 |
THING | -11.264 |
Token | Wooden |
Token ID | 40143 |
Feature activation | +7.38e-02 |
Pos logit contributions | |
verts | +4.126 |
ements | +4.037 |
uez | +3.995 |
enhagen | +3.777 |
nesses | +3.652 |
Neg logit contributions | |
rigging | -4.707 |
sparing | -4.650 |
ONE | -4.604 |
THING | -4.458 |
Problem | -4.407 |
Token | Award |
Token ID | 11289 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
rigging | +0.187 |
sparing | +0.180 |
ONE | +0.179 |
discord | +0.160 |
Problem | +0.160 |
Neg logit contributions | |
verts | -0.647 |
ements | -0.643 |
uez | -0.632 |
enhagen | -0.620 |
nces | -0.610 |
Token | voting |
Token ID | 6709 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
rigging | +0.641 |
sparing | +0.623 |
ONE | +0.616 |
centre | +0.587 |
Problem | +0.587 |
Neg logit contributions | |
verts | -0.778 |
ements | -0.774 |
uez | -0.761 |
enhagen | -0.734 |
nces | -0.718 |
Token | ( |
Token ID | 357 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
verts | +4.192 |
ements | +4.080 |
uez | +4.016 |
enhagen | +3.895 |
verages | +3.761 |
Neg logit contributions | |
rigging | -3.763 |
ONE | -3.750 |
sparing | -3.742 |
THING | -3.622 |
Problem | -3.599 |
Token | of |
Token ID | 286 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
verts | +1.769 |
ements | +1.744 |
uez | +1.703 |
enhagen | +1.653 |
nces | +1.592 |
Neg logit contributions | |
rigging | -1.868 |
ONE | -1.834 |
sparing | -1.831 |
THING | -1.759 |
Problem | -1.748 |
Token | tears |
Token ID | 10953 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
verts | +4.486 |
ements | +4.380 |
uez | +4.314 |
enhagen | +4.160 |
nces | +4.044 |
Neg logit contributions | |
ONE | -3.569 |
rigging | -3.538 |
sparing | -3.414 |
THING | -3.392 |
Problem | -3.386 |
Token | as |
Token ID | 355 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
verts | +0.340 |
ements | +0.334 |
uez | +0.329 |
enhagen | +0.321 |
nesses | +0.308 |
Neg logit contributions | |
rigging | -0.291 |
sparing | -0.288 |
ONE | -0.284 |
discord | -0.271 |
THING | -0.269 |
Token | her |
Token ID | 607 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
rigging | +2.235 |
sparing | +2.231 |
ONE | +2.140 |
centre | +2.044 |
discord | +2.043 |
Neg logit contributions | |
verts | -4.440 |
ements | -4.376 |
uez | -4.320 |
enhagen | -4.303 |
verages | -4.151 |
Token | emotions |
Token ID | 10825 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
verts | +0.491 |
ements | +0.486 |
uez | +0.479 |
enhagen | +0.471 |
nces | +0.457 |
Neg logit contributions | |
rigging | -0.268 |
sparing | -0.263 |
ONE | -0.258 |
discord | -0.244 |
centre | -0.242 |
Token | overt |
Token ID | 9929 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
verts | +1.820 |
ements | +1.789 |
uez | +1.765 |
enhagen | +1.718 |
nces | +1.666 |
Neg logit contributions | |
rigging | -1.408 |
sparing | -1.385 |
ONE | -1.372 |
discord | -1.306 |
THING | -1.302 |
Token | ook |
Token ID | 566 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
verts | +10.475 |
ements | +10.076 |
ellig | +10.062 |
uez | +10.014 |
enhagen | +9.894 |
Neg logit contributions | |
rigging | -8.286 |
sparing | -8.229 |
THING | -7.802 |
Problem | -7.691 |
orally | -7.651 |
Token | her |
Token ID | 607 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
verts | +3.274 |
ements | +3.220 |
uez | +3.165 |
enhagen | +3.076 |
nces | +2.984 |
Neg logit contributions | |
rigging | -2.598 |
ONE | -2.549 |
sparing | -2.542 |
THING | -2.424 |
Problem | -2.416 |
Token | at |
Token ID | 379 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
verts | +1.947 |
ements | +1.919 |
uez | +1.888 |
enhagen | +1.847 |
nces | +1.778 |
Neg logit contributions | |
rigging | -1.502 |
sparing | -1.477 |
ONE | -1.464 |
discord | -1.394 |
THING | -1.385 |
Token | one |
Token ID | 530 |
Feature activation | -8.91e-02 |
Pos logit contributions | |
rigging | +0.807 |
sparing | +0.802 |
ONE | +0.789 |
centre | +0.762 |
discord | +0.754 |
Neg logit contributions | |
verts | -0.959 |
ements | -0.948 |
uez | -0.930 |
enhagen | -0.913 |
nesses | -0.886 |
Token | point |
Token ID | 966 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
verts | +0.745 |
ements | +0.736 |
uez | +0.727 |
enhagen | +0.713 |
nces | +0.696 |
Neg logit contributions | |
rigging | -0.263 |
sparing | -0.255 |
ONE | -0.255 |
discord | -0.232 |
THING | -0.231 |
Token | national |
Token ID | 2260 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
verts | +0.282 |
ements | +0.277 |
uez | +0.274 |
enhagen | +0.267 |
nces | +0.259 |
Neg logit contributions | |
rigging | -0.195 |
sparing | -0.193 |
ONE | -0.189 |
discord | -0.181 |
centre | -0.180 |
Token | level |
Token ID | 1241 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
rigging | +1.748 |
sparing | +1.734 |
ONE | +1.698 |
centre | +1.638 |
discord | +1.637 |
Neg logit contributions | |
verts | -2.669 |
ements | -2.630 |
uez | -2.624 |
enhagen | -2.561 |
nces | -2.491 |
Token | ( |
Token ID | 357 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
sparing | +3.680 |
rigging | +3.648 |
ONE | +3.477 |
orally | +3.466 |
discord | +3.445 |
Neg logit contributions | |
verts | -4.836 |
ements | -4.770 |
uez | -4.715 |
enhagen | -4.492 |
verages | -4.454 |
Token | e |
Token ID | 68 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
verts | +1.202 |
ements | +1.184 |
uez | +1.165 |
enhagen | +1.134 |
nces | +1.095 |
Neg logit contributions | |
rigging | -1.021 |
ONE | -1.008 |
sparing | -1.002 |
Problem | -0.955 |
THING | -0.953 |
Token | . |
Token ID | 13 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
verts | +4.894 |
ements | +4.738 |
uez | +4.553 |
enhagen | +4.184 |
ellig | +4.176 |
Neg logit contributions | |
rigging | -6.174 |
sparing | -6.051 |
ONE | -5.811 |
resonate | -5.794 |
discord | -5.775 |
Token | g |
Token ID | 70 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
verts | +4.696 |
ements | +4.606 |
uez | +4.451 |
enhagen | +4.202 |
nesses | +4.122 |
Neg logit contributions | |
rigging | -5.033 |
sparing | -4.954 |
ONE | -4.899 |
resonate | -4.721 |
discord | -4.711 |
Token | ., |
Token ID | 1539 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
verts | +5.808 |
uez | +5.768 |
ements | +5.762 |
enhagen | +5.359 |
ellig | +5.045 |
Neg logit contributions | |
rigging | -12.503 |
sparing | -12.330 |
ONE | -12.290 |
THING | -12.050 |
discord | -11.965 |
Token | the |
Token ID | 262 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
verts | +2.765 |
ements | +2.723 |
uez | +2.677 |
enhagen | +2.608 |
nces | +2.527 |
Neg logit contributions | |
rigging | -2.056 |
sparing | -2.015 |
ONE | -2.012 |
THING | -1.905 |
discord | -1.899 |
Token | 2015 |
Token ID | 1853 |
Feature activation | -8.22e-04 |
Pos logit contributions | |
verts | +2.200 |
ements | +2.162 |
uez | +2.127 |
enhagen | +2.069 |
nesses | +2.008 |
Neg logit contributions | |
rigging | -1.763 |
sparing | -1.730 |
ONE | -1.724 |
THING | -1.635 |
discord | -1.634 |
Token | referendum |
Token ID | 11467 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
verts | +0.005 |
ements | +0.005 |
uez | +0.005 |
enhagen | +0.005 |
nesses | +0.005 |
Neg logit contributions | |
rigging | -0.004 |
sparing | -0.004 |
ONE | -0.004 |
discord | -0.004 |
THING | -0.004 |
Token | in |
Token ID | 287 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
verts | +0.886 |
ements | +0.876 |
uez | +0.863 |
enhagen | +0.841 |
nces | +0.816 |
Neg logit contributions | |
rigging | -0.671 |
sparing | -0.655 |
ONE | -0.649 |
discord | -0.616 |
underestimate | -0.614 |
Token | anc |
Token ID | 1192 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
ONE | +2.648 |
rigging | +2.604 |
sparing | +2.574 |
centre | +2.544 |
underestimate | +2.434 |
Neg logit contributions | |
verts | -7.833 |
ements | -7.693 |
enhagen | -7.490 |
nces | -7.431 |
uez | -7.386 |
Token |
|
Token ID | 198 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
verts | +2.320 |
ements | +2.259 |
uez | +2.232 |
enhagen | +2.140 |
nesses | +2.087 |
Neg logit contributions | |
rigging | -2.138 |
sparing | -2.101 |
ONE | -2.078 |
THING | -1.996 |
underestimate | -1.978 |
Token |
|
Token ID | 198 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
verts | +1.368 |
ements | +1.342 |
uez | +1.317 |
enhagen | +1.261 |
nesses | +1.235 |
Neg logit contributions | |
rigging | -1.225 |
sparing | -1.204 |
ONE | -1.192 |
THING | -1.140 |
discord | -1.135 |
Token | 2004 |
Token ID | 15724 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
verts | +1.557 |
ements | +1.531 |
uez | +1.505 |
enhagen | +1.463 |
nces | +1.415 |
Neg logit contributions | |
rigging | -1.320 |
sparing | -1.295 |
ONE | -1.294 |
THING | -1.230 |
discord | -1.226 |
Token | John |
Token ID | 1757 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
rigging | +1.108 |
ONE | +1.075 |
sparing | +1.061 |
discord | +1.024 |
THING | +1.010 |
Neg logit contributions | |
verts | -1.552 |
ements | -1.537 |
uez | -1.515 |
enhagen | -1.500 |
nces | -1.445 |
Token | R |
Token ID | 371 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
ONE | +2.313 |
rigging | +2.303 |
sparing | +2.301 |
centre | +2.151 |
discord | +2.150 |
Neg logit contributions | |
verts | -3.500 |
ements | -3.429 |
uez | -3.389 |
enhagen | -3.369 |
nesses | -3.237 |
Token | itter |
Token ID | 1967 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
uez | +8.827 |
ements | +8.765 |
verts | +8.443 |
ellig | +8.007 |
nesses | +7.629 |
Neg logit contributions | |
rigging | -10.231 |
captcha | -10.212 |
sparing | -9.992 |
discord | -9.529 |
orally | -9.474 |
Token |
|
Token ID | 198 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
verts | +3.066 |
ements | +2.930 |
uez | +2.905 |
enhagen | +2.833 |
bats | +2.728 |
Neg logit contributions | |
rigging | -3.514 |
sparing | -3.474 |
ONE | -3.456 |
THING | -3.359 |
Problem | -3.308 |
Token |
|
Token ID | 198 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
verts | +2.162 |
ements | +2.112 |
uez | +2.071 |
enhagen | +1.942 |
nesses | +1.938 |
Neg logit contributions | |
rigging | -2.077 |
sparing | -2.044 |
ONE | -2.006 |
THING | -1.932 |
underestimate | -1.930 |
Token | 2004 |
Token ID | 15724 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
verts | +1.562 |
ements | +1.542 |
uez | +1.513 |
enhagen | +1.476 |
nces | +1.425 |
Neg logit contributions | |
rigging | -1.295 |
ONE | -1.277 |
sparing | -1.269 |
THING | -1.210 |
Problem | -1.208 |
Token | Tony |
Token ID | 8832 |
Feature activation | -8.12e-02 |
Pos logit contributions | |
verts | +0.104 |
ements | +0.103 |
uez | +0.101 |
enhagen | +0.099 |
nces | +0.096 |
Neg logit contributions | |
rigging | -0.081 |
ONE | -0.079 |
sparing | -0.078 |
discord | -0.075 |
THING | -0.075 |
Token | a |
Token ID | 257 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
rigging | +2.157 |
sparing | +2.126 |
ONE | +2.086 |
THING | +2.001 |
discord | +1.991 |
Neg logit contributions | |
verts | -2.510 |
ements | -2.450 |
uez | -2.435 |
enhagen | -2.430 |
nces | -2.325 |
Token | method |
Token ID | 2446 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
rigging | +1.615 |
sparing | +1.605 |
ONE | +1.575 |
THING | +1.489 |
discord | +1.482 |
Neg logit contributions | |
verts | -2.504 |
ements | -2.441 |
enhagen | -2.425 |
uez | -2.422 |
nces | -2.346 |
Token | ( |
Token ID | 357 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
verts | +0.637 |
ements | +0.625 |
uez | +0.616 |
enhagen | +0.601 |
nces | +0.586 |
Neg logit contributions | |
rigging | -0.547 |
sparing | -0.541 |
ONE | -0.535 |
discord | -0.509 |
THING | -0.508 |
Token | i |
Token ID | 72 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
verts | +1.468 |
ements | +1.447 |
uez | +1.425 |
enhagen | +1.390 |
nces | +1.345 |
Neg logit contributions | |
rigging | -1.190 |
ONE | -1.170 |
sparing | -1.167 |
THING | -1.110 |
Problem | -1.107 |
Token | . |
Token ID | 13 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
verts | +5.901 |
ements | +5.770 |
uez | +5.566 |
nesses | +5.035 |
enhagen | +5.015 |
Neg logit contributions | |
rigging | -7.861 |
sparing | -7.761 |
ONE | -7.735 |
THING | -7.501 |
captcha | -7.485 |
Token | e |
Token ID | 68 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
verts | +4.620 |
ements | +4.574 |
uez | +4.397 |
nesses | +4.120 |
enhagen | +4.114 |
Neg logit contributions | |
rigging | -3.733 |
sparing | -3.675 |
ONE | -3.565 |
resonate | -3.481 |
captcha | -3.469 |
Token | . |
Token ID | 13 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
verts | +8.103 |
ements | +8.030 |
uez | +7.756 |
enhagen | +7.141 |
acters | +7.128 |
Neg logit contributions | |
ONE | -10.081 |
rigging | -9.922 |
sparing | -9.742 |
THING | -9.728 |
discord | -9.682 |
Token | is |
Token ID | 318 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
verts | +3.894 |
ements | +3.837 |
uez | +3.771 |
enhagen | +3.647 |
nesses | +3.542 |
Neg logit contributions | |
rigging | -2.993 |
ONE | -2.953 |
sparing | -2.927 |
THING | -2.799 |
Problem | -2.781 |
Token | the |
Token ID | 262 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
verts | +2.748 |
ements | +2.707 |
uez | +2.658 |
enhagen | +2.581 |
nesses | +2.498 |
Neg logit contributions | |
rigging | -2.248 |
ONE | -2.209 |
sparing | -2.202 |
THING | -2.098 |
discord | -2.090 |
Token | syntax |
Token ID | 15582 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
verts | +0.902 |
ements | +0.886 |
uez | +0.877 |
enhagen | +0.856 |
nces | +0.834 |
Neg logit contributions | |
rigging | -0.563 |
sparing | -0.554 |
ONE | -0.549 |
THING | -0.515 |
centre | -0.514 |
Token | just |
Token ID | 655 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
verts | +7.136 |
ements | +7.065 |
uez | +6.914 |
enhagen | +6.558 |
nesses | +6.487 |
Neg logit contributions | |
rigging | -5.485 |
ONE | -5.454 |
sparing | -5.284 |
THING | -5.182 |
Problem | -5.129 |
Token | it |
Token ID | 340 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
verts | +4.047 |
ements | +3.967 |
uez | +3.892 |
enhagen | +3.762 |
nesses | +3.637 |
Neg logit contributions | |
rigging | -4.023 |
ONE | -3.956 |
sparing | -3.950 |
THING | -3.775 |
Problem | -3.768 |
Token | , |
Token ID | 11 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
verts | +3.918 |
ements | +3.829 |
uez | +3.767 |
enhagen | +3.658 |
nces | +3.526 |
Neg logit contributions | |
rigging | -3.687 |
ONE | -3.624 |
sparing | -3.614 |
THING | -3.459 |
Problem | -3.447 |
Token | I |
Token ID | 314 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
verts | +1.510 |
ements | +1.499 |
uez | +1.471 |
enhagen | +1.435 |
nesses | +1.379 |
Neg logit contributions | |
rigging | -1.379 |
sparing | -1.361 |
ONE | -1.354 |
discord | -1.286 |
THING | -1.282 |
Token | call |
Token ID | 869 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
rigging | +0.282 |
sparing | +0.278 |
ONE | +0.273 |
discord | +0.261 |
centre | +0.260 |
Neg logit contributions | |
verts | -0.423 |
ements | -0.416 |
uez | -0.410 |
enhagen | -0.401 |
bats | -0.391 |
Token | these |
Token ID | 777 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
verts | +2.481 |
ements | +2.442 |
uez | +2.394 |
enhagen | +2.327 |
nces | +2.237 |
Neg logit contributions | |
rigging | -2.634 |
sparing | -2.592 |
ONE | -2.583 |
THING | -2.469 |
discord | -2.466 |
Token | instances |
Token ID | 10245 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
verts | +4.161 |
ements | +4.081 |
uez | +4.003 |
enhagen | +3.869 |
nces | +3.755 |
Neg logit contributions | |
rigging | -3.888 |
ONE | -3.816 |
sparing | -3.805 |
THING | -3.638 |
Problem | -3.634 |
Token | " |
Token ID | 366 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
verts | +9.220 |
ements | +8.992 |
uez | +8.823 |
Ports | +8.327 |
nces | +8.302 |
Neg logit contributions | |
rigging | -9.198 |
ONE | -8.963 |
sparing | -8.936 |
Problem | -8.794 |
restling | -8.627 |
Token | P |
Token ID | 47 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
verts | +2.590 |
ements | +2.549 |
uez | +2.505 |
enhagen | +2.438 |
nces | +2.361 |
Neg logit contributions | |
rigging | -2.050 |
sparing | -2.010 |
ONE | -2.007 |
THING | -1.905 |
discord | -1.899 |
Token | V |
Token ID | 53 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
ONE | +1.706 |
rigging | +1.676 |
sparing | +1.641 |
THING | +1.573 |
Problem | +1.572 |
Neg logit contributions | |
verts | -2.290 |
ements | -2.282 |
uez | -2.233 |
enhagen | -2.197 |
nces | -2.161 |
Token | H |
Token ID | 39 |
Feature activation | +8.32e-02 |
Pos logit contributions | |
verts | +2.140 |
ements | +2.105 |
uez | +2.070 |
enhagen | +2.014 |
nces | +1.956 |
Neg logit contributions | |
rigging | -1.576 |
sparing | -1.543 |
ONE | -1.534 |
THING | -1.456 |
discord | -1.454 |
Token | VM |
Token ID | 15996 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
ONE | +0.422 |
rigging | +0.421 |
sparing | +0.413 |
Problem | +0.394 |
THING | +0.393 |
Neg logit contributions | |
verts | -0.512 |
ements | -0.507 |
uez | -0.498 |
enhagen | -0.493 |
nesses | -0.470 |
Token | of |
Token ID | 286 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
verts | +1.594 |
ements | +1.568 |
uez | +1.543 |
enhagen | +1.502 |
nces | +1.452 |
Neg logit contributions | |
rigging | -1.291 |
ONE | -1.267 |
sparing | -1.266 |
THING | -1.202 |
discord | -1.198 |
Token | genres |
Token ID | 27962 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
verts | +3.421 |
ements | +3.357 |
uez | +3.291 |
enhagen | +3.212 |
nesses | +3.102 |
Neg logit contributions | |
rigging | -2.708 |
ONE | -2.678 |
sparing | -2.649 |
THING | -2.521 |
Problem | -2.517 |
Token | — |
Token ID | 851 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
rigging | +0.328 |
sparing | +0.325 |
ONE | +0.319 |
discord | +0.308 |
centre | +0.306 |
Neg logit contributions | |
verts | -0.333 |
ements | -0.327 |
uez | -0.323 |
enhagen | -0.313 |
nces | -0.304 |
Token | i |
Token ID | 1312 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
verts | +6.406 |
ements | +6.284 |
uez | +6.111 |
enhagen | +5.927 |
nesses | +5.734 |
Neg logit contributions | |
rigging | -5.348 |
ONE | -5.303 |
sparing | -5.150 |
THING | -5.045 |
Problem | -5.024 |
Token | . |
Token ID | 13 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
verts | +3.571 |
ements | +3.489 |
uez | +3.406 |
enhagen | +3.203 |
nesses | +3.168 |
Neg logit contributions | |
rigging | -4.102 |
sparing | -4.041 |
ONE | -3.988 |
discord | -3.851 |
captcha | -3.840 |
Token | e |
Token ID | 68 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
verts | +2.850 |
ements | +2.824 |
uez | +2.748 |
enhagen | +2.644 |
nesses | +2.590 |
Neg logit contributions | |
rigging | -2.045 |
sparing | -2.001 |
ONE | -1.961 |
discord | -1.875 |
underestimate | -1.872 |
Token | . |
Token ID | 13 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
verts | +6.157 |
ements | +5.838 |
uez | +5.542 |
nces | +5.283 |
enhagen | +5.247 |
Neg logit contributions | |
rigging | -12.143 |
ONE | -11.986 |
sparing | -11.861 |
captcha | -11.785 |
THING | -11.636 |
Token | the |
Token ID | 262 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
verts | +4.206 |
ements | +4.119 |
uez | +4.056 |
enhagen | +3.930 |
nesses | +3.823 |
Neg logit contributions | |
rigging | -3.178 |
ONE | -3.128 |
sparing | -3.079 |
THING | -2.943 |
Problem | -2.935 |
Token | prim |
Token ID | 2684 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
verts | +2.287 |
ements | +2.252 |
uez | +2.216 |
enhagen | +2.156 |
nces | +2.089 |
Neg logit contributions | |
rigging | -1.786 |
sparing | -1.753 |
ONE | -1.749 |
THING | -1.660 |
discord | -1.657 |
Token | etime |
Token ID | 8079 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
rigging | +1.299 |
sparing | +1.290 |
ONE | +1.255 |
discord | +1.221 |
centre | +1.204 |
Neg logit contributions | |
verts | -1.604 |
ements | -1.603 |
uez | -1.588 |
enhagen | -1.542 |
verages | -1.500 |
Token | soap |
Token ID | 19533 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
rigging | +1.395 |
sparing | +1.383 |
ONE | +1.343 |
discord | +1.307 |
centre | +1.300 |
Neg logit contributions | |
verts | -1.716 |
ements | -1.706 |
uez | -1.699 |
enhagen | -1.665 |
nces | -1.586 |
Token | this |
Token ID | 428 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
rigging | +6.363 |
centre | +6.110 |
discord | +6.046 |
ONE | +5.967 |
sparing | +5.957 |
Neg logit contributions | |
verts | -8.208 |
nces | -8.057 |
ements | -8.026 |
uez | -7.803 |
nesses | -7.683 |
Token | gathering |
Token ID | 11228 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
rigging | +2.537 |
sparing | +2.434 |
ONE | +2.396 |
centre | +2.371 |
discord | +2.368 |
Neg logit contributions | |
verts | -4.071 |
ements | -4.068 |
uez | -3.971 |
enhagen | -3.904 |
nces | -3.852 |
Token | , |
Token ID | 11 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
rigging | +5.456 |
discord | +5.125 |
sparing | +5.091 |
centre | +5.077 |
ONE | +4.944 |
Neg logit contributions | |
verts | -8.251 |
ements | -8.171 |
uez | -8.064 |
enhagen | -7.911 |
inventoryQuantity | -7.806 |
Token | i |
Token ID | 1312 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
rigging | +2.314 |
sparing | +2.269 |
ONE | +2.224 |
discord | +2.161 |
centre | +2.143 |
Neg logit contributions | |
verts | -2.760 |
ements | -2.715 |
uez | -2.674 |
enhagen | -2.637 |
nces | -2.578 |
Token | . |
Token ID | 13 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
verts | +3.296 |
ements | +3.241 |
uez | +3.167 |
enhagen | +3.054 |
nesses | +2.945 |
Neg logit contributions | |
rigging | -3.505 |
sparing | -3.454 |
ONE | -3.432 |
THING | -3.303 |
discord | -3.286 |
Token | e |
Token ID | 68 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
verts | +3.800 |
ements | +3.774 |
uez | +3.670 |
enhagen | +3.553 |
nesses | +3.462 |
Neg logit contributions | |
rigging | -2.786 |
sparing | -2.723 |
ONE | -2.702 |
THING | -2.563 |
underestimate | -2.560 |
Token | . |
Token ID | 13 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
verts | +6.229 |
ements | +6.124 |
uez | +5.950 |
ellig | +5.460 |
enhagen | +5.436 |
Neg logit contributions | |
rigging | -11.953 |
sparing | -11.931 |
ONE | -11.848 |
THING | -11.699 |
captcha | -11.693 |
Token | an |
Token ID | 281 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
verts | +1.329 |
ements | +1.308 |
uez | +1.286 |
enhagen | +1.252 |
nces | +1.210 |
Neg logit contributions | |
rigging | -1.247 |
sparing | -1.227 |
ONE | -1.224 |
discord | -1.172 |
THING | -1.162 |
Token | Old |
Token ID | 5706 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
rigging | +1.621 |
ONE | +1.612 |
sparing | +1.594 |
underestimate | +1.525 |
discord | +1.519 |
Neg logit contributions | |
verts | -2.334 |
ements | -2.280 |
uez | -2.229 |
enhagen | -2.179 |
nesses | -2.145 |
Token | Guard |
Token ID | 4932 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
rigging | +0.192 |
sparing | +0.187 |
ONE | +0.187 |
THING | +0.175 |
Problem | +0.174 |
Neg logit contributions | |
verts | -0.339 |
ements | -0.334 |
uez | -0.329 |
enhagen | -0.322 |
nesses | -0.313 |
Token | defending |
Token ID | 11749 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
verts | +1.367 |
ements | +1.348 |
uez | +1.323 |
enhagen | +1.290 |
nces | +1.251 |
Neg logit contributions | |
rigging | -1.109 |
sparing | -1.087 |
ONE | -1.085 |
discord | -1.031 |
THING | -1.026 |
Token | one |
Token ID | 530 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
rigging | +0.852 |
ONE | +0.840 |
sparing | +0.837 |
discord | +0.790 |
underestimate | +0.790 |
Neg logit contributions | |
verts | -0.966 |
ements | -0.957 |
uez | -0.939 |
enhagen | -0.923 |
nces | -0.895 |
Token | must |
Token ID | 1276 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
rigging | +1.434 |
sparing | +1.422 |
ONE | +1.411 |
discord | +1.329 |
underestimate | +1.325 |
Neg logit contributions | |
verts | -2.075 |
ements | -2.042 |
uez | -2.007 |
enhagen | -1.978 |
nces | -1.921 |
Token | consider |
Token ID | 2074 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
sparing | +0.979 |
rigging | +0.975 |
ONE | +0.945 |
underestimate | +0.916 |
orally | +0.910 |
Neg logit contributions | |
verts | -1.488 |
ements | -1.471 |
uez | -1.440 |
enhagen | -1.431 |
nces | -1.382 |
Token | the |
Token ID | 262 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
rigging | +0.170 |
sparing | +0.169 |
ONE | +0.165 |
discord | +0.158 |
THING | +0.157 |
Neg logit contributions | |
verts | -0.193 |
ements | -0.191 |
uez | -0.188 |
enhagen | -0.183 |
nces | -0.176 |
Token | pros |
Token ID | 10360 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
verts | +1.268 |
ements | +1.248 |
uez | +1.229 |
enhagen | +1.198 |
nces | +1.161 |
Neg logit contributions | |
rigging | -0.984 |
sparing | -0.969 |
ONE | -0.960 |
discord | -0.912 |
THING | -0.912 |
Token | and |
Token ID | 290 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
sparing | +3.012 |
rigging | +2.984 |
ONE | +2.974 |
centre | +2.756 |
Problem | +2.739 |
Neg logit contributions | |
verts | -3.833 |
ements | -3.749 |
uez | -3.682 |
enhagen | -3.574 |
nces | -3.498 |
Token | cons |
Token ID | 762 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
verts | +4.307 |
ements | +4.075 |
uez | +3.884 |
nesses | +3.704 |
itutes | +3.444 |
Neg logit contributions | |
ONE | -14.201 |
THING | -13.775 |
rigging | -13.705 |
sparing | -13.627 |
captcha | -13.533 |
Token | . |
Token ID | 13 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
sparing | +1.106 |
rigging | +1.105 |
ONE | +1.085 |
orally | +1.026 |
discord | +1.024 |
Neg logit contributions | |
verts | -1.297 |
ements | -1.271 |
uez | -1.259 |
enhagen | -1.208 |
nces | -1.180 |
Token | For |
Token ID | 1114 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
verts | +1.241 |
ements | +1.225 |
uez | +1.201 |
enhagen | +1.174 |
nces | +1.135 |
Neg logit contributions | |
rigging | -1.156 |
ONE | -1.143 |
sparing | -1.134 |
THING | -1.086 |
Problem | -1.085 |
Token | example |
Token ID | 1672 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
verts | +2.729 |
ements | +2.683 |
uez | +2.632 |
enhagen | +2.555 |
nesses | +2.467 |
Neg logit contributions | |
rigging | -2.531 |
ONE | -2.485 |
sparing | -2.484 |
THING | -2.369 |
discord | -2.360 |
Token | , |
Token ID | 11 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
verts | +1.404 |
ements | +1.369 |
uez | +1.354 |
enhagen | +1.307 |
nces | +1.258 |
Neg logit contributions | |
rigging | -1.482 |
sparing | -1.457 |
ONE | -1.457 |
THING | -1.399 |
Problem | -1.390 |
Token | a |
Token ID | 257 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
verts | +0.608 |
ements | +0.600 |
uez | +0.591 |
enhagen | +0.579 |
nesses | +0.560 |
Neg logit contributions | |
rigging | -0.431 |
sparing | -0.425 |
ONE | -0.422 |
discord | -0.398 |
THING | -0.398 |
Token | block |
Token ID | 2512 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
rigging | +0.222 |
sparing | +0.220 |
ONE | +0.218 |
THING | +0.207 |
centre | +0.206 |
Neg logit contributions | |
verts | -0.317 |
ements | -0.313 |
uez | -0.307 |
enhagen | -0.305 |
nces | -0.294 |
Token | ( |
Token ID | 357 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
verts | +3.490 |
ements | +3.455 |
uez | +3.371 |
enhagen | +3.269 |
nces | +3.151 |
Neg logit contributions | |
rigging | -3.221 |
ONE | -3.146 |
sparing | -3.132 |
THING | -3.001 |
discord | -2.991 |
Token | e |
Token ID | 68 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
verts | +1.847 |
ements | +1.821 |
uez | +1.793 |
enhagen | +1.752 |
nces | +1.700 |
Neg logit contributions | |
rigging | -1.298 |
ONE | -1.276 |
sparing | -1.271 |
THING | -1.204 |
Problem | -1.199 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
verts | +5.510 |
ements | +5.345 |
uez | +5.175 |
ellig | +4.695 |
bats | +4.657 |
Neg logit contributions | |
rigging | -7.195 |
sparing | -7.051 |
ONE | -6.875 |
resonate | -6.782 |
discord | -6.770 |
Token | g |
Token ID | 70 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
verts | +5.238 |
ements | +5.114 |
uez | +4.950 |
ellig | +4.552 |
nesses | +4.550 |
Neg logit contributions | |
rigging | -6.103 |
sparing | -6.002 |
ONE | -5.933 |
resonate | -5.789 |
discord | -5.737 |
Token | . |
Token ID | 13 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
verts | +7.564 |
ements | +7.494 |
uez | +7.436 |
enhagen | +6.779 |
ellig | +6.728 |
Neg logit contributions | |
rigging | -10.291 |
sparing | -10.195 |
ONE | -10.194 |
discord | -9.846 |
THING | -9.841 |
Token | print |
Token ID | 3601 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
verts | +3.799 |
ements | +3.745 |
uez | +3.690 |
enhagen | +3.555 |
nesses | +3.437 |
Neg logit contributions | |
rigging | -3.188 |
ONE | -3.124 |
sparing | -3.114 |
Problem | -2.970 |
THING | -2.969 |
Token | it |
Token ID | 340 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
rigging | +2.070 |
ONE | +2.064 |
sparing | +2.061 |
THING | +1.969 |
Problem | +1.932 |
Neg logit contributions | |
verts | -2.321 |
ements | -2.270 |
uez | -2.226 |
enhagen | -2.197 |
nesses | -2.127 |
Token | out |
Token ID | 503 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
rigging | +0.061 |
sparing | +0.060 |
ONE | +0.060 |
THING | +0.057 |
discord | +0.057 |
Neg logit contributions | |
verts | -0.077 |
ements | -0.076 |
uez | -0.074 |
enhagen | -0.072 |
nesses | -0.070 |
Token | ) |
Token ID | 8 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
rigging | +0.434 |
sparing | +0.432 |
ONE | +0.424 |
THING | +0.404 |
discord | +0.404 |
Neg logit contributions | |
verts | -0.557 |
ements | -0.549 |
uez | -0.542 |
enhagen | -0.529 |
nesses | -0.511 |
Token | intellectual |
Token ID | 9028 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
rigging | +1.078 |
sparing | +1.058 |
ONE | +1.045 |
discord | +1.018 |
centre | +1.010 |
Neg logit contributions | |
verts | -0.993 |
ements | -0.971 |
uez | -0.962 |
enhagen | -0.960 |
nces | -0.911 |
Token | avenues |
Token ID | 34265 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
rigging | +2.516 |
sparing | +2.458 |
ONE | +2.437 |
discord | +2.416 |
centre | +2.394 |
Neg logit contributions | |
verts | -1.947 |
enhagen | -1.908 |
ements | -1.869 |
uez | -1.865 |
bats | -1.798 |
Token | ( |
Token ID | 357 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
verts | +0.956 |
ements | +0.937 |
uez | +0.923 |
enhagen | +0.895 |
nesses | +0.865 |
Neg logit contributions | |
rigging | -0.894 |
sparing | -0.882 |
ONE | -0.877 |
discord | -0.836 |
THING | -0.833 |
Token | i |
Token ID | 72 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
ONE | +0.656 |
rigging | +0.654 |
sparing | +0.640 |
Problem | +0.620 |
THING | +0.613 |
Neg logit contributions | |
verts | -0.826 |
ements | -0.817 |
uez | -0.804 |
enhagen | -0.787 |
nces | -0.765 |
Token | . |
Token ID | 13 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
verts | +3.935 |
ements | +3.875 |
uez | +3.799 |
enhagen | +3.568 |
nesses | +3.504 |
Neg logit contributions | |
rigging | -4.433 |
sparing | -4.367 |
ONE | -4.320 |
THING | -4.176 |
discord | -4.163 |
Token | e |
Token ID | 68 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
verts | +2.514 |
ements | +2.487 |
uez | +2.427 |
enhagen | +2.344 |
nesses | +2.292 |
Neg logit contributions | |
rigging | -1.748 |
sparing | -1.713 |
ONE | -1.688 |
discord | -1.604 |
THING | -1.602 |
Token | . |
Token ID | 13 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
verts | +6.265 |
ements | +6.159 |
uez | +5.942 |
enhagen | +5.575 |
nces | +5.383 |
Neg logit contributions | |
rigging | -11.728 |
sparing | -11.670 |
ONE | -11.666 |
captcha | -11.487 |
THING | -11.428 |
Token | pen |
Token ID | 3112 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
verts | +2.082 |
ements | +2.053 |
uez | +2.018 |
enhagen | +1.971 |
nces | +1.915 |
Neg logit contributions | |
rigging | -1.399 |
sparing | -1.369 |
ONE | -1.366 |
THING | -1.288 |
discord | -1.286 |
Token | ning |
Token ID | 768 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
sparing | +3.623 |
ONE | +3.555 |
rigging | +3.529 |
centre | +3.380 |
Problem | +3.327 |
Neg logit contributions | |
uez | -4.823 |
ements | -4.762 |
verts | -4.726 |
enhagen | -4.669 |
verages | -4.616 |
Token | a |
Token ID | 257 |
Feature activation | +9.13e-02 |
Pos logit contributions | |
sparing | +1.456 |
rigging | +1.446 |
ONE | +1.425 |
discord | +1.388 |
THING | +1.363 |
Neg logit contributions | |
verts | -1.798 |
ements | -1.795 |
uez | -1.772 |
enhagen | -1.728 |
verages | -1.677 |
Token | fictional |
Token ID | 19812 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
sparing | +0.413 |
rigging | +0.412 |
ONE | +0.403 |
discord | +0.391 |
centre | +0.384 |
Neg logit contributions | |
ements | -0.613 |
verts | -0.612 |
uez | -0.603 |
enhagen | -0.591 |
nces | -0.579 |
Token | " |
Token ID | 366 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
rigging | +0.582 |
sparing | +0.578 |
ONE | +0.571 |
discord | +0.547 |
centre | +0.546 |
Neg logit contributions | |
verts | -0.527 |
ements | -0.513 |
uez | -0.503 |
enhagen | -0.495 |
nces | -0.476 |
Token | Did |
Token ID | 11633 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
ONE | +0.684 |
rigging | +0.672 |
sparing | +0.651 |
Problem | +0.650 |
THING | +0.636 |
Neg logit contributions | |
verts | -1.029 |
ements | -1.014 |
uez | -1.004 |
enhagen | -0.998 |
nesses | -0.959 |
Token | n |
Token ID | 77 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
rigging | +1.161 |
sparing | +1.130 |
ONE | +1.120 |
Problem | +1.034 |
discord | +1.033 |
Neg logit contributions | |
verts | -2.776 |
ements | -2.740 |
uez | -2.710 |
enhagen | -2.666 |
nesses | -2.594 |
Token | 't |
Token ID | 470 |
Feature activation | +8.98e-02 |
Pos logit contributions | |
ONE | +1.498 |
rigging | +1.478 |
sparing | +1.454 |
Problem | +1.407 |
THING | +1.378 |
Neg logit contributions | |
verts | -2.911 |
enhagen | -2.885 |
ements | -2.860 |
uez | -2.843 |
nces | -2.748 |
Token | I |
Token ID | 314 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
rigging | +0.505 |
sparing | +0.497 |
ONE | +0.496 |
discord | +0.473 |
underestimate | +0.473 |
Neg logit contributions | |
verts | -0.510 |
ements | -0.502 |
uez | -0.491 |
enhagen | -0.481 |
nces | -0.463 |
Token | tell |
Token ID | 1560 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
verts | +4.535 |
ements | +4.486 |
uez | +4.442 |
enhagen | +4.227 |
nesses | +4.165 |
Neg logit contributions | |
rigging | -3.747 |
ONE | -3.724 |
sparing | -3.638 |
Problem | -3.557 |
THING | -3.551 |
Token | you |
Token ID | 345 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
verts | +5.992 |
uez | +5.803 |
ements | +5.774 |
nesses | +5.176 |
jas | +4.890 |
Neg logit contributions | |
ONE | -11.904 |
rigging | -11.820 |
THING | -11.634 |
sparing | -11.628 |
captcha | -11.609 |
Token | I |
Token ID | 314 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
verts | +3.320 |
ements | +3.283 |
uez | +3.204 |
enhagen | +3.066 |
nces | +2.974 |
Neg logit contributions | |
rigging | -3.651 |
ONE | -3.616 |
sparing | -3.581 |
THING | -3.456 |
Problem | -3.450 |
Token | 'd |
Token ID | 1549 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
ements | +6.565 |
verts | +6.499 |
uez | +6.396 |
nces | +6.130 |
enhagen | +6.090 |
Neg logit contributions | |
rigging | -3.296 |
ONE | -3.268 |
sparing | -3.157 |
captcha | -3.104 |
THING | -3.074 |
Token | burn |
Token ID | 4245 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
verts | +2.642 |
ements | +2.614 |
uez | +2.581 |
enhagen | +2.472 |
nesses | +2.416 |
Neg logit contributions | |
rigging | -2.375 |
ONE | -2.348 |
sparing | -2.323 |
Problem | -2.246 |
THING | -2.245 |
Token | your |
Token ID | 534 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
verts | +5.131 |
ements | +5.057 |
uez | +4.933 |
enhagen | +4.757 |
nces | +4.680 |
Neg logit contributions | |
rigging | -4.953 |
ONE | -4.906 |
sparing | -4.776 |
Problem | -4.704 |
THING | -4.682 |
Token | is |
Token ID | 318 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
verts | +1.217 |
ements | +1.199 |
uez | +1.179 |
enhagen | +1.153 |
nces | +1.112 |
Neg logit contributions | |
rigging | -1.053 |
sparing | -1.037 |
ONE | -1.035 |
discord | -0.985 |
THING | -0.984 |
Token | well |
Token ID | 880 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
verts | +0.317 |
ements | +0.315 |
uez | +0.308 |
enhagen | +0.305 |
nces | +0.297 |
Neg logit contributions | |
rigging | -0.199 |
sparing | -0.197 |
ONE | -0.196 |
discord | -0.183 |
centre | -0.182 |
Token | . |
Token ID | 13 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
verts | +1.491 |
ements | +1.472 |
uez | +1.442 |
enhagen | +1.402 |
nces | +1.351 |
Neg logit contributions | |
rigging | -1.417 |
sparing | -1.394 |
ONE | -1.392 |
THING | -1.325 |
discord | -1.323 |
Token | In |
Token ID | 554 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
verts | +1.026 |
ements | +1.017 |
uez | +0.994 |
enhagen | +0.978 |
nces | +0.940 |
Neg logit contributions | |
rigging | -0.907 |
ONE | -0.901 |
sparing | -0.890 |
Problem | -0.854 |
THING | -0.853 |
Token | the |
Token ID | 262 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
verts | +1.243 |
ements | +1.238 |
uez | +1.217 |
enhagen | +1.190 |
nces | +1.147 |
Neg logit contributions | |
rigging | -0.936 |
sparing | -0.916 |
ONE | -0.913 |
discord | -0.867 |
Problem | -0.861 |
Token | rare |
Token ID | 4071 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
verts | +1.454 |
ements | +1.435 |
uez | +1.411 |
enhagen | +1.379 |
nces | +1.335 |
Neg logit contributions | |
rigging | -1.017 |
sparing | -0.999 |
ONE | -0.994 |
discord | -0.944 |
THING | -0.936 |
Token | case |
Token ID | 1339 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ements | +10.098 |
verts | +10.007 |
uez | +9.599 |
nces | +9.340 |
nesses | +9.178 |
Neg logit contributions | |
rigging | -8.230 |
sparing | -7.941 |
ONE | -7.917 |
Problem | -7.562 |
resonate | -7.559 |
Token | where |
Token ID | 810 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
verts | +6.864 |
uez | +6.635 |
ements | +6.602 |
enhagen | +6.292 |
nces | +6.185 |
Neg logit contributions | |
rigging | -7.554 |
sparing | -7.383 |
ONE | -7.342 |
Problem | -7.142 |
THING | -7.135 |
Token | two |
Token ID | 734 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
verts | +1.087 |
ements | +1.076 |
uez | +1.053 |
enhagen | +1.029 |
nesses | +0.994 |
Neg logit contributions | |
rigging | -0.856 |
sparing | -0.839 |
ONE | -0.838 |
discord | -0.797 |
THING | -0.794 |
Token | tapes |
Token ID | 23695 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
rigging | +2.831 |
ONE | +2.815 |
sparing | +2.793 |
discord | +2.720 |
THING | +2.668 |
Neg logit contributions | |
verts | -2.400 |
ements | -2.359 |
uez | -2.319 |
enhagen | -2.294 |
nces | -2.179 |
Token | are |
Token ID | 389 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
rigging | +1.448 |
sparing | +1.428 |
ONE | +1.403 |
discord | +1.362 |
underestimate | +1.356 |
Neg logit contributions | |
verts | -2.639 |
ements | -2.637 |
uez | -2.614 |
enhagen | -2.571 |
verages | -2.474 |
Token | ind |
Token ID | 773 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
ONE | +2.334 |
rigging | +2.319 |
sparing | +2.304 |
Problem | +2.231 |
THING | +2.193 |
Neg logit contributions | |
verts | -3.022 |
uez | -2.971 |
ements | -2.937 |
enhagen | -2.894 |
nces | -2.826 |
Token | irection |
Token ID | 4154 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
ONE | +3.205 |
sparing | +3.095 |
rigging | +3.026 |
Problem | +2.956 |
discord | +2.895 |
Neg logit contributions | |
enhagen | -6.313 |
verts | -6.306 |
ements | -6.292 |
uez | -6.259 |
verages | -6.213 |
Token | ( |
Token ID | 357 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
verts | +1.434 |
ements | +1.411 |
uez | +1.390 |
enhagen | +1.354 |
nces | +1.311 |
Neg logit contributions | |
rigging | -1.186 |
sparing | -1.168 |
ONE | -1.165 |
THING | -1.106 |
discord | -1.105 |
Token | e |
Token ID | 68 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
rigging | +0.956 |
ONE | +0.953 |
sparing | +0.936 |
Problem | +0.902 |
THING | +0.902 |
Neg logit contributions | |
verts | -1.197 |
ements | -1.190 |
uez | -1.179 |
enhagen | -1.152 |
nces | -1.117 |
Token | . |
Token ID | 13 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
verts | +5.154 |
ements | +5.046 |
uez | +4.894 |
enhagen | +4.704 |
nesses | +4.568 |
Neg logit contributions | |
rigging | -5.233 |
sparing | -5.056 |
ONE | -5.026 |
THING | -4.852 |
discord | -4.839 |
Token | g |
Token ID | 70 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
verts | +4.806 |
ements | +4.733 |
uez | +4.544 |
enhagen | +4.223 |
nesses | +4.211 |
Neg logit contributions | |
rigging | -5.382 |
sparing | -5.280 |
ONE | -5.173 |
discord | -5.073 |
resonate | -5.057 |
Token | ., |
Token ID | 1539 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
verts | +7.260 |
ements | +7.006 |
uez | +6.922 |
enhagen | +6.338 |
ellig | +6.321 |
Neg logit contributions | |
rigging | -10.679 |
sparing | -10.606 |
ONE | -10.501 |
discord | -10.152 |
THING | -10.118 |
Token | a |
Token ID | 257 |
Feature activation | -7.59e-02 |
Pos logit contributions | |
verts | +1.281 |
ements | +1.263 |
uez | +1.241 |
enhagen | +1.213 |
nces | +1.174 |
Neg logit contributions | |
rigging | -1.049 |
sparing | -1.029 |
ONE | -1.025 |
THING | -0.973 |
discord | -0.972 |
Token | ` |
Token ID | 4600 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
verts | +0.481 |
ements | +0.473 |
uez | +0.466 |
enhagen | +0.458 |
nces | +0.445 |
Neg logit contributions | |
rigging | -0.377 |
ONE | -0.372 |
sparing | -0.370 |
THING | -0.352 |
Problem | -0.351 |
Token | Box |
Token ID | 14253 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
rigging | +0.249 |
ONE | +0.248 |
sparing | +0.243 |
Problem | +0.234 |
THING | +0.234 |
Neg logit contributions | |
verts | -0.323 |
ements | -0.321 |
uez | -0.315 |
enhagen | -0.311 |
nces | -0.300 |
Token | `, |
Token ID | 47671 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
rigging | +1.205 |
ONE | +1.198 |
sparing | +1.185 |
Problem | +1.140 |
THING | +1.123 |
Neg logit contributions | |
verts | -1.642 |
ements | -1.609 |
uez | -1.604 |
enhagen | -1.563 |
nces | -1.516 |
Token | with |
Token ID | 351 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
verts | +0.250 |
ements | +0.246 |
uez | +0.243 |
enhagen | +0.238 |
nces | +0.232 |
Neg logit contributions | |
rigging | -0.172 |
sparing | -0.170 |
ONE | -0.168 |
discord | -0.158 |
centre | -0.158 |
Token | Monaco |
Token ID | 31630 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
verts | +1.711 |
ements | +1.682 |
uez | +1.653 |
enhagen | +1.604 |
nces | +1.555 |
Neg logit contributions | |
rigging | -1.576 |
ONE | -1.548 |
sparing | -1.547 |
discord | -1.477 |
THING | -1.473 |
Token | in |
Token ID | 287 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
verts | +0.390 |
ements | +0.385 |
uez | +0.378 |
enhagen | +0.367 |
nces | +0.359 |
Neg logit contributions | |
rigging | -0.305 |
sparing | -0.300 |
ONE | -0.299 |
discord | -0.283 |
THING | -0.283 |
Token | 2008 |
Token ID | 3648 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
verts | +0.507 |
ements | +0.501 |
uez | +0.493 |
enhagen | +0.480 |
nces | +0.465 |
Neg logit contributions | |
rigging | -0.525 |
sparing | -0.514 |
ONE | -0.509 |
discord | -0.493 |
centre | -0.489 |
Token | , |
Token ID | 11 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
rigging | +1.966 |
sparing | +1.922 |
ONE | +1.913 |
centre | +1.843 |
discord | +1.839 |
Neg logit contributions | |
verts | -2.448 |
ements | -2.416 |
uez | -2.375 |
nces | -2.295 |
enhagen | -2.275 |
Token | president |
Token ID | 1893 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
rigging | +0.566 |
sparing | +0.554 |
ONE | +0.554 |
discord | +0.527 |
THING | +0.524 |
Neg logit contributions | |
verts | -0.720 |
ements | -0.709 |
uez | -0.696 |
enhagen | -0.675 |
nces | -0.668 |
Token | Jerome |
Token ID | 33617 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
rigging | +4.874 |
sparing | +4.776 |
ONE | +4.749 |
centre | +4.656 |
discord | +4.648 |
Neg logit contributions | |
verts | -5.848 |
enhagen | -5.678 |
uez | -5.659 |
ements | -5.608 |
verages | -5.549 |
Token | de |
Token ID | 390 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
verts | +1.424 |
ements | +1.395 |
uez | +1.361 |
enhagen | +1.339 |
nces | +1.292 |
Neg logit contributions | |
rigging | -1.321 |
ONE | -1.303 |
sparing | -1.297 |
discord | -1.238 |
THING | -1.234 |
Token | B |
Token ID | 347 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
verts | +1.973 |
ements | +1.938 |
uez | +1.901 |
enhagen | +1.843 |
nces | +1.777 |
Neg logit contributions | |
rigging | -2.000 |
sparing | -1.965 |
ONE | -1.964 |
THING | -1.876 |
discord | -1.870 |
Token | ont |
Token ID | 756 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
verts | +2.872 |
ements | +2.830 |
uez | +2.774 |
enhagen | +2.693 |
nces | +2.592 |
Neg logit contributions | |
rigging | -2.755 |
sparing | -2.706 |
ONE | -2.694 |
THING | -2.579 |
discord | -2.569 |
Token | in |
Token ID | 259 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
verts | +0.901 |
ements | +0.877 |
uez | +0.866 |
enhagen | +0.844 |
nces | +0.823 |
Neg logit contributions | |
rigging | -0.660 |
sparing | -0.652 |
ONE | -0.650 |
discord | -0.617 |
THING | -0.609 |
Token | global |
Token ID | 3298 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
rigging | +1.308 |
sparing | +1.268 |
ONE | +1.249 |
discord | +1.215 |
centre | +1.200 |
Neg logit contributions | |
verts | -1.749 |
ements | -1.726 |
enhagen | -1.710 |
uez | -1.704 |
verages | -1.614 |
Token | citizens |
Token ID | 4290 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
rigging | +3.393 |
sparing | +3.233 |
discord | +3.200 |
ONE | +3.196 |
centre | +3.167 |
Neg logit contributions | |
enhagen | -4.486 |
verts | -4.460 |
ements | -4.394 |
uez | -4.372 |
nces | -4.202 |
Token | , |
Token ID | 11 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
rigging | +0.184 |
sparing | +0.180 |
ONE | +0.178 |
discord | +0.172 |
centre | +0.170 |
Neg logit contributions | |
verts | -0.212 |
ements | -0.208 |
uez | -0.206 |
enhagen | -0.202 |
nces | -0.193 |
Token | and |
Token ID | 290 |
Feature activation | +9.26e-02 |
Pos logit contributions | |
verts | +2.919 |
ements | +2.875 |
uez | +2.825 |
enhagen | +2.749 |
nces | +2.666 |
Neg logit contributions | |
rigging | -2.179 |
ONE | -2.137 |
sparing | -2.134 |
THING | -2.026 |
Problem | -2.014 |
Token | it |
Token ID | 340 |
Feature activation | +2.46e-04 |
Pos logit contributions | |
rigging | +0.460 |
sparing | +0.454 |
ONE | +0.440 |
discord | +0.427 |
centre | +0.421 |
Neg logit contributions | |
verts | -0.592 |
ements | -0.584 |
uez | -0.581 |
enhagen | -0.572 |
nces | -0.547 |
Token | begins |
Token ID | 6140 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
rigging | +0.001 |
sparing | +0.001 |
ONE | +0.001 |
discord | +0.001 |
centre | +0.001 |
Neg logit contributions | |
verts | -0.001 |
uez | -0.001 |
ements | -0.001 |
enhagen | -0.001 |
nesses | -0.001 |
Token | with |
Token ID | 351 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
rigging | +4.633 |
sparing | +4.539 |
ONE | +4.265 |
orally | +4.200 |
centre | +4.184 |
Neg logit contributions | |
verts | -6.309 |
uez | -6.218 |
enhagen | -6.195 |
ements | -6.184 |
bats | -5.924 |
Token | understanding |
Token ID | 4547 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
rigging | +4.260 |
sparing | +4.144 |
ONE | +3.916 |
discord | +3.885 |
centre | +3.836 |
Neg logit contributions | |
ements | -6.046 |
verts | -6.024 |
uez | -5.963 |
enhagen | -5.954 |
bats | -5.721 |
Token | who |
Token ID | 508 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
verts | +0.402 |
ements | +0.397 |
uez | +0.388 |
enhagen | +0.384 |
nces | +0.367 |
Neg logit contributions | |
rigging | -0.380 |
sparing | -0.373 |
ONE | -0.369 |
discord | -0.357 |
THING | -0.352 |
Token | we |
Token ID | 356 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
verts | +3.130 |
ements | +3.067 |
uez | +3.007 |
enhagen | +2.907 |
nces | +2.810 |
Neg logit contributions | |
rigging | -3.211 |
ONE | -3.166 |
sparing | -3.160 |
THING | -3.026 |
Problem | -3.013 |
Token | are |
Token ID | 389 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
verts | +0.916 |
ements | +0.905 |
uez | +0.893 |
enhagen | +0.874 |
nces | +0.848 |
Neg logit contributions | |
rigging | -0.535 |
sparing | -0.525 |
ONE | -0.521 |
discord | -0.492 |
underestimate | -0.490 |
Token | ator |
Token ID | 1352 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
centre | +2.087 |
rigging | +2.040 |
ONE | +2.022 |
sparing | +1.870 |
Problem | +1.829 |
Neg logit contributions | |
verts | -6.637 |
enhagen | -6.563 |
ements | -6.545 |
inventoryQuantity | -6.517 |
verages | -6.473 |
Token | , |
Token ID | 11 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
rigging | +2.255 |
sparing | +2.214 |
ONE | +2.180 |
centre | +2.131 |
discord | +2.094 |
Neg logit contributions | |
verts | -2.733 |
ements | -2.721 |
uez | -2.676 |
enhagen | -2.583 |
nesses | -2.530 |
Token | cent |
Token ID | 1247 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
rigging | +0.731 |
sparing | +0.720 |
ONE | +0.704 |
centre | +0.686 |
discord | +0.685 |
Neg logit contributions | |
ements | -0.831 |
verts | -0.825 |
uez | -0.813 |
enhagen | -0.799 |
nces | -0.770 |
Token | rip |
Token ID | 5528 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
rigging | +0.502 |
ONE | +0.495 |
sparing | +0.495 |
discord | +0.453 |
THING | +0.452 |
Neg logit contributions | |
verts | -1.113 |
ements | -1.106 |
uez | -1.094 |
enhagen | -1.067 |
nces | -1.055 |
Token | et |
Token ID | 316 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
ONE | +0.661 |
rigging | +0.660 |
sparing | +0.652 |
Problem | +0.631 |
centre | +0.625 |
Neg logit contributions | |
verts | -0.587 |
ements | -0.582 |
uez | -0.570 |
enhagen | -0.565 |
nces | -0.558 |
Token | al |
Token ID | 282 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
rigging | +1.801 |
ONE | +1.736 |
sparing | +1.717 |
centre | +1.667 |
Problem | +1.624 |
Neg logit contributions | |
ements | -3.677 |
verts | -3.665 |
enhagen | -3.614 |
uez | -3.613 |
nesses | -3.497 |
Token | acceleration |
Token ID | 20309 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
rigging | +3.431 |
sparing | +3.252 |
centre | +3.175 |
discord | +3.000 |
resonate | +2.933 |
Neg logit contributions | |
ements | -8.146 |
uez | -8.134 |
enhagen | -7.981 |
verts | -7.856 |
nces | -7.809 |
Token | only |
Token ID | 691 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
ements | +0.141 |
verts | +0.141 |
uez | +0.139 |
enhagen | +0.136 |
nces | +0.130 |
Neg logit contributions | |
rigging | -0.137 |
sparing | -0.135 |
ONE | -0.131 |
discord | -0.128 |
centre | -0.127 |
Token | counter |
Token ID | 3753 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
verts | +0.056 |
ements | +0.056 |
uez | +0.055 |
enhagen | +0.054 |
nces | +0.051 |
Neg logit contributions | |
sparing | -0.063 |
rigging | -0.062 |
ONE | -0.060 |
discord | -0.059 |
centre | -0.059 |
Token | acts |
Token ID | 8656 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
verts | +2.010 |
ements | +2.005 |
uez | +1.997 |
enhagen | +1.925 |
nesses | +1.841 |
Neg logit contributions | |
rigging | -1.926 |
sparing | -1.892 |
ONE | -1.887 |
Problem | -1.798 |
THING | -1.793 |
Token | Earth |
Token ID | 3668 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
rigging | +1.924 |
sparing | +1.908 |
centre | +1.840 |
ONE | +1.813 |
discord | +1.813 |
Neg logit contributions | |
ements | -2.462 |
uez | -2.430 |
verts | -2.405 |
enhagen | -2.383 |
nces | -2.292 |
Token | the |
Token ID | 262 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
verts | +4.157 |
ements | +4.100 |
uez | +4.012 |
enhagen | +3.887 |
nesses | +3.773 |
Neg logit contributions | |
rigging | -3.375 |
ONE | -3.313 |
sparing | -3.305 |
THING | -3.155 |
Problem | -3.149 |
Token | way |
Token ID | 835 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
verts | +4.653 |
ements | +4.586 |
uez | +4.481 |
enhagen | +4.342 |
nesses | +4.232 |
Neg logit contributions | |
rigging | -3.416 |
ONE | -3.359 |
sparing | -3.351 |
THING | -3.201 |
Problem | -3.195 |
Token | to |
Token ID | 284 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
verts | +4.177 |
ements | +4.120 |
uez | +4.022 |
enhagen | +3.844 |
nesses | +3.745 |
Neg logit contributions | |
rigging | -5.078 |
ONE | -4.984 |
sparing | -4.968 |
THING | -4.795 |
Problem | -4.785 |
Token | modify |
Token ID | 13096 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
verts | +1.602 |
ements | +1.578 |
uez | +1.549 |
enhagen | +1.521 |
nces | +1.474 |
Neg logit contributions | |
rigging | -1.223 |
sparing | -1.200 |
ONE | -1.193 |
discord | -1.135 |
underestimate | -1.130 |
Token | it |
Token ID | 340 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
rigging | +0.260 |
sparing | +0.256 |
ONE | +0.250 |
discord | +0.243 |
centre | +0.241 |
Neg logit contributions | |
verts | -0.290 |
ements | -0.285 |
uez | -0.282 |
enhagen | -0.277 |
nces | -0.271 |
Token | ," |
Token ID | 553 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
verts | +2.175 |
ements | +2.137 |
uez | +2.099 |
enhagen | +2.038 |
nces | +1.966 |
Neg logit contributions | |
rigging | -2.104 |
sparing | -2.070 |
ONE | -2.063 |
THING | -1.968 |
discord | -1.964 |
Token | said |
Token ID | 531 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
centre | +3.865 |
ONE | +3.827 |
rigging | +3.816 |
sparing | +3.765 |
discord | +3.625 |
Neg logit contributions | |
verts | -7.674 |
ements | -7.630 |
uez | -7.405 |
enhagen | -7.405 |
nces | -7.355 |
Token | Elizabeth |
Token ID | 10674 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
rigging | +0.783 |
sparing | +0.767 |
ONE | +0.763 |
centre | +0.734 |
discord | +0.726 |
Neg logit contributions | |
verts | -1.266 |
ements | -1.255 |
uez | -1.234 |
enhagen | -1.209 |
nces | -1.181 |
Token | Mack |
Token ID | 16640 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
verts | +2.044 |
ements | +2.009 |
uez | +1.971 |
enhagen | +1.910 |
nces | +1.842 |
Neg logit contributions | |
rigging | -2.045 |
sparing | -2.010 |
ONE | -2.008 |
THING | -1.918 |
discord | -1.911 |
Token | enzie |
Token ID | 26389 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
verts | +3.801 |
ements | +3.737 |
uez | +3.693 |
enhagen | +3.602 |
nesses | +3.479 |
Neg logit contributions | |
rigging | -2.904 |
sparing | -2.831 |
ONE | -2.819 |
THING | -2.691 |
Problem | -2.671 |
Token | , |
Token ID | 11 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
verts | +2.577 |
ements | +2.529 |
uez | +2.486 |
enhagen | +2.401 |
nces | +2.315 |
Neg logit contributions | |
rigging | -2.605 |
sparing | -2.560 |
ONE | -2.548 |
THING | -2.450 |
Problem | -2.431 |
Token | much |
Token ID | 881 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
sparing | +4.183 |
rigging | +3.977 |
ONE | +3.836 |
discord | +3.829 |
underestimate | +3.764 |
Neg logit contributions | |
verts | -5.831 |
uez | -5.797 |
enhagen | -5.773 |
ements | -5.679 |
nces | -5.496 |
Token | as |
Token ID | 355 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
sparing | +4.018 |
rigging | +3.858 |
ONE | +3.718 |
discord | +3.681 |
centre | +3.642 |
Neg logit contributions | |
verts | -5.829 |
uez | -5.767 |
ements | -5.675 |
enhagen | -5.579 |
nces | -5.480 |
Token | $ |
Token ID | 720 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
rigging | +1.587 |
sparing | +1.584 |
ONE | +1.546 |
discord | +1.500 |
centre | +1.499 |
Neg logit contributions | |
verts | -1.488 |
ements | -1.454 |
uez | -1.449 |
enhagen | -1.382 |
nces | -1.364 |
Token | 15 |
Token ID | 1314 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
ONE | +1.904 |
rigging | +1.797 |
Problem | +1.769 |
sparing | +1.758 |
THING | +1.739 |
Neg logit contributions | |
verts | -2.749 |
ements | -2.742 |
uez | -2.717 |
enhagen | -2.711 |
nces | -2.620 |
Token | million |
Token ID | 1510 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
rigging | +1.752 |
sparing | +1.740 |
ONE | +1.737 |
underestimate | +1.629 |
discord | +1.627 |
Neg logit contributions | |
verts | -2.198 |
ements | -2.159 |
uez | -2.143 |
enhagen | -2.091 |
nces | -2.019 |
Token | after |
Token ID | 706 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
sparing | +1.961 |
rigging | +1.935 |
ONE | +1.885 |
centre | +1.793 |
orally | +1.790 |
Neg logit contributions | |
verts | -2.745 |
ements | -2.738 |
uez | -2.724 |
enhagen | -2.627 |
nces | -2.594 |
Token | next |
Token ID | 1306 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
sparing | +6.011 |
rigging | +5.950 |
centre | +5.481 |
ONE | +5.437 |
discord | +5.340 |
Neg logit contributions | |
ements | -7.681 |
uez | -7.527 |
verts | -7.412 |
nces | -7.322 |
ellig | -7.284 |
Token | season |
Token ID | 1622 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
rigging | +0.154 |
sparing | +0.151 |
ONE | +0.149 |
discord | +0.141 |
THING | +0.141 |
Neg logit contributions | |
verts | -0.221 |
ements | -0.220 |
uez | -0.215 |
enhagen | -0.210 |
nces | -0.206 |
Token | instead |
Token ID | 2427 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
rigging | +2.619 |
sparing | +2.609 |
ONE | +2.502 |
centre | +2.430 |
orally | +2.414 |
Neg logit contributions | |
verts | -3.233 |
ements | -3.207 |
uez | -3.177 |
enhagen | -3.073 |
nces | -3.011 |
Token | of |
Token ID | 286 |
Feature activation | -7.58e-02 |
Pos logit contributions | |
verts | +2.779 |
ements | +2.746 |
uez | +2.626 |
enhagen | +2.598 |
nesses | +2.482 |
Neg logit contributions | |
rigging | -3.097 |
ONE | -3.069 |
sparing | -3.031 |
THING | -2.954 |
Problem | -2.944 |
Token | the |
Token ID | 262 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
verts | +0.468 |
ements | +0.461 |
uez | +0.455 |
enhagen | +0.442 |
nces | +0.431 |
Neg logit contributions | |
rigging | -0.393 |
sparing | -0.389 |
ONE | -0.380 |
discord | -0.364 |
underestimate | -0.362 |
Token | in |
Token ID | 287 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
verts | +0.102 |
ements | +0.100 |
uez | +0.099 |
enhagen | +0.097 |
nces | +0.093 |
Neg logit contributions | |
rigging | -0.085 |
sparing | -0.084 |
ONE | -0.081 |
centre | -0.079 |
discord | -0.079 |
Token | that |
Token ID | 326 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
verts | +0.795 |
ements | +0.788 |
uez | +0.771 |
enhagen | +0.757 |
nces | +0.722 |
Neg logit contributions | |
rigging | -0.822 |
sparing | -0.812 |
ONE | -0.805 |
discord | -0.770 |
centre | -0.769 |
Token | game |
Token ID | 983 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
verts | +3.468 |
ements | +3.415 |
uez | +3.363 |
enhagen | +3.272 |
nces | +3.179 |
Neg logit contributions | |
rigging | -2.292 |
ONE | -2.244 |
sparing | -2.243 |
THING | -2.120 |
Problem | -2.112 |
Token | and |
Token ID | 290 |
Feature activation | -9.22e-02 |
Pos logit contributions | |
verts | +1.065 |
ements | +1.051 |
uez | +1.031 |
enhagen | +1.008 |
nces | +0.967 |
Neg logit contributions | |
rigging | -0.988 |
sparing | -0.972 |
ONE | -0.960 |
discord | -0.920 |
centre | -0.914 |
Token | I |
Token ID | 314 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
verts | +0.555 |
ements | +0.546 |
uez | +0.536 |
enhagen | +0.526 |
nces | +0.505 |
Neg logit contributions | |
rigging | -0.493 |
sparing | -0.484 |
ONE | -0.480 |
discord | -0.459 |
centre | -0.457 |
Token | think |
Token ID | 892 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
rigging | +0.193 |
sparing | +0.190 |
ONE | +0.185 |
centre | +0.180 |
underestimate | +0.180 |
Neg logit contributions | |
verts | -0.288 |
ements | -0.283 |
uez | -0.279 |
enhagen | -0.275 |
verages | -0.265 |
Token | only |
Token ID | 691 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
rigging | +0.916 |
sparing | +0.901 |
ONE | +0.884 |
centre | +0.856 |
discord | +0.856 |
Neg logit contributions | |
verts | -0.920 |
ements | -0.908 |
uez | -0.892 |
enhagen | -0.883 |
nces | -0.846 |
Token | ( |
Token ID | 357 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
rigging | +1.791 |
sparing | +1.785 |
ONE | +1.732 |
centre | +1.675 |
underestimate | +1.660 |
Neg logit contributions | |
verts | -2.369 |
ements | -2.345 |
uez | -2.303 |
enhagen | -2.300 |
nces | -2.222 |
Token | Ram |
Token ID | 33754 |
Feature activation | +3.95e-03 |
Pos logit contributions | |
ONE | +0.904 |
rigging | +0.896 |
sparing | +0.866 |
Problem | +0.839 |
THING | +0.833 |
Neg logit contributions | |
verts | -1.268 |
ements | -1.259 |
uez | -1.247 |
enhagen | -1.223 |
nces | -1.187 |
Token | na |
Token ID | 2616 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
rigging | +0.019 |
ONE | +0.019 |
sparing | +0.019 |
discord | +0.018 |
centre | +0.018 |
Neg logit contributions | |
verts | -0.025 |
ements | -0.025 |
uez | -0.024 |
enhagen | -0.024 |
verages | -0.023 |
Token | resh |
Token ID | 3447 |
Feature activation | -5.59e-02 |
Pos logit contributions | |
rigging | +0.620 |
sparing | +0.609 |
ONE | +0.605 |
discord | +0.579 |
centre | +0.577 |
Neg logit contributions | |
verts | -0.712 |
ements | -0.697 |
enhagen | -0.685 |
uez | -0.676 |
nces | -0.664 |
Token |
|
Token ID | 198 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
rigging | +0.282 |
ONE | +0.279 |
sparing | +0.277 |
discord | +0.264 |
Problem | +0.264 |
Neg logit contributions | |
verts | -0.355 |
ements | -0.350 |
uez | -0.343 |
enhagen | -0.337 |
nces | -0.326 |
Token |
|
Token ID | 198 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
rigging | +0.083 |
ONE | +0.082 |
sparing | +0.081 |
Problem | +0.078 |
THING | +0.077 |
Neg logit contributions | |
verts | -0.105 |
ements | -0.103 |
uez | -0.102 |
enhagen | -0.101 |
nces | -0.097 |
Token | K |
Token ID | 42 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
verts | +0.661 |
ements | +0.654 |
uez | +0.642 |
enhagen | +0.634 |
nces | +0.611 |
Neg logit contributions | |
ONE | -0.472 |
rigging | -0.471 |
sparing | -0.459 |
Problem | -0.446 |
THING | -0.441 |
Token | ol |
Token ID | 349 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
verts | +0.878 |
ements | +0.863 |
uez | +0.848 |
enhagen | +0.828 |
nces | +0.803 |
Neg logit contributions | |
rigging | -0.692 |
ONE | -0.683 |
sparing | -0.676 |
THING | -0.644 |
Problem | -0.643 |
Token | omo |
Token ID | 17902 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
rigging | +0.660 |
ONE | +0.653 |
sparing | +0.649 |
Problem | +0.621 |
THING | +0.621 |
Neg logit contributions | |
verts | -0.563 |
ements | -0.551 |
uez | -0.538 |
enhagen | -0.522 |
nces | -0.506 |
Token | isky |
Token ID | 34041 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
verts | +1.441 |
ements | +1.415 |
uez | +1.390 |
enhagen | +1.348 |
nesses | +1.300 |
Neg logit contributions | |
rigging | -1.349 |
sparing | -1.325 |
ONE | -1.323 |
THING | -1.263 |
discord | -1.259 |
Token | did |
Token ID | 750 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
rigging | +2.304 |
sparing | +2.226 |
ONE | +2.207 |
centre | +2.129 |
Problem | +2.115 |
Neg logit contributions | |
verts | -2.766 |
ements | -2.730 |
enhagen | -2.652 |
uez | -2.623 |
nces | -2.609 |
Token | not |
Token ID | 407 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
verts | +0.593 |
ements | +0.584 |
uez | +0.574 |
enhagen | +0.561 |
nces | +0.544 |
Neg logit contributions | |
rigging | -0.404 |
sparing | -0.396 |
ONE | -0.394 |
THING | -0.372 |
discord | -0.371 |
Token | respond |
Token ID | 3031 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
verts | +1.750 |
ements | +1.726 |
uez | +1.701 |
enhagen | +1.668 |
nces | +1.623 |
Neg logit contributions | |
rigging | -0.859 |
sparing | -0.839 |
ONE | -0.833 |
discord | -0.776 |
THING | -0.775 |
Token | to |
Token ID | 284 |
Feature activation | +8.20e-02 |
Pos logit contributions | |
rigging | +0.110 |
sparing | +0.108 |
ONE | +0.108 |
discord | +0.103 |
THING | +0.103 |
Neg logit contributions | |
verts | -0.099 |
ements | -0.097 |
uez | -0.095 |
enhagen | -0.093 |
verages | -0.089 |
Token | requests |
Token ID | 7007 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
rigging | +0.450 |
sparing | +0.443 |
ONE | +0.441 |
discord | +0.427 |
orally | +0.420 |
Neg logit contributions | |
verts | -0.478 |
ements | -0.465 |
uez | -0.460 |
enhagen | -0.449 |
verages | -0.435 |
Token | , |
Token ID | 11 |
Feature activation | -2.62e-03 |
Pos logit contributions | |
verts | +1.200 |
ements | +1.176 |
uez | +1.160 |
enhagen | +1.131 |
nces | +1.092 |
Neg logit contributions | |
rigging | -1.040 |
sparing | -1.020 |
ONE | -1.013 |
discord | -0.963 |
Problem | -0.961 |
Token | Government |
Token ID | 5070 |
Feature activation | +9.55e-02 |
Pos logit contributions | |
verts | +0.016 |
ements | +0.016 |
uez | +0.016 |
enhagen | +0.015 |
nces | +0.015 |
Neg logit contributions | |
rigging | -0.014 |
sparing | -0.014 |
ONE | -0.013 |
centre | -0.013 |
discord | -0.013 |
Token | should |
Token ID | 815 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
rigging | +0.498 |
sparing | +0.489 |
ONE | +0.483 |
centre | +0.466 |
discord | +0.466 |
Neg logit contributions | |
verts | -0.588 |
ements | -0.573 |
uez | -0.572 |
enhagen | -0.564 |
nces | -0.542 |
Token | immediately |
Token ID | 3393 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
rigging | +0.798 |
sparing | +0.792 |
ONE | +0.757 |
centre | +0.753 |
discord | +0.738 |
Neg logit contributions | |
verts | -1.277 |
ements | -1.247 |
uez | -1.239 |
enhagen | -1.226 |
nces | -1.183 |
Token | bring |
Token ID | 2222 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
rigging | +0.687 |
sparing | +0.679 |
ONE | +0.654 |
centre | +0.644 |
discord | +0.635 |
Neg logit contributions | |
verts | -1.096 |
ements | -1.073 |
uez | -1.063 |
enhagen | -1.053 |
nces | -1.019 |
Token | amendments |
Token ID | 17835 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
rigging | +2.041 |
sparing | +2.023 |
centre | +1.939 |
ONE | +1.934 |
discord | +1.895 |
Neg logit contributions | |
verts | -3.126 |
ements | -3.062 |
uez | -3.046 |
enhagen | -3.034 |
nesses | -2.885 |
Token | to |
Token ID | 284 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
rigging | +0.426 |
sparing | +0.421 |
ONE | +0.410 |
centre | +0.397 |
orally | +0.395 |
Neg logit contributions | |
verts | -0.461 |
uez | -0.454 |
ements | -0.448 |
enhagen | -0.436 |
nces | -0.423 |
Token | the |
Token ID | 262 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
rigging | +2.537 |
sparing | +2.526 |
ONE | +2.425 |
centre | +2.395 |
discord | +2.348 |
Neg logit contributions | |
uez | -2.929 |
verts | -2.925 |
ements | -2.880 |
enhagen | -2.789 |
nces | -2.734 |
Token | present |
Token ID | 1944 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
rigging | +1.962 |
sparing | +1.929 |
ONE | +1.892 |
centre | +1.850 |
discord | +1.832 |
Neg logit contributions | |
verts | -1.960 |
uez | -1.933 |
ements | -1.901 |
enhagen | -1.868 |
nces | -1.790 |
Token | Motor |
Token ID | 12533 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
rigging | +2.190 |
sparing | +2.147 |
ONE | +2.099 |
centre | +2.050 |
Problem | +2.025 |
Neg logit contributions | |
verts | -2.388 |
uez | -2.334 |
ements | -2.310 |
enhagen | -2.301 |
nces | -2.198 |
Token | Vehicle |
Token ID | 21501 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
verts | +2.624 |
ements | +2.586 |
uez | +2.523 |
enhagen | +2.401 |
nesses | +2.350 |
Neg logit contributions | |
rigging | -2.887 |
sparing | -2.824 |
ONE | -2.821 |
THING | -2.729 |
discord | -2.696 |
Token | � |
Token ID | 447 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
rigging | +1.517 |
ONE | +1.502 |
sparing | +1.500 |
underestimate | +1.464 |
Problem | +1.425 |
Neg logit contributions | |
verts | -2.817 |
ements | -2.761 |
uez | -2.727 |
enhagen | -2.647 |
bats | -2.607 |
Token | � |
Token ID | 247 |
Feature activation | -1.37e-03 |
Pos logit contributions | |
verts | +2.264 |
ements | +2.224 |
uez | +2.186 |
enhagen | +2.112 |
nces | +2.040 |
Neg logit contributions | |
rigging | -2.274 |
sparing | -2.232 |
ONE | -2.229 |
THING | -2.127 |
discord | -2.122 |
Token | re |
Token ID | 260 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
verts | +0.009 |
ements | +0.009 |
uez | +0.009 |
enhagen | +0.009 |
nces | +0.009 |
Neg logit contributions | |
rigging | -0.006 |
ONE | -0.006 |
sparing | -0.006 |
underestimate | -0.006 |
Problem | -0.006 |
Token | supposed |
Token ID | 4385 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
rigging | +0.877 |
sparing | +0.863 |
ONE | +0.849 |
underestimate | +0.799 |
discord | +0.798 |
Neg logit contributions | |
verts | -1.460 |
ements | -1.435 |
uez | -1.425 |
enhagen | -1.387 |
nces | -1.357 |
Token | to |
Token ID | 284 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
verts | +1.844 |
ements | +1.809 |
uez | +1.770 |
enhagen | +1.707 |
nesses | +1.644 |
Neg logit contributions | |
rigging | -2.284 |
ONE | -2.249 |
sparing | -2.246 |
THING | -2.159 |
Problem | -2.148 |
Token | teach |
Token ID | 4545 |
Feature activation | +2.67e-03 |
Pos logit contributions | |
verts | +3.191 |
ements | +3.139 |
uez | +3.094 |
enhagen | +3.004 |
nesses | +2.925 |
Neg logit contributions | |
rigging | -2.275 |
ONE | -2.233 |
sparing | -2.221 |
THING | -2.113 |
Problem | -2.100 |
Token | citizenship |
Token ID | 14218 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
rigging | +0.013 |
sparing | +0.013 |
ONE | +0.013 |
discord | +0.013 |
centre | +0.012 |
Neg logit contributions | |
verts | -0.017 |
ements | -0.017 |
uez | -0.016 |
enhagen | -0.016 |
nces | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
verts | +0.884 |
ements | +0.870 |
uez | +0.862 |
enhagen | +0.831 |
nces | +0.805 |
Neg logit contributions | |
rigging | -0.814 |
sparing | -0.800 |
ONE | -0.794 |
discord | -0.759 |
THING | -0.758 |
Token | � |
Token ID | 447 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
ONE | +0.546 |
rigging | +0.541 |
sparing | +0.528 |
Problem | +0.522 |
THING | +0.517 |
Neg logit contributions | |
verts | -0.643 |
ements | -0.635 |
uez | -0.625 |
enhagen | -0.610 |
nces | -0.592 |
Token | � |
Token ID | 251 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
rigging | +0.838 |
ONE | +0.830 |
sparing | +0.825 |
Problem | +0.795 |
THING | +0.792 |
Neg logit contributions | |
verts | -0.744 |
ements | -0.733 |
uez | -0.719 |
enhagen | -0.696 |
nces | -0.667 |
Token |
|
Token ID | 198 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
ONE | +1.633 |
rigging | +1.609 |
sparing | +1.564 |
Problem | +1.555 |
THING | +1.536 |
Neg logit contributions | |
verts | -1.945 |
ements | -1.901 |
uez | -1.872 |
enhagen | -1.821 |
nces | -1.778 |
Token | on |
Token ID | 319 |
Feature activation | +8.93e-02 |
Pos logit contributions | |
rigging | +1.986 |
sparing | +1.983 |
ONE | +1.908 |
discord | +1.844 |
centre | +1.836 |
Neg logit contributions | |
verts | -2.835 |
uez | -2.794 |
ements | -2.753 |
enhagen | -2.728 |
nces | -2.681 |
Token | the |
Token ID | 262 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
rigging | +0.456 |
sparing | +0.447 |
ONE | +0.440 |
discord | +0.429 |
centre | +0.424 |
Neg logit contributions | |
verts | -0.549 |
ements | -0.546 |
uez | -0.534 |
enhagen | -0.528 |
nces | -0.520 |
Token | local |
Token ID | 1957 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
verts | +0.902 |
ements | +0.891 |
uez | +0.881 |
enhagen | +0.859 |
nces | +0.840 |
Neg logit contributions | |
rigging | -0.620 |
sparing | -0.605 |
ONE | -0.603 |
discord | -0.573 |
centre | -0.567 |
Token | currency |
Token ID | 7395 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
verts | +0.987 |
ements | +0.977 |
uez | +0.963 |
enhagen | +0.937 |
nces | +0.911 |
Neg logit contributions | |
rigging | -0.852 |
ONE | -0.837 |
sparing | -0.834 |
discord | -0.796 |
THING | -0.788 |
Token | including |
Token ID | 1390 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
verts | +4.659 |
ements | +4.548 |
uez | +4.477 |
enhagen | +4.340 |
nesses | +4.172 |
Neg logit contributions | |
rigging | -4.262 |
ONE | -4.219 |
sparing | -4.182 |
THING | -4.039 |
Problem | -4.006 |
Token | the |
Token ID | 262 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
rigging | +0.710 |
sparing | +0.699 |
ONE | +0.676 |
discord | +0.651 |
centre | +0.644 |
Neg logit contributions | |
verts | -0.995 |
ements | -0.985 |
uez | -0.968 |
enhagen | -0.955 |
nces | -0.923 |
Token | requirement |
Token ID | 9079 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
rigging | +0.130 |
sparing | +0.128 |
ONE | +0.125 |
discord | +0.120 |
centre | +0.119 |
Neg logit contributions | |
verts | -0.169 |
ements | -0.167 |
uez | -0.165 |
enhagen | -0.161 |
nces | -0.156 |
Token | to |
Token ID | 284 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
verts | +0.642 |
ements | +0.630 |
uez | +0.616 |
enhagen | +0.594 |
nces | +0.573 |
Neg logit contributions | |
rigging | -0.822 |
sparing | -0.812 |
ONE | -0.809 |
discord | -0.775 |
THING | -0.773 |
Token | apply |
Token ID | 4174 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
rigging | +0.381 |
sparing | +0.378 |
ONE | +0.364 |
underestimate | +0.352 |
discord | +0.351 |
Neg logit contributions | |
verts | -0.613 |
ements | -0.609 |
uez | -0.596 |
enhagen | -0.590 |
nces | -0.572 |
Token | some |
Token ID | 617 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
rigging | +3.396 |
sparing | +3.382 |
discord | +3.178 |
centre | +3.156 |
ONE | +3.155 |
Neg logit contributions | |
ements | -3.913 |
verts | -3.882 |
uez | -3.833 |
enhagen | -3.733 |
inventoryQuantity | -3.662 |
Token | or |
Token ID | 393 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
rigging | +2.894 |
sparing | +2.826 |
ONE | +2.804 |
centre | +2.660 |
discord | +2.645 |
Neg logit contributions | |
verts | -4.077 |
uez | -4.048 |
ements | -4.010 |
enhagen | -3.944 |
nesses | -3.811 |
Token | discussion |
Token ID | 5114 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
verts | +0.192 |
ements | +0.189 |
uez | +0.186 |
enhagen | +0.182 |
nces | +0.178 |
Neg logit contributions | |
rigging | -0.133 |
sparing | -0.128 |
ONE | -0.127 |
discord | -0.123 |
THING | -0.121 |
Token | ( |
Token ID | 357 |
Feature activation | +7.97e-02 |
Pos logit contributions | |
rigging | +0.626 |
sparing | +0.610 |
ONE | +0.608 |
discord | +0.586 |
THING | +0.577 |
Neg logit contributions | |
verts | -0.735 |
ements | -0.721 |
uez | -0.715 |
enhagen | -0.697 |
nces | -0.680 |
Token | even |
Token ID | 10197 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
ONE | +0.403 |
rigging | +0.403 |
sparing | +0.392 |
Problem | +0.380 |
THING | +0.378 |
Neg logit contributions | |
verts | -0.494 |
ements | -0.488 |
uez | -0.482 |
enhagen | -0.470 |
nces | -0.456 |
Token | mang |
Token ID | 45663 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
rigging | +1.431 |
sparing | +1.401 |
ONE | +1.385 |
discord | +1.329 |
THING | +1.314 |
Neg logit contributions | |
verts | -1.867 |
ements | -1.815 |
uez | -1.812 |
enhagen | -1.771 |
nces | -1.717 |
Token | achu |
Token ID | 32323 |
Feature activation | -8.12e-02 |
Pos logit contributions | |
rigging | +0.213 |
ONE | +0.207 |
sparing | +0.207 |
discord | +0.198 |
THING | +0.196 |
Neg logit contributions | |
verts | -0.242 |
ements | -0.235 |
uez | -0.230 |
enhagen | -0.226 |
nces | -0.223 |
Token | or |
Token ID | 393 |
Feature activation | -7.53e-02 |
Pos logit contributions | |
verts | +0.508 |
ements | +0.500 |
uez | +0.492 |
enhagen | +0.479 |
nesses | +0.465 |
Neg logit contributions | |
rigging | -0.412 |
sparing | -0.404 |
ONE | -0.403 |
discord | -0.384 |
THING | -0.383 |
Token | bre |
Token ID | 1449 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
verts | +0.451 |
ements | +0.445 |
uez | +0.435 |
enhagen | +0.426 |
nesses | +0.411 |
Neg logit contributions | |
rigging | -0.404 |
sparing | -0.397 |
ONE | -0.395 |
discord | -0.384 |
THING | -0.376 |
Token | ade |
Token ID | 671 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
verts | +0.948 |
ements | +0.936 |
uez | +0.918 |
enhagen | +0.901 |
verages | +0.872 |
Neg logit contributions | |
rigging | -0.826 |
ONE | -0.811 |
sparing | -0.806 |
discord | -0.774 |
THING | -0.769 |
Token | x |
Token ID | 87 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
verts | +0.336 |
ements | +0.331 |
uez | +0.326 |
enhagen | +0.318 |
nesses | +0.308 |
Neg logit contributions | |
rigging | -0.270 |
sparing | -0.264 |
ONE | -0.264 |
discord | -0.252 |
THING | -0.249 |
Token | pert |
Token ID | 11766 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
verts | +0.139 |
ements | +0.137 |
uez | +0.134 |
enhagen | +0.132 |
verages | +0.128 |
Neg logit contributions | |
rigging | -0.110 |
ONE | -0.107 |
sparing | -0.107 |
discord | -0.102 |
THING | -0.101 |
Token | at |
Token ID | 379 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
rigging | +1.904 |
ONE | +1.858 |
sparing | +1.853 |
discord | +1.788 |
underestimate | +1.756 |
Neg logit contributions | |
verts | -2.412 |
ements | -2.358 |
uez | -2.317 |
enhagen | -2.283 |
verages | -2.215 |
Token | ... |
Token ID | 2644 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
rigging | +1.779 |
ONE | +1.761 |
sparing | +1.759 |
Problem | +1.664 |
centre | +1.656 |
Neg logit contributions | |
verts | -2.728 |
ements | -2.707 |
uez | -2.664 |
enhagen | -2.598 |
nces | -2.542 |
Token | | |
Token ID | 930 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
verts | +0.944 |
ements | +0.929 |
uez | +0.913 |
enhagen | +0.890 |
nces | +0.861 |
Neg logit contributions | |
rigging | -0.780 |
ONE | -0.766 |
sparing | -0.765 |
THING | -0.727 |
discord | -0.724 |
Token | + |
Token ID | 1343 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
verts | +1.059 |
ements | +1.040 |
uez | +1.021 |
enhagen | +0.993 |
nces | +0.958 |
Neg logit contributions | |
rigging | -0.919 |
sparing | -0.900 |
ONE | -0.899 |
THING | -0.857 |
discord | -0.853 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
verts | +1.264 |
ements | +1.249 |
uez | +1.231 |
enhagen | +1.202 |
nesses | +1.175 |
Neg logit contributions | |
rigging | -0.504 |
sparing | -0.488 |
ONE | -0.484 |
THING | -0.446 |
discord | -0.445 |
Token | --+ |
Token ID | 44785 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
verts | +4.897 |
uez | +4.751 |
ements | +4.728 |
ellig | +4.455 |
enhagen | +4.418 |
Neg logit contributions | |
rigging | -4.000 |
sparing | -3.870 |
ONE | -3.742 |
resonate | -3.654 |
discord | -3.629 |
Token | + |
Token ID | 1343 |
Feature activation | -9.80e-02 |
Pos logit contributions | |
verts | +1.057 |
ements | +1.042 |
uez | +1.023 |
enhagen | +0.999 |
nces | +0.966 |
Neg logit contributions | |
rigging | -0.866 |
sparing | -0.851 |
ONE | -0.851 |
THING | -0.807 |
discord | -0.806 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
verts | +0.798 |
ements | +0.789 |
uez | +0.778 |
enhagen | +0.761 |
nces | +0.743 |
Neg logit contributions | |
rigging | -0.310 |
sparing | -0.301 |
ONE | -0.299 |
THING | -0.275 |
discord | -0.274 |
Token | --+ |
Token ID | 44785 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
verts | +5.122 |
uez | +4.982 |
ements | +4.949 |
ellig | +4.661 |
enhagen | +4.601 |
Neg logit contributions | |
rigging | -4.292 |
sparing | -4.143 |
ONE | -4.002 |
resonate | -3.926 |
discord | -3.878 |
Token | < |
Token ID | 1279 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
rigging | +2.745 |
ONE | +2.742 |
sparing | +2.731 |
Problem | +2.602 |
underestimate | +2.597 |
Neg logit contributions | |
verts | -2.815 |
ements | -2.762 |
uez | -2.741 |
enhagen | -2.646 |
bats | -2.568 |
Token | -- |
Token ID | 438 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
ONE | +1.025 |
rigging | +1.017 |
sparing | +0.995 |
Problem | +0.957 |
THING | +0.948 |
Neg logit contributions | |
verts | -1.954 |
ements | -1.946 |
enhagen | -1.924 |
uez | -1.917 |
nces | -1.846 |
Token | Start |
Token ID | 7253 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
verts | +4.962 |
ements | +4.785 |
uez | +4.656 |
enhagen | +4.489 |
verages | +4.378 |
Neg logit contributions | |
rigging | -5.560 |
sparing | -5.472 |
ONE | -5.405 |
discord | -5.266 |
underestimate | -5.197 |
Token | rock |
Token ID | 3881 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
ONE | +2.522 |
sparing | +2.476 |
rigging | +2.443 |
THING | +2.347 |
centre | +2.334 |
Neg logit contributions | |
verts | -3.141 |
uez | -3.047 |
ements | -3.036 |
enhagen | -3.013 |
nces | -2.970 |
Token | examined |
Token ID | 11068 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
verts | +3.784 |
ements | +3.721 |
uez | +3.638 |
enhagen | +3.548 |
nesses | +3.420 |
Neg logit contributions | |
rigging | -3.215 |
ONE | -3.124 |
sparing | -3.121 |
THING | -2.987 |
Problem | -2.976 |
Token | by |
Token ID | 416 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
rigging | +0.580 |
sparing | +0.574 |
ONE | +0.566 |
discord | +0.540 |
orally | +0.539 |
Neg logit contributions | |
verts | -0.737 |
ements | -0.729 |
uez | -0.717 |
enhagen | -0.699 |
nces | -0.676 |
Token | the |
Token ID | 262 |
Feature activation | +7.98e-05 |
Pos logit contributions | |
rigging | +0.161 |
sparing | +0.158 |
ONE | +0.158 |
discord | +0.150 |
THING | +0.150 |
Neg logit contributions | |
verts | -0.169 |
ements | -0.168 |
uez | -0.164 |
enhagen | -0.158 |
nces | -0.155 |
Token | Chemistry |
Token ID | 27867 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
rigging | +0.000 |
sparing | +0.000 |
ONE | +0.000 |
centre | +0.000 |
discord | +0.000 |
Neg logit contributions | |
verts | -0.000 |
ements | -0.000 |
uez | -0.000 |
enhagen | -0.000 |
nces | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
verts | +3.227 |
ements | +3.172 |
uez | +3.109 |
enhagen | +3.009 |
nces | +2.911 |
Neg logit contributions | |
rigging | -3.123 |
sparing | -3.062 |
ONE | -3.051 |
THING | -2.928 |
discord | -2.911 |
Token | Camera |
Token ID | 20432 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
verts | +2.715 |
ements | +2.668 |
uez | +2.616 |
enhagen | +2.538 |
nces | +2.451 |
Neg logit contributions | |
rigging | -2.621 |
sparing | -2.575 |
ONE | -2.571 |
THING | -2.455 |
discord | -2.447 |
Token | ( |
Token ID | 357 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
verts | +0.787 |
ements | +0.775 |
uez | +0.761 |
enhagen | +0.738 |
nces | +0.713 |
Neg logit contributions | |
rigging | -0.698 |
sparing | -0.687 |
ONE | -0.685 |
THING | -0.653 |
discord | -0.652 |
Token | Chem |
Token ID | 41829 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
ONE | +4.014 |
rigging | +3.901 |
Problem | +3.802 |
sparing | +3.793 |
THING | +3.691 |
Neg logit contributions | |
verts | -6.874 |
ements | -6.641 |
uez | -6.628 |
enhagen | -6.541 |
ellig | -6.435 |
Token | Cam |
Token ID | 21701 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
verts | +3.795 |
ements | +3.721 |
uez | +3.646 |
enhagen | +3.505 |
nesses | +3.365 |
Neg logit contributions | |
rigging | -4.422 |
sparing | -4.370 |
ONE | -4.312 |
discord | -4.171 |
THING | -4.164 |
Token | ) |
Token ID | 8 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
rigging | +1.238 |
ONE | +1.210 |
sparing | +1.201 |
discord | +1.138 |
THING | +1.134 |
Neg logit contributions | |
verts | -1.749 |
ements | -1.730 |
uez | -1.701 |
enhagen | -1.654 |
nesses | -1.613 |
Token | in |
Token ID | 287 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
verts | +0.184 |
ements | +0.182 |
uez | +0.179 |
enhagen | +0.173 |
nces | +0.168 |
Neg logit contributions | |
rigging | -0.165 |
sparing | -0.163 |
ONE | -0.161 |
discord | -0.154 |
THING | -0.154 |
Token | some |
Token ID | 617 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
ements | +0.277 |
verts | +0.276 |
uez | +0.273 |
enhagen | +0.268 |
nces | +0.259 |
Neg logit contributions | |
rigging | -0.225 |
sparing | -0.223 |
ONE | -0.220 |
discord | -0.212 |
centre | -0.207 |
Token | way |
Token ID | 835 |
Feature activation | -8.38e-02 |
Pos logit contributions | |
verts | +4.737 |
ements | +4.641 |
uez | +4.473 |
enhagen | +4.289 |
nesses | +4.199 |
Neg logit contributions | |
rigging | -5.541 |
ONE | -5.406 |
sparing | -5.404 |
Problem | -5.228 |
THING | -5.228 |
Token | . |
Token ID | 13 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
verts | +0.495 |
ements | +0.487 |
uez | +0.480 |
enhagen | +0.465 |
nces | +0.449 |
Neg logit contributions | |
rigging | -0.454 |
sparing | -0.449 |
ONE | -0.445 |
discord | -0.425 |
THING | -0.424 |
Token | We |
Token ID | 775 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
ONE | +0.776 |
rigging | +0.758 |
sparing | +0.737 |
THING | +0.731 |
Problem | +0.729 |
Neg logit contributions | |
verts | -0.982 |
ements | -0.976 |
uez | -0.960 |
enhagen | -0.956 |
nces | -0.917 |
Token | all |
Token ID | 477 |
Feature activation | -9.38e-02 |
Pos logit contributions | |
rigging | +1.127 |
sparing | +1.117 |
ONE | +1.101 |
underestimate | +1.072 |
discord | +1.049 |
Neg logit contributions | |
verts | -1.819 |
ements | -1.796 |
uez | -1.768 |
enhagen | -1.722 |
nces | -1.687 |
Token | turn |
Token ID | 1210 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
verts | +0.662 |
ements | +0.653 |
uez | +0.643 |
enhagen | +0.629 |
nces | +0.614 |
Neg logit contributions | |
rigging | -0.400 |
sparing | -0.393 |
ONE | -0.387 |
underestimate | -0.369 |
discord | -0.368 |
Token | a |
Token ID | 257 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
verts | +5.791 |
ements | +5.584 |
uez | +5.547 |
enhagen | +5.287 |
nesses | +5.145 |
Neg logit contributions | |
rigging | -5.415 |
ONE | -5.336 |
sparing | -5.256 |
THING | -5.084 |
Problem | -5.063 |
Token | blind |
Token ID | 7770 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
verts | +4.271 |
ements | +4.121 |
uez | +4.075 |
enhagen | +3.887 |
verages | +3.811 |
Neg logit contributions | |
rigging | -4.267 |
ONE | -4.173 |
sparing | -4.159 |
THING | -3.988 |
Problem | -3.983 |
Token | eye |
Token ID | 4151 |
Feature activation | -9.55e-02 |
Pos logit contributions | |
verts | +1.139 |
ements | +1.131 |
uez | +1.112 |
enhagen | +1.094 |
nces | +1.071 |
Neg logit contributions | |
rigging | -0.429 |
sparing | -0.416 |
ONE | -0.415 |
THING | -0.382 |
discord | -0.380 |
Token | to |
Token ID | 284 |
Feature activation | -7.95e-02 |
Pos logit contributions | |
verts | +0.531 |
ements | +0.523 |
uez | +0.517 |
enhagen | +0.498 |
nces | +0.483 |
Neg logit contributions | |
rigging | -0.550 |
sparing | -0.543 |
ONE | -0.537 |
discord | -0.515 |
THING | -0.513 |
Token | fast |
Token ID | 3049 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
rigging | +0.368 |
sparing | +0.360 |
ONE | +0.354 |
discord | +0.342 |
centre | +0.338 |
Neg logit contributions | |
verts | -0.458 |
ements | -0.457 |
uez | -0.446 |
enhagen | -0.440 |
nces | -0.424 |
Token | - |
Token ID | 12 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
verts | +1.458 |
ements | +1.442 |
uez | +1.415 |
enhagen | +1.382 |
nces | +1.332 |
Neg logit contributions | |
rigging | -1.477 |
sparing | -1.453 |
ONE | -1.438 |
discord | -1.381 |
THING | -1.376 |
Token | moving |
Token ID | 31462 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
rigging | +1.120 |
sparing | +1.094 |
ONE | +1.076 |
discord | +1.029 |
Problem | +1.023 |
Neg logit contributions | |
uez | -1.640 |
ements | -1.638 |
verts | -1.636 |
enhagen | -1.592 |
nces | -1.550 |
Token | creatures |
Token ID | 8109 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
verts | +0.313 |
ements | +0.312 |
uez | +0.305 |
enhagen | +0.300 |
nces | +0.289 |
Neg logit contributions | |
rigging | -0.299 |
sparing | -0.290 |
ONE | -0.287 |
discord | -0.277 |
centre | -0.275 |
Token | in |
Token ID | 287 |
Feature activation | -2.08e-03 |
Pos logit contributions | |
verts | +1.910 |
ements | +1.878 |
uez | +1.845 |
enhagen | +1.791 |
nces | +1.731 |
Neg logit contributions | |
rigging | -1.745 |
sparing | -1.713 |
ONE | -1.709 |
THING | -1.629 |
discord | -1.626 |
Token | place |
Token ID | 1295 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
ements | +0.014 |
verts | +0.014 |
uez | +0.013 |
enhagen | +0.013 |
nces | +0.013 |
Neg logit contributions | |
rigging | -0.010 |
sparing | -0.010 |
ONE | -0.010 |
discord | -0.009 |
centre | -0.009 |
Token | while |
Token ID | 981 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
verts | +2.286 |
ements | +2.251 |
uez | +2.200 |
enhagen | +2.142 |
nces | +2.061 |
Neg logit contributions | |
rigging | -2.284 |
ONE | -2.256 |
sparing | -2.243 |
THING | -2.153 |
Problem | -2.147 |
Token | ampl |
Token ID | 12306 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
rigging | +1.830 |
sparing | +1.819 |
ONE | +1.715 |
discord | +1.680 |
centre | +1.669 |
Neg logit contributions | |
verts | -2.277 |
ements | -2.275 |
uez | -2.230 |
enhagen | -2.190 |
nces | -2.122 |
Token | ifying |
Token ID | 4035 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
rigging | +3.325 |
sparing | +3.263 |
ONE | +3.056 |
lining | +2.991 |
discord | +2.959 |
Neg logit contributions | |
verts | -5.394 |
ements | -5.273 |
uez | -5.230 |
verages | -5.213 |
enhagen | -5.196 |
Token | damage |
Token ID | 2465 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
rigging | +2.004 |
sparing | +1.983 |
ONE | +1.887 |
discord | +1.882 |
centre | +1.846 |
Neg logit contributions | |
ements | -2.392 |
verts | -2.365 |
uez | -2.328 |
enhagen | -2.280 |
nces | -2.224 |
Token | from |
Token ID | 422 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
sparing | +1.542 |
rigging | +1.533 |
ONE | +1.491 |
centre | +1.437 |
discord | +1.427 |
Neg logit contributions | |
verts | -1.810 |
ements | -1.791 |
uez | -1.782 |
enhagen | -1.729 |
nces | -1.671 |
Token | In |
Token ID | 818 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
verts | +1.775 |
ements | +1.750 |
uez | +1.721 |
enhagen | +1.682 |
nces | +1.629 |
Neg logit contributions | |
rigging | -1.259 |
ONE | -1.240 |
sparing | -1.230 |
THING | -1.171 |
Problem | -1.168 |
Token | late |
Token ID | 2739 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
verts | +0.248 |
ements | +0.245 |
uez | +0.242 |
enhagen | +0.236 |
nesses | +0.228 |
Neg logit contributions | |
rigging | -0.209 |
sparing | -0.206 |
ONE | -0.204 |
discord | -0.196 |
THING | -0.193 |
Token | 2016 |
Token ID | 1584 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
verts | +0.704 |
ements | +0.691 |
uez | +0.677 |
enhagen | +0.656 |
nces | +0.625 |
Neg logit contributions | |
rigging | -1.059 |
sparing | -1.040 |
ONE | -1.037 |
discord | -1.002 |
THING | -0.995 |
Token | , |
Token ID | 11 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
rigging | +0.811 |
sparing | +0.793 |
ONE | +0.792 |
discord | +0.759 |
THING | +0.752 |
Neg logit contributions | |
verts | -0.892 |
ements | -0.873 |
uez | -0.860 |
enhagen | -0.829 |
verages | -0.813 |
Token | Michael |
Token ID | 3899 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
verts | +3.036 |
ements | +2.990 |
uez | +2.940 |
enhagen | +2.848 |
nces | +2.748 |
Neg logit contributions | |
rigging | -2.764 |
ONE | -2.722 |
sparing | -2.716 |
THING | -2.593 |
Problem | -2.585 |
Token | G |
Token ID | 402 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
rigging | +0.688 |
sparing | +0.679 |
ONE | +0.670 |
discord | +0.648 |
orally | +0.636 |
Neg logit contributions | |
verts | -0.800 |
ements | -0.787 |
uez | -0.774 |
enhagen | -0.748 |
nces | -0.746 |
Token | . |
Token ID | 13 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
uez | +5.661 |
ements | +5.636 |
verts | +5.634 |
enhagen | +5.241 |
ellig | +5.146 |
Neg logit contributions | |
rigging | -7.449 |
sparing | -7.356 |
captcha | -7.206 |
ONE | -7.155 |
THING | -7.115 |
Token | Flynn |
Token ID | 14654 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
verts | +2.611 |
ements | +2.563 |
uez | +2.518 |
enhagen | +2.413 |
nces | +2.305 |
Neg logit contributions | |
rigging | -3.327 |
ONE | -3.279 |
sparing | -3.273 |
THING | -3.156 |
Problem | -3.130 |
Token | announced |
Token ID | 3414 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
verts | +3.578 |
ements | +3.523 |
uez | +3.460 |
enhagen | +3.370 |
nesses | +3.241 |
Neg logit contributions | |
rigging | -3.180 |
ONE | -3.127 |
sparing | -3.119 |
THING | -2.982 |
Problem | -2.960 |
Token | that |
Token ID | 326 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
rigging | +1.327 |
sparing | +1.315 |
ONE | +1.289 |
discord | +1.260 |
orally | +1.227 |
Neg logit contributions | |
verts | -1.600 |
ements | -1.555 |
uez | -1.534 |
enhagen | -1.508 |
verages | -1.464 |
Token | Jen |
Token ID | 13364 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
rigging | +0.846 |
sparing | +0.824 |
ONE | +0.811 |
discord | +0.774 |
centre | +0.753 |
Neg logit contributions | |
verts | -1.809 |
ements | -1.787 |
uez | -1.758 |
enhagen | -1.731 |
nces | -1.689 |
Token |
|
Token ID | 198 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
verts | +0.781 |
ements | +0.773 |
uez | +0.757 |
enhagen | +0.736 |
nesses | +0.712 |
Neg logit contributions | |
rigging | -0.669 |
ONE | -0.660 |
sparing | -0.658 |
discord | -0.625 |
THING | -0.625 |
Token |
|
Token ID | 198 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
verts | +2.389 |
ements | +2.330 |
uez | +2.280 |
enhagen | +2.140 |
nesses | +2.139 |
Neg logit contributions | |
rigging | -2.307 |
sparing | -2.271 |
ONE | -2.230 |
underestimate | -2.146 |
THING | -2.144 |
Token | 27 |
Token ID | 1983 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
verts | +2.444 |
ements | +2.404 |
uez | +2.361 |
enhagen | +2.295 |
nces | +2.216 |
Neg logit contributions | |
rigging | -2.186 |
ONE | -2.146 |
sparing | -2.145 |
THING | -2.042 |
discord | -2.035 |
Token | " |
Token ID | 1 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
verts | +2.234 |
ements | +2.200 |
uez | +2.132 |
enhagen | +2.059 |
nces | +1.994 |
Neg logit contributions | |
rigging | -2.771 |
sparing | -2.741 |
ONE | -2.703 |
THING | -2.602 |
discord | -2.599 |
Token | 8 |
Token ID | 807 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
ONE | +2.026 |
rigging | +2.003 |
sparing | +1.979 |
Problem | +1.901 |
discord | +1.901 |
Neg logit contributions | |
ements | -2.652 |
verts | -2.643 |
uez | -2.603 |
enhagen | -2.579 |
nesses | -2.473 |
Token | ms |
Token ID | 907 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
verts | +1.124 |
ements | +1.107 |
uez | +1.087 |
enhagen | +1.054 |
nces | +1.005 |
Neg logit contributions | |
rigging | -1.363 |
ONE | -1.349 |
sparing | -1.344 |
THING | -1.289 |
Problem | -1.287 |
Token | G |
Token ID | 402 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
verts | +5.589 |
ements | +5.377 |
uez | +5.357 |
enhagen | +5.166 |
nces | +5.070 |
Neg logit contributions | |
rigging | -6.264 |
sparing | -6.154 |
ONE | -6.056 |
THING | -5.912 |
Problem | -5.868 |
Token | 2 |
Token ID | 17 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
verts | +3.681 |
ements | +3.593 |
uez | +3.541 |
enhagen | +3.337 |
nces | +3.296 |
Neg logit contributions | |
rigging | -2.982 |
sparing | -2.960 |
ONE | -2.806 |
underestimate | -2.773 |
resonate | -2.740 |
Token | G |
Token ID | 38 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
verts | +3.101 |
ements | +3.013 |
uez | +2.987 |
enhagen | +2.813 |
nesses | +2.776 |
Neg logit contributions | |
rigging | -2.681 |
sparing | -2.661 |
ONE | -2.531 |
underestimate | -2.497 |
resonate | -2.492 |
Token | LG |
Token ID | 17370 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
verts | +3.713 |
ements | +3.616 |
uez | +3.578 |
enhagen | +3.404 |
nces | +3.304 |
Neg logit contributions | |
rigging | -4.560 |
sparing | -4.492 |
ONE | -4.442 |
THING | -4.296 |
Problem | -4.282 |
Token | . |
Token ID | 13 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
verts | +4.584 |
ements | +4.430 |
uez | +4.389 |
enhagen | +4.019 |
ellig | +3.987 |
Neg logit contributions | |
rigging | -5.853 |
sparing | -5.835 |
ONE | -5.577 |
orally | -5.479 |
underestimate | -5.472 |
Token | reach |
Token ID | 3151 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
sparing | +1.841 |
ONE | +1.831 |
rigging | +1.822 |
discord | +1.758 |
centre | +1.729 |
Neg logit contributions | |
ements | -2.819 |
uez | -2.777 |
enhagen | -2.758 |
verts | -2.748 |
nces | -2.680 |
Token | of |
Token ID | 286 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
verts | +1.250 |
ements | +1.237 |
uez | +1.228 |
enhagen | +1.183 |
nesses | +1.143 |
Neg logit contributions | |
rigging | -1.162 |
sparing | -1.145 |
ONE | -1.145 |
discord | -1.092 |
THING | -1.084 |
Token | Facebook |
Token ID | 3203 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
verts | +1.691 |
ements | +1.672 |
uez | +1.642 |
enhagen | +1.600 |
nces | +1.544 |
Neg logit contributions | |
rigging | -1.505 |
sparing | -1.481 |
ONE | -1.479 |
discord | -1.411 |
THING | -1.406 |
Token | posts |
Token ID | 6851 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
verts | +0.965 |
ements | +0.959 |
uez | +0.946 |
enhagen | +0.918 |
nces | +0.891 |
Neg logit contributions | |
rigging | -0.898 |
ONE | -0.888 |
sparing | -0.885 |
discord | -0.854 |
THING | -0.842 |
Token | is |
Token ID | 318 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
verts | +1.750 |
ements | +1.728 |
uez | +1.706 |
enhagen | +1.650 |
nesses | +1.593 |
Neg logit contributions | |
rigging | -1.575 |
sparing | -1.547 |
ONE | -1.539 |
discord | -1.473 |
THING | -1.464 |
Token | going |
Token ID | 1016 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
verts | +3.260 |
ements | +3.210 |
uez | +3.151 |
enhagen | +3.082 |
nces | +2.981 |
Neg logit contributions | |
rigging | -2.479 |
ONE | -2.437 |
sparing | -2.430 |
THING | -2.319 |
Problem | -2.302 |
Token | down |
Token ID | 866 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
verts | +7.564 |
ements | +7.323 |
enhagen | +7.266 |
uez | +7.251 |
verages | +6.890 |
Neg logit contributions | |
rigging | -7.905 |
sparing | -7.807 |
ONE | -7.755 |
Problem | -7.625 |
THING | -7.388 |
Token | . |
Token ID | 13 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
verts | +2.281 |
ements | +2.239 |
uez | +2.192 |
enhagen | +2.144 |
nces | +2.064 |
Neg logit contributions | |
rigging | -2.149 |
ONE | -2.111 |
sparing | -2.107 |
THING | -2.017 |
Problem | -2.012 |
Token |
|
Token ID | 198 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
verts | +2.143 |
ements | +2.112 |
uez | +2.075 |
enhagen | +2.022 |
nces | +1.948 |
Neg logit contributions | |
rigging | -1.993 |
ONE | -1.965 |
sparing | -1.953 |
THING | -1.870 |
discord | -1.868 |
Token |
|
Token ID | 198 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
verts | +0.833 |
ements | +0.820 |
uez | +0.806 |
enhagen | +0.784 |
nces | +0.758 |
Neg logit contributions | |
rigging | -0.706 |
sparing | -0.692 |
ONE | -0.692 |
THING | -0.658 |
discord | -0.656 |
Token | Those |
Token ID | 9627 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
verts | +1.582 |
ements | +1.564 |
uez | +1.542 |
enhagen | +1.513 |
nces | +1.461 |
Neg logit contributions | |
rigging | -1.148 |
ONE | -1.147 |
sparing | -1.118 |
Problem | -1.084 |
THING | -1.078 |
Token | Review |
Token ID | 6602 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
rigging | +4.911 |
ONE | +4.802 |
sparing | +4.785 |
discord | +4.577 |
centre | +4.537 |
Neg logit contributions | |
verts | -7.201 |
ements | -7.160 |
enhagen | -7.083 |
nces | -6.932 |
uez | -6.872 |
Token | national |
Token ID | 2260 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
verts | +2.145 |
ements | +2.111 |
uez | +2.073 |
enhagen | +2.013 |
nces | +1.952 |
Neg logit contributions | |
rigging | -1.818 |
sparing | -1.785 |
ONE | -1.783 |
THING | -1.693 |
Problem | -1.691 |
Token | affairs |
Token ID | 9674 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
rigging | +3.107 |
sparing | +3.030 |
ONE | +2.971 |
centre | +2.962 |
discord | +2.959 |
Neg logit contributions | |
ements | -4.547 |
verts | -4.523 |
uez | -4.449 |
enhagen | -4.349 |
nces | -4.348 |
Token | correspondent |
Token ID | 21076 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
verts | +1.017 |
ements | +1.006 |
uez | +0.990 |
enhagen | +0.960 |
nces | +0.940 |
Neg logit contributions | |
rigging | -0.691 |
sparing | -0.677 |
ONE | -0.676 |
discord | -0.646 |
Problem | -0.643 |
Token | John |
Token ID | 1757 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
verts | +2.835 |
ements | +2.790 |
uez | +2.741 |
enhagen | +2.664 |
nces | +2.577 |
Neg logit contributions | |
rigging | -2.396 |
sparing | -2.351 |
ONE | -2.350 |
THING | -2.234 |
discord | -2.225 |
Token | Fund |
Token ID | 7557 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
verts | +0.990 |
ements | +0.973 |
uez | +0.954 |
enhagen | +0.938 |
nesses | +0.909 |
Neg logit contributions | |
rigging | -0.918 |
ONE | -0.914 |
sparing | -0.912 |
discord | -0.870 |
centre | -0.869 |
Token | wrote |
Token ID | 2630 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
verts | +7.243 |
ements | +7.234 |
uez | +7.104 |
enhagen | +7.028 |
ellig | +6.665 |
Neg logit contributions | |
rigging | -5.845 |
sparing | -5.760 |
ONE | -5.725 |
THING | -5.570 |
Problem | -5.465 |
Token | in |
Token ID | 287 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
verts | +4.298 |
ements | +4.229 |
uez | +4.144 |
enhagen | +4.029 |
nces | +3.904 |
Neg logit contributions | |
rigging | -3.541 |
ONE | -3.484 |
sparing | -3.460 |
THING | -3.305 |
Problem | -3.291 |
Token | March |
Token ID | 2805 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
verts | +3.994 |
ements | +3.905 |
uez | +3.840 |
enhagen | +3.722 |
nesses | +3.579 |
Neg logit contributions | |
rigging | -3.722 |
sparing | -3.658 |
ONE | -3.657 |
THING | -3.505 |
Problem | -3.478 |
Token | . |
Token ID | 13 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
rigging | +0.251 |
sparing | +0.247 |
ONE | +0.247 |
discord | +0.235 |
Problem | +0.235 |
Neg logit contributions | |
verts | -0.269 |
ements | -0.265 |
uez | -0.260 |
enhagen | -0.251 |
nces | -0.245 |
Token | � |
Token ID | 564 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
rigging | +0.941 |
ONE | +0.931 |
sparing | +0.916 |
Problem | +0.893 |
THING | +0.882 |
Neg logit contributions | |
verts | -1.127 |
ements | -1.104 |
uez | -1.080 |
enhagen | -1.058 |
nces | -1.024 |
Token | ank |
Token ID | 962 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
rigging | +0.750 |
ONE | +0.745 |
sparing | +0.706 |
Problem | +0.660 |
discord | +0.660 |
Neg logit contributions | |
verts | -1.647 |
ements | -1.632 |
uez | -1.576 |
enhagen | -1.557 |
verages | -1.541 |
Token | fore |
Token ID | 1674 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
rigging | +2.884 |
ONE | +2.781 |
sparing | +2.776 |
centre | +2.677 |
discord | +2.662 |
Neg logit contributions | |
verts | -3.296 |
ements | -3.217 |
uez | -3.175 |
enhagen | -3.110 |
nces | -3.048 |
Token | closed |
Token ID | 20225 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
rigging | +0.302 |
sparing | +0.294 |
ONE | +0.293 |
centre | +0.281 |
discord | +0.279 |
Neg logit contributions | |
verts | -0.355 |
ements | -0.352 |
uez | -0.351 |
enhagen | -0.337 |
ellig | -0.325 |
Token | on |
Token ID | 319 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
verts | +0.369 |
ements | +0.361 |
uez | +0.358 |
enhagen | +0.349 |
nces | +0.338 |
Neg logit contributions | |
rigging | -0.307 |
sparing | -0.302 |
ONE | -0.299 |
discord | -0.284 |
centre | -0.283 |
Token | Andrew |
Token ID | 6858 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
verts | +0.092 |
ements | +0.090 |
uez | +0.089 |
enhagen | +0.087 |
nces | +0.084 |
Neg logit contributions | |
rigging | -0.083 |
sparing | -0.081 |
ONE | -0.081 |
discord | -0.077 |
centre | -0.077 |
Token | W |
Token ID | 370 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
verts | +2.461 |
ements | +2.419 |
uez | +2.374 |
enhagen | +2.305 |
nces | +2.223 |
Neg logit contributions | |
rigging | -2.436 |
sparing | -2.394 |
ONE | -2.392 |
THING | -2.283 |
discord | -2.278 |
Token | ied |
Token ID | 798 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
verts | +8.036 |
ements | +7.708 |
uez | +7.636 |
ellig | +7.188 |
enhagen | +7.171 |
Neg logit contributions | |
rigging | -7.806 |
sparing | -7.430 |
ONE | -7.354 |
THING | -7.308 |
Problem | -7.231 |
Token | er |
Token ID | 263 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
verts | +2.771 |
ements | +2.731 |
uez | +2.681 |
enhagen | +2.615 |
nesses | +2.499 |
Neg logit contributions | |
rigging | -2.621 |
ONE | -2.569 |
sparing | -2.563 |
THING | -2.458 |
Problem | -2.442 |
Token | horn |
Token ID | 25311 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
verts | +4.843 |
ements | +4.767 |
uez | +4.680 |
enhagen | +4.586 |
nesses | +4.389 |
Neg logit contributions | |
rigging | -3.965 |
ONE | -3.885 |
sparing | -3.859 |
THING | -3.702 |
Problem | -3.677 |
Token | � |
Token ID | 447 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
verts | +2.312 |
ements | +2.273 |
uez | +2.232 |
enhagen | +2.168 |
nces | +2.101 |
Neg logit contributions | |
rigging | -1.981 |
sparing | -1.946 |
ONE | -1.943 |
THING | -1.846 |
discord | -1.842 |
Token | � |
Token ID | 247 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
rigging | +0.599 |
ONE | +0.589 |
sparing | +0.585 |
Problem | +0.555 |
THING | +0.552 |
Neg logit contributions | |
verts | -0.902 |
ements | -0.891 |
uez | -0.873 |
enhagen | -0.856 |
nesses | -0.832 |