Token | self |
Token ID | 2116 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
axes | +1.594 |
ochond | +1.515 |
acceler | +1.434 |
OTOS | +1.385 |
opsis | +1.384 |
Neg logit contributions | |
util | -2.968 |
onen | -2.931 |
idium | -2.894 |
hler | -2.816 |
cone | -2.787 |
Token | . |
Token ID | 764 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
util | +3.177 |
onen | +3.001 |
hler | +2.879 |
idium | +2.854 |
unia | +2.715 |
Neg logit contributions | |
escription | -3.037 |
ochond | -2.856 |
axes | -2.751 |
pollut | -2.733 |
OTOS | -2.689 |
Token | half |
Token ID | 13959 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
axes | +3.812 |
ochond | +3.707 |
OTOS | +3.490 |
acceler | +3.467 |
escription | +3.431 |
Neg logit contributions | |
util | -4.100 |
onen | -4.055 |
idium | -4.038 |
hler | -3.901 |
illance | -3.840 |
Token | _ |
Token ID | 62 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
util | +1.260 |
onen | +1.230 |
idium | +1.217 |
hler | +1.179 |
cone | +1.146 |
Neg logit contributions | |
axes | -1.119 |
ochond | -1.112 |
acceler | -1.052 |
OTOS | -1.052 |
opsis | -1.044 |
Token | m |
Token ID | 76 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
util | +0.368 |
onen | +0.361 |
idium | +0.357 |
hler | +0.347 |
cone | +0.339 |
Neg logit contributions | |
axes | -0.302 |
ochond | -0.299 |
acceler | -0.281 |
opsis | -0.280 |
OTOS | -0.278 |
Token | oves |
Token ID | 5241 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
util | +2.330 |
onen | +2.168 |
idium | +2.044 |
hler | +2.022 |
unia | +1.963 |
Neg logit contributions | |
escription | -3.111 |
pollut | -3.098 |
axes | -3.056 |
ochond | -2.986 |
physic | -2.932 |
Token | , |
Token ID | 837 |
Feature activation | -7.74e-02 |
Pos logit contributions | |
util | +8.854 |
onen | +8.277 |
idium | +8.062 |
hler | +8.026 |
ilogy | +7.626 |
Neg logit contributions | |
ochond | -7.598 |
pollut | -7.477 |
axes | -7.424 |
OTOS | -7.374 |
opsis | -7.323 |
Token | depth |
Token ID | 6795 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
axes | +0.648 |
ochond | +0.640 |
OTOS | +0.608 |
acceler | +0.606 |
pollut | +0.604 |
Neg logit contributions | |
util | -0.892 |
onen | -0.873 |
idium | -0.859 |
hler | -0.835 |
cone | -0.818 |
Token | : |
Token ID | 1058 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
util | +2.232 |
onen | +2.158 |
hler | +2.056 |
idium | +2.025 |
cone | +1.989 |
Neg logit contributions | |
escription | -2.031 |
axes | -1.977 |
pollut | -1.976 |
ochond | -1.975 |
opsis | -1.873 |
Token | self |
Token ID | 2116 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
axes | +0.948 |
ochond | +0.917 |
acceler | +0.859 |
opsis | +0.841 |
OTOS | +0.839 |
Neg logit contributions | |
util | -1.850 |
onen | -1.826 |
idium | -1.803 |
hler | -1.757 |
cone | -1.730 |
Token | . |
Token ID | 764 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
util | +3.106 |
onen | +2.929 |
hler | +2.806 |
idium | +2.801 |
cone | +2.661 |
Neg logit contributions | |
escription | -2.855 |
ochond | -2.726 |
axes | -2.643 |
pollut | -2.590 |
OTOS | -2.566 |
Token | in |
Token ID | 287 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
util | +3.602 |
onen | +3.217 |
hler | +3.108 |
cone | +3.104 |
idium | +3.051 |
Neg logit contributions | |
escription | -5.220 |
ochond | -4.765 |
axes | -4.692 |
OTOS | -4.624 |
pollut | -4.598 |
Token | a |
Token ID | 257 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
util | +2.183 |
onen | +2.025 |
idium | +1.936 |
cone | +1.935 |
hler | +1.909 |
Neg logit contributions | |
escription | -2.918 |
ochond | -2.705 |
axes | -2.608 |
OTOS | -2.579 |
opsis | -2.575 |
Token | skillet |
Token ID | 41306 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
util | +4.314 |
onen | +4.095 |
cone | +4.022 |
hler | +3.928 |
idium | +3.605 |
Neg logit contributions | |
escription | -7.368 |
ochond | -6.789 |
axes | -6.662 |
OTOS | -6.662 |
opsis | -6.563 |
Token | over |
Token ID | 625 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
util | +3.131 |
onen | +3.058 |
hler | +2.898 |
cone | +2.757 |
idium | +2.730 |
Neg logit contributions | |
escription | -4.579 |
ochond | -4.298 |
axes | -4.224 |
OTOS | -4.203 |
opsis | -4.134 |
Token | medium |
Token ID | 7090 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
util | +2.242 |
onen | +2.123 |
idium | +2.027 |
hler | +1.948 |
cone | +1.931 |
Neg logit contributions | |
escription | -3.197 |
ochond | -3.094 |
OTOS | -3.016 |
opsis | -2.984 |
axes | -2.968 |
Token | - |
Token ID | 12 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
util | +4.546 |
onen | +4.043 |
hler | +3.732 |
cone | +3.721 |
idium | +3.719 |
Neg logit contributions | |
escription | -9.675 |
ochond | -8.525 |
opsis | -8.470 |
OTOS | -8.451 |
axes | -8.168 |
Token | high |
Token ID | 8929 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
util | +5.057 |
onen | +4.956 |
hey | +4.666 |
cone | +4.287 |
hler | +4.269 |
Neg logit contributions | |
escription | -12.454 |
OTOS | -11.693 |
axes | -11.651 |
ochond | -11.380 |
opsis | -11.249 |
Token | heat |
Token ID | 4894 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
util | +3.469 |
onen | +3.307 |
hler | +3.191 |
cone | +3.140 |
idium | +3.091 |
Neg logit contributions | |
escription | -3.827 |
ochond | -3.570 |
OTOS | -3.508 |
opsis | -3.487 |
axes | -3.456 |
Token | . |
Token ID | 13 |
Feature activation | +9.85e-02 |
Pos logit contributions | |
util | +3.500 |
onen | +3.183 |
hler | +3.065 |
cone | +3.011 |
idium | +2.990 |
Neg logit contributions | |
escription | -5.661 |
ochond | -5.056 |
axes | -5.055 |
pollut | -5.026 |
subsequ | -4.922 |
Token | Place |
Token ID | 8474 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
util | +0.783 |
onen | +0.731 |
hler | +0.682 |
idium | +0.677 |
cone | +0.664 |
Neg logit contributions | |
escription | -1.208 |
axes | -1.206 |
ochond | -1.194 |
pollut | -1.167 |
opsis | -1.142 |
Token | f |
Token ID | 277 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
util | +5.159 |
onen | +4.839 |
idium | +4.683 |
hler | +4.587 |
cone | +4.561 |
Neg logit contributions | |
escription | -7.713 |
OTOS | -6.912 |
ochond | -6.896 |
opsis | -6.739 |
axes | -6.554 |
Token | ussian |
Token ID | 31562 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
util | +2.414 |
onen | +2.252 |
ussen | +1.933 |
uristic | +1.866 |
hler | +1.836 |
Neg logit contributions | |
escription | -8.224 |
OTOS | -7.876 |
physic | -7.859 |
ochond | -7.829 |
pollut | -7.822 |
Token | , |
Token ID | 11 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
util | +4.020 |
onen | +3.913 |
idium | +3.662 |
hler | +3.620 |
cone | +3.434 |
Neg logit contributions | |
escription | -6.160 |
ochond | -5.854 |
OTOS | -5.722 |
opsis | -5.506 |
axes | -5.468 |
Token | then |
Token ID | 788 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
util | +3.965 |
onen | +3.359 |
hler | +3.182 |
kov | +3.134 |
unia | +2.934 |
Neg logit contributions | |
escription | -12.870 |
ochond | -11.481 |
OTOS | -11.261 |
opsis | -11.213 |
phies | -10.994 |
Token | apply |
Token ID | 4174 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
util | +1.900 |
onen | +1.815 |
hler | +1.740 |
idium | +1.716 |
cone | +1.691 |
Neg logit contributions | |
escription | -1.848 |
ochond | -1.778 |
axes | -1.753 |
OTOS | -1.711 |
opsis | -1.686 |
Token | the |
Token ID | 262 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
util | +3.285 |
onen | +3.044 |
hler | +2.950 |
idium | +2.907 |
cone | +2.801 |
Neg logit contributions | |
escription | -4.246 |
ochond | -3.922 |
OTOS | -3.783 |
opsis | -3.757 |
axes | -3.742 |
Token | black |
Token ID | 2042 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
util | +5.485 |
onen | +5.443 |
idium | +5.216 |
hler | +5.103 |
uristic | +5.031 |
Neg logit contributions | |
escription | -5.507 |
ochond | -5.302 |
OTOS | -4.981 |
opsis | -4.920 |
phies | -4.697 |
Token | hat |
Token ID | 5183 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
util | +7.570 |
hler | +7.153 |
onen | +7.023 |
cone | +6.908 |
hey | +6.848 |
Neg logit contributions | |
escription | -8.762 |
OTOS | -8.700 |
ochond | -8.443 |
opsis | -8.320 |
acceler | -8.306 |
Token | # |
Token ID | 1303 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
util | +3.532 |
onen | +3.322 |
idium | +3.175 |
hler | +3.043 |
cone | +2.993 |
Neg logit contributions | |
ochond | -7.338 |
axes | -7.260 |
opsis | -7.080 |
OTOS | -7.053 |
acceler | -7.018 |
Token | morph |
Token ID | 17488 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
util | +4.533 |
onen | +4.407 |
hler | +4.189 |
idium | +4.070 |
cone | +3.960 |
Neg logit contributions | |
escription | -4.948 |
ochond | -4.832 |
OTOS | -4.739 |
axes | -4.602 |
opsis | -4.546 |
Token | ological |
Token ID | 2770 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
axes | +0.598 |
ochond | +0.586 |
OTOS | +0.576 |
pollut | +0.574 |
escription | +0.572 |
Neg logit contributions | |
util | -0.329 |
onen | -0.321 |
idium | -0.308 |
hler | -0.293 |
cone | -0.280 |
Token | operator |
Token ID | 10088 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
util | +4.996 |
onen | +4.898 |
hler | +4.667 |
idium | +4.530 |
cone | +4.520 |
Neg logit contributions | |
escription | -3.475 |
ochond | -3.137 |
OTOS | -3.036 |
axes | -2.977 |
opsis | -2.911 |
Token | = |
Token ID | 796 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
util | +6.252 |
onen | +5.973 |
cone | +5.708 |
hler | +5.696 |
idium | +5.639 |
Neg logit contributions | |
ochond | -6.258 |
axes | -6.102 |
opsis | -6.043 |
OTOS | -5.990 |
acceler | -5.977 |
Token | c |
Token ID | 269 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
util | +2.405 |
onen | +2.292 |
idium | +2.235 |
hler | +2.160 |
cone | +2.157 |
Neg logit contributions | |
ochond | -2.874 |
axes | -2.793 |
OTOS | -2.742 |
opsis | -2.740 |
escription | -2.730 |
Token | v |
Token ID | 85 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
util | +1.876 |
onen | +1.649 |
hler | +1.565 |
cone | +1.554 |
idium | +1.552 |
Neg logit contributions | |
escription | -2.949 |
axes | -2.901 |
OTOS | -2.885 |
pollut | -2.834 |
ochond | -2.815 |
Token | 2 |
Token ID | 17 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
util | +3.121 |
onen | +2.612 |
hler | +2.547 |
idium | +2.542 |
cone | +2.488 |
Neg logit contributions | |
escription | -5.844 |
pollut | -5.462 |
axes | -5.396 |
ochond | -5.355 |
OTOS | -5.293 |
Token | . |
Token ID | 13 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
util | +4.321 |
onen | +3.717 |
hler | +3.547 |
cone | +3.510 |
pn | +3.417 |
Neg logit contributions | |
escription | -7.343 |
dilig | -6.539 |
subsequ | -6.495 |
pollut | -6.479 |
axes | -6.451 |
Token | Ga |
Token ID | 35389 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
util | +4.094 |
onen | +3.877 |
idium | +3.718 |
cone | +3.658 |
hler | +3.623 |
Neg logit contributions | |
ochond | -4.427 |
axes | -4.380 |
pollut | -4.291 |
OTOS | -4.262 |
opsis | -4.240 |
Token | ussian |
Token ID | 31562 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
util | +4.201 |
onen | +3.791 |
unia | +3.350 |
ussen | +3.191 |
hler | +3.069 |
Neg logit contributions | |
axes | -12.030 |
ochond | -11.996 |
pollut | -11.891 |
acceler | -11.834 |
DAC | -11.823 |
Token | Bl |
Token ID | 3629 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
util | +4.461 |
onen | +4.301 |
idium | +4.142 |
hler | +4.062 |
cone | +4.045 |
Neg logit contributions | |
ochond | -4.778 |
axes | -4.669 |
opsis | -4.538 |
pollut | -4.536 |
escription | -4.497 |
Token | ur |
Token ID | 333 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
util | +3.501 |
onen | +3.282 |
idium | +3.067 |
hler | +3.000 |
ussen | +2.929 |
Neg logit contributions | |
axes | -5.405 |
ochond | -5.318 |
OTOS | -5.270 |
acceler | -5.234 |
escription | -5.175 |
Token | ( |
Token ID | 7 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
util | +4.728 |
onen | +4.536 |
idium | +4.440 |
hler | +4.354 |
cone | +4.281 |
Neg logit contributions | |
ochond | -4.685 |
axes | -4.647 |
pollut | -4.456 |
opsis | -4.440 |
OTOS | -4.436 |
Token | gray |
Token ID | 44605 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
util | +1.534 |
onen | +1.479 |
idium | +1.437 |
hler | +1.388 |
cone | +1.373 |
Neg logit contributions | |
ochond | -1.940 |
axes | -1.926 |
OTOS | -1.859 |
opsis | -1.854 |
pollut | -1.848 |
Token | Beaut |
Token ID | 13711 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
util | +1.694 |
onen | +1.655 |
idium | +1.609 |
hler | +1.566 |
cone | +1.531 |
Neg logit contributions | |
ochond | -1.475 |
axes | -1.473 |
pollut | -1.393 |
OTOS | -1.390 |
opsis | -1.382 |
Token | ifully |
Token ID | 17049 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
axes | +1.880 |
ochond | +1.875 |
opsis | +1.809 |
OTOS | +1.809 |
pollut | +1.797 |
Neg logit contributions | |
util | -1.206 |
onen | -1.166 |
idium | -1.140 |
hler | -1.098 |
cone | -1.066 |
Token | Paid |
Token ID | 47355 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
util | +1.087 |
onen | +1.055 |
idium | +1.023 |
hler | +0.997 |
cone | +0.980 |
Neg logit contributions | |
axes | -1.030 |
ochond | -1.025 |
OTOS | -0.977 |
pollut | -0.973 |
opsis | -0.968 |
Token | Hom |
Token ID | 8074 |
Feature activation | +3.67e-03 |
Pos logit contributions | |
util | +2.490 |
onen | +2.415 |
idium | +2.328 |
hler | +2.289 |
cone | +2.215 |
Neg logit contributions | |
ochond | -2.569 |
axes | -2.556 |
pollut | -2.423 |
OTOS | -2.405 |
opsis | -2.391 |
Token | age |
Token ID | 496 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
util | +0.031 |
onen | +0.030 |
idium | +0.029 |
hler | +0.028 |
cone | +0.027 |
Neg logit contributions | |
axes | -0.042 |
ochond | -0.042 |
OTOS | -0.040 |
opsis | -0.040 |
pollut | -0.040 |
Token | To |
Token ID | 1675 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
util | +3.275 |
onen | +3.162 |
idium | +3.078 |
hler | +3.027 |
cone | +2.930 |
Neg logit contributions | |
axes | -2.840 |
ochond | -2.834 |
OTOS | -2.684 |
opsis | -2.663 |
pollut | -2.662 |
Token | Lost |
Token ID | 9164 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
util | +7.485 |
onen | +7.481 |
idium | +6.929 |
hler | +6.629 |
ilogy | +6.433 |
Neg logit contributions | |
axes | -8.297 |
ochond | -8.232 |
acceler | -7.910 |
escription | -7.852 |
pollut | -7.704 |
Token | Leader |
Token ID | 10540 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
util | +3.246 |
onen | +3.176 |
idium | +3.010 |
hler | +2.972 |
ilogy | +2.883 |
Neg logit contributions | |
axes | -3.128 |
ochond | -3.123 |
pollut | -2.980 |
acceler | -2.974 |
OTOS | -2.960 |
Token | O |
Token ID | 440 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
util | +3.100 |
onen | +3.030 |
idium | +2.929 |
hler | +2.831 |
cone | +2.779 |
Neg logit contributions | |
axes | -3.231 |
ochond | -3.213 |
pollut | -3.053 |
OTOS | -3.048 |
acceler | -3.043 |
Token | der |
Token ID | 1082 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
util | +2.243 |
onen | +2.195 |
idium | +2.117 |
hler | +1.991 |
cone | +1.977 |
Neg logit contributions | |
axes | -4.660 |
escription | -4.613 |
ochond | -4.610 |
acceler | -4.509 |
pollut | -4.477 |
Token | us |
Token ID | 385 |
Feature activation | +8.11e-02 |
Pos logit contributions | |
axes | +2.241 |
ochond | +2.234 |
OTOS | +2.132 |
pollut | +2.130 |
acceler | +2.122 |
Neg logit contributions | |
util | -2.301 |
onen | -2.234 |
idium | -2.188 |
hler | -2.116 |
cone | -2.065 |
Token | = |
Token ID | 796 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
util | +2.911 |
onen | +2.800 |
idium | +2.735 |
hler | +2.678 |
cone | +2.628 |
Neg logit contributions | |
ochond | -2.641 |
axes | -2.616 |
pollut | -2.523 |
opsis | -2.500 |
OTOS | -2.489 |
Token | im |
Token ID | 545 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
util | +3.569 |
onen | +3.377 |
idium | +3.298 |
cone | +3.249 |
hler | +3.219 |
Neg logit contributions | |
ochond | -3.147 |
escription | -2.986 |
OTOS | -2.978 |
axes | -2.960 |
opsis | -2.946 |
Token | utils |
Token ID | 26791 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
util | +0.775 |
onen | +0.606 |
idium | +0.578 |
hler | +0.497 |
ilogy | +0.447 |
Neg logit contributions | |
axes | -3.734 |
ochond | -3.683 |
escription | -3.671 |
pollut | -3.663 |
acceler | -3.639 |
Token | . |
Token ID | 13 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
util | +3.044 |
onen | +2.685 |
hler | +2.617 |
idium | +2.588 |
cone | +2.479 |
Neg logit contributions | |
ochond | -3.575 |
axes | -3.569 |
escription | -3.567 |
pollut | -3.560 |
acceler | -3.432 |
Token | res |
Token ID | 411 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
util | +2.032 |
onen | +1.929 |
idium | +1.862 |
hler | +1.793 |
cone | +1.779 |
Neg logit contributions | |
ochond | -2.358 |
axes | -2.356 |
pollut | -2.290 |
OTOS | -2.267 |
acceler | -2.259 |
Token | ize |
Token ID | 1096 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
util | +1.506 |
onen | +1.451 |
idium | +1.425 |
hler | +1.391 |
cone | +1.374 |
Neg logit contributions | |
ochond | -0.912 |
axes | -0.908 |
OTOS | -0.868 |
pollut | -0.867 |
acceler | -0.856 |
Token | ( |
Token ID | 7 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
util | +7.483 |
onen | +6.854 |
cone | +6.616 |
idium | +6.521 |
irtual | +6.394 |
Neg logit contributions | |
ochond | -8.695 |
axes | -8.610 |
pollut | -8.598 |
acceler | -8.547 |
escription | -8.369 |
Token | image |
Token ID | 9060 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
util | +2.862 |
onen | +2.638 |
idium | +2.542 |
cone | +2.501 |
hler | +2.443 |
Neg logit contributions | |
ochond | -4.674 |
axes | -4.603 |
OTOS | -4.518 |
pollut | -4.513 |
acceler | -4.493 |
Token | , |
Token ID | 11 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
util | +5.358 |
onen | +5.090 |
idium | +4.998 |
hler | +4.937 |
cone | +4.876 |
Neg logit contributions | |
ochond | -3.896 |
axes | -3.751 |
pollut | -3.678 |
opsis | -3.633 |
acceler | -3.621 |
Token | height |
Token ID | 6001 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
util | +1.959 |
onen | +1.886 |
idium | +1.851 |
hler | +1.799 |
cone | +1.791 |
Neg logit contributions | |
ochond | -1.640 |
axes | -1.571 |
OTOS | -1.544 |
opsis | -1.538 |
escription | -1.517 |
Token | = |
Token ID | 28 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
util | +1.837 |
onen | +1.781 |
idium | +1.752 |
hler | +1.711 |
cone | +1.683 |
Neg logit contributions | |
ochond | -1.261 |
axes | -1.249 |
opsis | -1.189 |
pollut | -1.188 |
OTOS | -1.187 |
Token | film |
Token ID | 2646 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
util | +3.698 |
onen | +3.618 |
idium | +3.544 |
cone | +3.413 |
hler | +3.408 |
Neg logit contributions | |
ochond | -3.069 |
axes | -3.033 |
OTOS | -2.914 |
opsis | -2.894 |
pollut | -2.860 |
Token | � |
Token ID | 564 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
util | +5.793 |
onen | +5.602 |
idium | +5.489 |
cone | +5.357 |
ilogy | +5.326 |
Neg logit contributions | |
ochond | -6.151 |
axes | -6.078 |
OTOS | -5.715 |
opsis | -5.707 |
pollut | -5.666 |
Token | � |
Token ID | 250 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
util | +0.967 |
onen | +0.932 |
idium | +0.907 |
hler | +0.878 |
cone | +0.850 |
Neg logit contributions | |
ochond | -1.728 |
axes | -1.711 |
escription | -1.667 |
pollut | -1.658 |
opsis | -1.643 |
Token | E |
Token ID | 36 |
Feature activation | +5.45e-02 |
Pos logit contributions | |
util | +3.172 |
onen | +3.041 |
idium | +2.939 |
cone | +2.829 |
hler | +2.810 |
Neg logit contributions | |
ochond | -4.622 |
axes | -4.608 |
pollut | -4.521 |
acceler | -4.449 |
opsis | -4.428 |
Token | scape |
Token ID | 6794 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
util | +0.501 |
onen | +0.479 |
idium | +0.468 |
hler | +0.456 |
cone | +0.453 |
Neg logit contributions | |
axes | -0.595 |
ochond | -0.581 |
escription | -0.564 |
pollut | -0.564 |
acceler | -0.563 |
Token | from |
Token ID | 422 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
util | +4.487 |
onen | +4.345 |
idium | +4.295 |
hler | +4.156 |
cone | +4.075 |
Neg logit contributions | |
axes | -3.984 |
ochond | -3.970 |
pollut | -3.773 |
opsis | -3.760 |
OTOS | -3.758 |
Token | Al |
Token ID | 978 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
util | +5.318 |
onen | +5.070 |
idium | +4.934 |
hler | +4.627 |
cone | +4.578 |
Neg logit contributions | |
axes | -10.336 |
ochond | -10.312 |
pollut | -9.979 |
opsis | -9.979 |
escription | -9.859 |
Token | cat |
Token ID | 9246 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
util | +2.191 |
onen | +2.032 |
cone | +1.895 |
idium | +1.889 |
hler | +1.830 |
Neg logit contributions | |
escription | -4.076 |
axes | -3.975 |
OTOS | -3.840 |
acceler | -3.838 |
pollut | -3.824 |
Token | raz |
Token ID | 3247 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
util | +1.041 |
onen | +1.010 |
idium | +0.967 |
hler | +0.945 |
cone | +0.938 |
Neg logit contributions | |
escription | -1.099 |
axes | -1.072 |
ochond | -1.067 |
OTOS | -1.028 |
pollut | -1.027 |
Token | � |
Token ID | 447 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
util | +3.375 |
onen | +3.286 |
idium | +3.212 |
hler | +3.102 |
cone | +3.046 |
Neg logit contributions | |
axes | -3.630 |
ochond | -3.627 |
OTOS | -3.460 |
pollut | -3.422 |
opsis | -3.408 |
Token | � |
Token ID | 251 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
util | +1.121 |
onen | +1.092 |
idium | +1.069 |
hler | +1.033 |
cone | +1.010 |
Neg logit contributions | |
axes | -1.177 |
ochond | -1.173 |
OTOS | -1.121 |
opsis | -1.119 |
pollut | -1.117 |
Token | 3 |
Token ID | 513 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
util | +3.427 |
onen | +3.416 |
hler | +3.172 |
idium | +3.169 |
cone | +3.165 |
Neg logit contributions | |
escription | -3.941 |
ochond | -3.834 |
OTOS | -3.639 |
opsis | -3.629 |
axes | -3.517 |
Token | x |
Token ID | 87 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
util | +1.802 |
onen | +1.733 |
idium | +1.678 |
cone | +1.630 |
hler | +1.607 |
Neg logit contributions | |
escription | -2.035 |
ochond | -1.913 |
axes | -1.885 |
pollut | -1.884 |
OTOS | -1.857 |
Token | 3 |
Token ID | 18 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
escription | +0.414 |
ochond | +0.410 |
axes | +0.407 |
pollut | +0.395 |
opsis | +0.390 |
Neg logit contributions | |
util | -0.362 |
onen | -0.349 |
idium | -0.335 |
hler | -0.334 |
cone | -0.325 |
Token | Ga |
Token ID | 12822 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
util | +2.888 |
onen | +2.717 |
hler | +2.599 |
cone | +2.596 |
idium | +2.566 |
Neg logit contributions | |
escription | -6.314 |
ochond | -6.095 |
OTOS | -5.858 |
opsis | -5.811 |
pollut | -5.745 |
Token | ussian |
Token ID | 31562 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
util | +2.414 |
onen | +2.252 |
ussen | +1.933 |
uristic | +1.866 |
hler | +1.836 |
Neg logit contributions | |
escription | -8.224 |
OTOS | -7.876 |
physic | -7.859 |
ochond | -7.829 |
pollut | -7.822 |
Token | , |
Token ID | 11 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
util | +4.020 |
onen | +3.913 |
idium | +3.662 |
hler | +3.620 |
cone | +3.434 |
Neg logit contributions | |
escription | -6.160 |
ochond | -5.854 |
OTOS | -5.722 |
opsis | -5.506 |
axes | -5.468 |
Token | then |
Token ID | 788 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
util | +3.965 |
onen | +3.359 |
hler | +3.182 |
kov | +3.134 |
unia | +2.934 |
Neg logit contributions | |
escription | -12.870 |
ochond | -11.481 |
OTOS | -11.261 |
opsis | -11.213 |
phies | -10.994 |
Token | apply |
Token ID | 4174 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
util | +1.900 |
onen | +1.815 |
hler | +1.740 |
idium | +1.716 |
cone | +1.691 |
Neg logit contributions | |
escription | -1.848 |
ochond | -1.778 |
axes | -1.753 |
OTOS | -1.711 |
opsis | -1.686 |
Token | the |
Token ID | 262 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
util | +3.285 |
onen | +3.044 |
hler | +2.950 |
idium | +2.907 |
cone | +2.801 |
Neg logit contributions | |
escription | -4.246 |
ochond | -3.922 |
OTOS | -3.783 |
opsis | -3.757 |
axes | -3.742 |
Token | black |
Token ID | 2042 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
util | +5.485 |
onen | +5.443 |
idium | +5.216 |
hler | +5.103 |
uristic | +5.031 |
Neg logit contributions | |
escription | -5.507 |
ochond | -5.302 |
OTOS | -4.981 |
opsis | -4.920 |
phies | -4.697 |
Token | hat |
Token ID | 5183 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
util | +7.570 |
hler | +7.153 |
onen | +7.023 |
cone | +6.908 |
hey | +6.848 |
Neg logit contributions | |
escription | -8.762 |
OTOS | -8.700 |
ochond | -8.443 |
opsis | -8.320 |
acceler | -8.306 |
Token | - |
Token ID | 12 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
util | +1.061 |
onen | +1.034 |
idium | +1.013 |
hler | +0.984 |
cone | +0.960 |
Neg logit contributions | |
axes | -0.991 |
ochond | -0.989 |
OTOS | -0.943 |
opsis | -0.939 |
pollut | -0.939 |
Token | 31 |
Token ID | 3132 |
Feature activation | +1.77e-04 |
Pos logit contributions | |
util | +2.519 |
onen | +2.380 |
idium | +2.299 |
hler | +2.276 |
cone | +2.174 |
Neg logit contributions | |
ochond | -3.205 |
axes | -3.196 |
pollut | -3.120 |
OTOS | -3.074 |
opsis | -3.049 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
util | +0.002 |
onen | +0.002 |
idium | +0.002 |
hler | +0.002 |
cone | +0.002 |
Neg logit contributions | |
axes | -0.002 |
ochond | -0.002 |
OTOS | -0.002 |
opsis | -0.002 |
acceler | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
util | +1.251 |
onen | +1.219 |
idium | +1.194 |
hler | +1.161 |
cone | +1.126 |
Neg logit contributions | |
ochond | -1.151 |
axes | -1.148 |
pollut | -1.094 |
opsis | -1.088 |
OTOS | -1.088 |
Token |
|
Token ID | 198 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
util | +1.822 |
onen | +1.707 |
idium | +1.617 |
hler | +1.615 |
cone | +1.562 |
Neg logit contributions | |
escription | -2.296 |
ochond | -2.141 |
axes | -2.141 |
pollut | -2.092 |
opsis | -2.039 |
Token | [ |
Token ID | 58 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
util | +3.956 |
onen | +3.845 |
idium | +3.764 |
hler | +3.638 |
cone | +3.560 |
Neg logit contributions | |
axes | -4.031 |
ochond | -4.008 |
acceler | -3.817 |
pollut | -3.817 |
opsis | -3.816 |
Token | 24 |
Token ID | 1731 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
util | +3.589 |
onen | +3.392 |
idium | +2.902 |
hey | +2.801 |
cone | +2.776 |
Neg logit contributions | |
escription | -12.964 |
dilig | -11.922 |
subsequ | -11.902 |
axes | -11.698 |
pollut | -11.617 |
Token | ] |
Token ID | 60 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
util | +3.713 |
onen | +3.492 |
hler | +3.435 |
idium | +3.318 |
kov | +3.218 |
Neg logit contributions | |
escription | -4.022 |
axes | -3.616 |
ochond | -3.582 |
pollut | -3.556 |
subsequ | -3.532 |
Token | Nah |
Token ID | 35201 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
util | +0.151 |
onen | +0.147 |
idium | +0.144 |
hler | +0.139 |
cone | +0.136 |
Neg logit contributions | |
axes | -0.141 |
ochond | -0.141 |
OTOS | -0.134 |
pollut | -0.133 |
opsis | -0.133 |
Token | man |
Token ID | 805 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
util | +0.590 |
onen | +0.578 |
idium | +0.566 |
hler | +0.543 |
cone | +0.530 |
Neg logit contributions | |
axes | -0.646 |
ochond | -0.639 |
OTOS | -0.618 |
pollut | -0.616 |
opsis | -0.615 |
Token | ides |
Token ID | 1460 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
axes | +0.639 |
ochond | +0.637 |
OTOS | +0.605 |
opsis | +0.604 |
pollut | +0.602 |
Neg logit contributions | |
util | -0.734 |
onen | -0.716 |
idium | -0.702 |
hler | -0.681 |
cone | -0.667 |
Token | - |
Token ID | 12 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
axes | +0.757 |
ochond | +0.744 |
OTOS | +0.712 |
pollut | +0.708 |
acceler | +0.707 |
Neg logit contributions | |
util | -0.930 |
onen | -0.912 |
idium | -0.890 |
hler | -0.869 |
cone | -0.846 |
Token | to |
Token ID | 1462 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
util | +3.201 |
onen | +3.128 |
idium | +3.069 |
hler | +2.979 |
cone | +2.917 |
Neg logit contributions | |
axes | -2.629 |
ochond | -2.620 |
OTOS | -2.488 |
opsis | -2.480 |
pollut | -2.475 |
Token | - |
Token ID | 12 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
util | +1.578 |
onen | +1.522 |
idium | +1.430 |
hler | +1.430 |
cone | +1.368 |
Neg logit contributions | |
escription | -1.898 |
axes | -1.878 |
ochond | -1.856 |
pollut | -1.810 |
opsis | -1.768 |
Token | 5 |
Token ID | 20 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
axes | +1.682 |
ochond | +1.677 |
OTOS | +1.608 |
opsis | +1.607 |
pollut | +1.605 |
Neg logit contributions | |
util | -1.275 |
onen | -1.237 |
idium | -1.205 |
hler | -1.161 |
cone | -1.130 |
Token | Working |
Token ID | 14594 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
util | +3.549 |
onen | +3.425 |
idium | +3.351 |
hler | +3.305 |
cone | +3.149 |
Neg logit contributions | |
axes | -4.383 |
ochond | -4.376 |
opsis | -4.206 |
OTOS | -4.200 |
acceler | -4.156 |
Token | Women |
Token ID | 6926 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
util | +1.703 |
onen | +1.653 |
idium | +1.616 |
hler | +1.568 |
cone | +1.522 |
Neg logit contributions | |
axes | -1.860 |
ochond | -1.854 |
acceler | -1.769 |
OTOS | -1.768 |
pollut | -1.766 |
Token | Education |
Token ID | 7868 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
util | +6.258 |
hler | +5.982 |
onen | +5.929 |
idium | +5.887 |
cone | +5.545 |
Neg logit contributions | |
ochond | -9.021 |
axes | -8.959 |
opsis | -8.631 |
OTOS | -8.587 |
escription | -8.583 |
Token | Fund |
Token ID | 7557 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
util | +4.060 |
onen | +3.972 |
idium | +3.885 |
hler | +3.800 |
cone | +3.704 |
Neg logit contributions | |
axes | -2.958 |
ochond | -2.935 |
opsis | -2.782 |
OTOS | -2.778 |
pollut | -2.767 |
Token | : |
Token ID | 25 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
util | +2.922 |
onen | +2.849 |
idium | +2.778 |
hler | +2.709 |
cone | +2.632 |
Neg logit contributions | |
ochond | -2.662 |
axes | -2.652 |
OTOS | -2.523 |
pollut | -2.513 |
opsis | -2.505 |
Token | ... |
Token ID | 2644 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
util | +4.229 |
onen | +4.085 |
idium | +4.024 |
hler | +3.883 |
cone | +3.769 |
Neg logit contributions | |
ochond | -4.209 |
axes | -4.099 |
OTOS | -3.916 |
escription | -3.915 |
pollut | -3.915 |
Token | $ |
Token ID | 720 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
util | +1.381 |
onen | +1.337 |
idium | +1.308 |
hler | +1.269 |
cone | +1.238 |
Neg logit contributions | |
ochond | -1.418 |
axes | -1.406 |
OTOS | -1.346 |
opsis | -1.343 |
pollut | -1.340 |
Token | 6 |
Token ID | 718 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
util | +3.438 |
onen | +3.315 |
idium | +3.215 |
hler | +3.165 |
cone | +3.073 |
Neg logit contributions | |
ochond | -3.895 |
axes | -3.824 |
pollut | -3.688 |
opsis | -3.682 |
OTOS | -3.664 |
Token | } |
Token ID | 92 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
util | +2.470 |
onen | +2.397 |
idium | +2.335 |
hler | +2.247 |
cone | +2.184 |
Neg logit contributions | |
axes | -3.452 |
ochond | -3.444 |
OTOS | -3.308 |
opsis | -3.301 |
pollut | -3.298 |
Token | < |
Token ID | 1279 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
util | +1.554 |
onen | +1.509 |
idium | +1.466 |
hler | +1.425 |
cone | +1.380 |
Neg logit contributions | |
ochond | -1.858 |
axes | -1.841 |
OTOS | -1.769 |
opsis | -1.768 |
pollut | -1.763 |
Token | -> |
Token ID | 3784 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
axes | +2.352 |
ochond | +2.342 |
OTOS | +2.254 |
opsis | +2.236 |
escription | +2.198 |
Neg logit contributions | |
onen | -4.189 |
util | -4.180 |
idium | -4.124 |
ilogy | -3.951 |
ussen | -3.943 |
Token | { |
Token ID | 1391 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
axes | +0.624 |
ochond | +0.605 |
acceler | +0.591 |
pollut | +0.590 |
opsis | +0.588 |
Neg logit contributions | |
util | -0.382 |
onen | -0.374 |
idium | -0.366 |
hler | -0.349 |
cone | -0.337 |
Token | 1 |
Token ID | 16 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
util | +1.365 |
onen | +1.331 |
idium | +1.301 |
hler | +1.248 |
cone | +1.216 |
Neg logit contributions | |
axes | -1.789 |
ochond | -1.770 |
OTOS | -1.707 |
opsis | -1.704 |
acceler | -1.695 |
Token | , |
Token ID | 11 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
util | +5.213 |
onen | +4.824 |
hler | +4.481 |
kov | +4.307 |
hey | +4.304 |
Neg logit contributions | |
escription | -11.496 |
dilig | -10.500 |
subsequ | -10.144 |
pollut | -10.005 |
ochond | -9.755 |
Token | 6 |
Token ID | 718 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
util | +3.630 |
onen | +3.524 |
idium | +3.435 |
hler | +3.352 |
cone | +3.260 |
Neg logit contributions | |
ochond | -3.674 |
axes | -3.657 |
OTOS | -3.494 |
opsis | -3.491 |
pollut | -3.484 |
Token | }, |
Token ID | 5512 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
util | +3.202 |
onen | +3.110 |
idium | +3.024 |
hler | +2.924 |
cone | +2.839 |
Neg logit contributions | |
axes | -4.353 |
ochond | -4.347 |
OTOS | -4.174 |
opsis | -4.163 |
pollut | -4.162 |
Token | { |
Token ID | 1391 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
axes | +0.232 |
ochond | +0.226 |
pollut | +0.222 |
acceler | +0.221 |
opsis | +0.220 |
Neg logit contributions | |
util | -0.135 |
onen | -0.132 |
idium | -0.131 |
hler | -0.123 |
cone | -0.120 |
Token | 1 |
Token ID | 16 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
util | +1.419 |
onen | +1.385 |
idium | +1.357 |
hler | +1.300 |
cone | +1.269 |
Neg logit contributions | |
axes | -1.836 |
ochond | -1.815 |
opsis | -1.751 |
OTOS | -1.750 |
acceler | -1.740 |
Token | who |
Token ID | 508 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
axes | +2.634 |
ochond | +2.515 |
acceler | +2.467 |
pollut | +2.412 |
OTOS | +2.387 |
Neg logit contributions | |
util | -3.832 |
onen | -3.774 |
idium | -3.721 |
hler | -3.580 |
ilogy | -3.550 |
Token | say |
Token ID | 910 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
axes | +2.833 |
ochond | +2.762 |
acceler | +2.645 |
pollut | +2.633 |
opsis | +2.630 |
Neg logit contributions | |
util | -3.583 |
onen | -3.502 |
idium | -3.462 |
hler | -3.314 |
avorite | -3.279 |
Token | that |
Token ID | 326 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
axes | +2.096 |
ochond | +2.044 |
acceler | +1.995 |
pollut | +1.956 |
OTOS | +1.930 |
Neg logit contributions | |
util | -2.941 |
onen | -2.875 |
idium | -2.853 |
hler | -2.741 |
ilogy | -2.713 |
Token | making |
Token ID | 1642 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
axes | +2.858 |
ochond | +2.752 |
acceler | +2.735 |
pollut | +2.662 |
opsis | +2.622 |
Neg logit contributions | |
util | -3.802 |
onen | -3.719 |
idium | -3.686 |
hler | -3.535 |
irtual | -3.487 |
Token | middle |
Token ID | 3504 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
axes | +1.307 |
ochond | +1.289 |
acceler | +1.233 |
pollut | +1.225 |
OTOS | +1.221 |
Neg logit contributions | |
util | -1.652 |
onen | -1.615 |
idium | -1.589 |
hler | -1.537 |
cone | -1.510 |
Token | and |
Token ID | 290 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
axes | +2.528 |
ochond | +2.482 |
acceler | +2.368 |
pollut | +2.338 |
opsis | +2.302 |
Neg logit contributions | |
util | -3.954 |
onen | -3.912 |
idium | -3.884 |
hler | -3.726 |
avorite | -3.688 |
Token | high |
Token ID | 1029 |
Feature activation | +6.47e-02 |
Pos logit contributions | |
util | +5.805 |
onen | +5.794 |
idium | +5.669 |
hler | +5.637 |
ussen | +5.421 |
Neg logit contributions | |
escription | -8.415 |
ochond | -8.369 |
OTOS | -8.091 |
axes | -7.980 |
opsis | -7.961 |
Token | school |
Token ID | 1524 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
util | +0.729 |
onen | +0.710 |
idium | +0.690 |
hler | +0.678 |
cone | +0.663 |
Neg logit contributions | |
ochond | -0.547 |
axes | -0.546 |
opsis | -0.528 |
OTOS | -0.526 |
escription | -0.514 |
Token | ers |
Token ID | 364 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
axes | +1.139 |
ochond | +1.133 |
OTOS | +1.075 |
acceler | +1.073 |
pollut | +1.073 |
Neg logit contributions | |
util | -1.380 |
onen | -1.348 |
idium | -1.325 |
hler | -1.284 |
cone | -1.258 |
Token | start |
Token ID | 923 |
Feature activation | -9.94e-02 |
Pos logit contributions | |
axes | +2.251 |
ochond | +2.200 |
acceler | +2.137 |
pollut | +2.107 |
opsis | +2.075 |
Neg logit contributions | |
util | -2.924 |
onen | -2.870 |
idium | -2.845 |
hler | -2.721 |
ilogy | -2.686 |
Token | classes |
Token ID | 6097 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
axes | +0.876 |
ochond | +0.875 |
OTOS | +0.831 |
opsis | +0.829 |
pollut | +0.827 |
Neg logit contributions | |
util | -1.097 |
onen | -1.072 |
idium | -1.049 |
hler | -1.020 |
cone | -1.000 |
Token | the |
Token ID | 262 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
axes | +1.052 |
ochond | +1.046 |
OTOS | +0.990 |
pollut | +0.988 |
opsis | +0.988 |
Neg logit contributions | |
util | -1.379 |
onen | -1.349 |
idium | -1.326 |
hler | -1.286 |
cone | -1.263 |
Token | commitment |
Token ID | 7901 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
axes | +0.758 |
ochond | +0.754 |
OTOS | +0.713 |
opsis | +0.712 |
pollut | +0.711 |
Neg logit contributions | |
util | -1.031 |
onen | -1.009 |
idium | -0.991 |
hler | -0.963 |
cone | -0.945 |
Token | to |
Token ID | 284 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
util | +0.229 |
onen | +0.224 |
idium | +0.220 |
hler | +0.214 |
cone | +0.210 |
Neg logit contributions | |
axes | -0.169 |
ochond | -0.168 |
OTOS | -0.159 |
opsis | -0.159 |
pollut | -0.158 |
Token | advancing |
Token ID | 19988 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
util | +0.236 |
onen | +0.231 |
idium | +0.225 |
hler | +0.220 |
cone | +0.215 |
Neg logit contributions | |
ochond | -0.192 |
axes | -0.191 |
opsis | -0.182 |
OTOS | -0.182 |
escription | -0.180 |
Token | civil |
Token ID | 3026 |
Feature activation | -8.00e-02 |
Pos logit contributions | |
axes | +2.459 |
ochond | +2.398 |
acceler | +2.310 |
pollut | +2.290 |
OTOS | +2.247 |
Neg logit contributions | |
util | -3.423 |
onen | -3.364 |
idium | -3.319 |
hler | -3.193 |
cone | -3.148 |
Token | and |
Token ID | 290 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
ochond | +0.724 |
axes | +0.724 |
OTOS | +0.688 |
opsis | +0.685 |
pollut | +0.682 |
Neg logit contributions | |
util | -0.864 |
onen | -0.843 |
idium | -0.826 |
hler | -0.803 |
cone | -0.786 |
Token | human |
Token ID | 1692 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
util | +6.578 |
onen | +6.365 |
hler | +6.028 |
idium | +5.867 |
irtual | +5.687 |
Neg logit contributions | |
escription | -7.834 |
ochond | -7.753 |
opsis | -7.582 |
axes | -7.518 |
OTOS | -7.337 |
Token | rights |
Token ID | 2489 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
util | +1.728 |
onen | +1.628 |
idium | +1.609 |
hler | +1.572 |
cone | +1.505 |
Neg logit contributions | |
ochond | -2.137 |
escription | -2.062 |
axes | -2.054 |
opsis | -2.047 |
OTOS | -2.033 |
Token | — |
Token ID | 960 |
Feature activation | -2.10e-03 |
Pos logit contributions | |
util | +2.584 |
onen | +2.493 |
idium | +2.419 |
hler | +2.367 |
cone | +2.331 |
Neg logit contributions | |
ochond | -2.277 |
axes | -2.243 |
escription | -2.222 |
OTOS | -2.221 |
opsis | -2.159 |
Token | these |
Token ID | 27218 |
Feature activation | +9.45e-02 |
Pos logit contributions | |
axes | +0.023 |
ochond | +0.023 |
opsis | +0.022 |
OTOS | +0.022 |
pollut | +0.022 |
Neg logit contributions | |
util | -0.019 |
onen | -0.019 |
idium | -0.018 |
hler | -0.017 |
cone | -0.017 |
Token | are |
Token ID | 389 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
util | +1.000 |
onen | +0.974 |
idium | +0.947 |
hler | +0.926 |
cone | +0.909 |
Neg logit contributions | |
ochond | -0.878 |
axes | -0.851 |
OTOS | -0.834 |
opsis | -0.832 |
escription | -0.828 |
Token | AIR |
Token ID | 42149 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
axes | +0.001 |
ochond | +0.001 |
opsis | +0.001 |
pollut | +0.001 |
OTOS | +0.001 |
Neg logit contributions | |
util | -0.001 |
onen | -0.001 |
idium | -0.001 |
hler | -0.001 |
cone | -0.001 |
Token | � |
Token ID | 447 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
axes | +2.085 |
ochond | +2.034 |
acceler | +1.980 |
pollut | +1.942 |
OTOS | +1.933 |
Neg logit contributions | |
util | -2.862 |
onen | -2.835 |
idium | -2.802 |
hler | -2.710 |
cone | -2.672 |
Token | � |
Token ID | 247 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
axes | +2.984 |
ochond | +2.939 |
opsis | +2.827 |
OTOS | +2.822 |
acceler | +2.817 |
Neg logit contributions | |
util | -3.173 |
onen | -3.111 |
idium | -3.043 |
ilogy | -2.898 |
hler | -2.897 |
Token | s |
Token ID | 82 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
axes | +3.286 |
ochond | +3.193 |
acceler | +3.131 |
opsis | +3.045 |
pollut | +3.039 |
Neg logit contributions | |
onen | -4.302 |
util | -4.295 |
idium | -4.256 |
hler | -4.104 |
avorite | -4.095 |
Token | Health |
Token ID | 3893 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
axes | +2.079 |
ochond | +2.020 |
acceler | +1.953 |
pollut | +1.952 |
opsis | +1.923 |
Neg logit contributions | |
util | -2.666 |
onen | -2.613 |
idium | -2.580 |
hler | -2.495 |
cone | -2.446 |
Token | and |
Token ID | 290 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
util | +0.272 |
onen | +0.266 |
idium | +0.259 |
hler | +0.252 |
cone | +0.246 |
Neg logit contributions | |
axes | -0.256 |
ochond | -0.255 |
opsis | -0.243 |
OTOS | -0.243 |
pollut | -0.242 |
Token | Social |
Token ID | 5483 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
util | +6.273 |
onen | +6.027 |
idium | +5.611 |
hler | +5.585 |
cone | +5.421 |
Neg logit contributions | |
ochond | -8.517 |
axes | -8.459 |
escription | -8.275 |
opsis | -8.243 |
OTOS | -8.147 |
Token | Development |
Token ID | 7712 |
Feature activation | -5.82e-03 |
Pos logit contributions | |
util | +2.922 |
onen | +2.815 |
idium | +2.736 |
hler | +2.710 |
illance | +2.568 |
Neg logit contributions | |
ochond | -3.112 |
axes | -3.111 |
opsis | -3.016 |
OTOS | -3.005 |
escription | -2.961 |
Token | program |
Token ID | 1430 |
Feature activation | +7.57e-02 |
Pos logit contributions | |
axes | +0.053 |
ochond | +0.053 |
OTOS | +0.050 |
acceler | +0.050 |
opsis | +0.050 |
Neg logit contributions | |
util | -0.062 |
onen | -0.061 |
idium | -0.060 |
hler | -0.058 |
cone | -0.057 |
Token | develops |
Token ID | 21126 |
Feature activation | -6.67e-02 |
Pos logit contributions | |
util | +0.871 |
onen | +0.848 |
idium | +0.830 |
hler | +0.808 |
cone | +0.791 |
Neg logit contributions | |
ochond | -0.634 |
axes | -0.630 |
OTOS | -0.602 |
opsis | -0.597 |
pollut | -0.594 |
Token | knowledge |
Token ID | 3725 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
axes | +0.582 |
ochond | +0.576 |
pollut | +0.547 |
acceler | +0.547 |
OTOS | +0.545 |
Neg logit contributions | |
util | -0.745 |
onen | -0.728 |
idium | -0.717 |
hler | -0.695 |
cone | -0.681 |
Token | v |
Token ID | 85 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
util | +0.607 |
onen | +0.556 |
idium | +0.531 |
hler | +0.523 |
cone | +0.517 |
Neg logit contributions | |
escription | -0.851 |
axes | -0.848 |
OTOS | -0.830 |
ochond | -0.830 |
pollut | -0.823 |
Token | 2 |
Token ID | 17 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
util | +3.430 |
onen | +2.844 |
idium | +2.735 |
hler | +2.733 |
cone | +2.651 |
Neg logit contributions | |
escription | -7.324 |
pollut | -6.648 |
dilig | -6.547 |
subsequ | -6.541 |
axes | -6.505 |
Token | . |
Token ID | 764 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
util | +4.700 |
onen | +4.230 |
hler | +4.110 |
idium | +3.984 |
cone | +3.906 |
Neg logit contributions | |
escription | -5.899 |
ochond | -5.011 |
pollut | -4.976 |
dilig | -4.958 |
subsequ | -4.945 |
Token | Ga |
Token ID | 12822 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
util | +4.889 |
onen | +4.709 |
idium | +4.571 |
hler | +4.522 |
cone | +4.478 |
Neg logit contributions | |
ochond | -4.590 |
OTOS | -4.454 |
opsis | -4.389 |
escription | -4.360 |
axes | -4.310 |
Token | ussian |
Token ID | 31562 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
util | +3.348 |
onen | +3.048 |
ussen | +2.505 |
uristic | +2.491 |
hler | +2.406 |
Neg logit contributions | |
escription | -11.197 |
OTOS | -11.055 |
DAC | -10.980 |
physic | -10.883 |
pollut | -10.849 |
Token | Bl |
Token ID | 3629 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
util | +4.167 |
onen | +3.903 |
hler | +3.569 |
idium | +3.505 |
kov | +3.360 |
Neg logit contributions | |
escription | -8.257 |
ochond | -7.703 |
opsis | -7.635 |
pollut | -7.610 |
subsequ | -7.544 |
Token | ur |
Token ID | 333 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
util | +1.770 |
uristic | +1.176 |
onen | +1.129 |
unia | +0.741 |
ussen | +0.495 |
Neg logit contributions | |
escription | -14.059 |
OTOS | -13.484 |
physic | -13.415 |
axes | -13.401 |
dilig | -13.304 |
Token | ( |
Token ID | 357 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
util | +3.496 |
onen | +3.218 |
hler | +2.978 |
idium | +2.949 |
cone | +2.806 |
Neg logit contributions | |
escription | -6.883 |
pollut | -6.195 |
axes | -6.078 |
ochond | -6.058 |
subsequ | -6.045 |
Token | gray |
Token ID | 12768 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
util | +2.958 |
onen | +2.827 |
idium | +2.764 |
hler | +2.661 |
cone | +2.611 |
Neg logit contributions | |
escription | -4.652 |
ochond | -4.433 |
OTOS | -4.432 |
opsis | -4.377 |
phies | -4.121 |
Token | , |
Token ID | 837 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
util | +4.359 |
onen | +4.085 |
idium | +3.860 |
hler | +3.799 |
kov | +3.701 |
Neg logit contributions | |
escription | -5.089 |
ochond | -4.547 |
subsequ | -4.538 |
pollut | -4.502 |
OTOS | -4.445 |
Token | ( |
Token ID | 357 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
util | +0.109 |
onen | +0.105 |
idium | +0.101 |
hler | +0.098 |
cone | +0.098 |
Neg logit contributions | |
ochond | -0.131 |
escription | -0.129 |
axes | -0.128 |
OTOS | -0.126 |
opsis | -0.126 |
Token |
|
Token ID | 198 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
util | +2.310 |
onen | +2.149 |
hler | +2.031 |
idium | +2.026 |
cone | +1.981 |
Neg logit contributions | |
escription | -3.030 |
axes | -2.771 |
ochond | -2.758 |
pollut | -2.724 |
OTOS | -2.644 |
Token | n |
Token ID | 77 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
util | +3.206 |
onen | +3.031 |
idium | +2.911 |
hler | +2.849 |
cone | +2.763 |
Neg logit contributions | |
axes | -3.701 |
ochond | -3.591 |
acceler | -3.565 |
escription | -3.533 |
pollut | -3.527 |
Token | pm |
Token ID | 4426 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
util | +2.752 |
onen | +2.515 |
hler | +2.003 |
unia | +1.838 |
idium | +1.833 |
Neg logit contributions | |
OTOS | -9.835 |
axes | -9.675 |
escription | -9.668 |
DAC | -9.333 |
physic | -9.327 |
Token | install |
Token ID | 2721 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
util | +3.026 |
onen | +2.867 |
hler | +2.603 |
idium | +2.597 |
unia | +2.546 |
Neg logit contributions | |
ochond | -3.930 |
axes | -3.837 |
OTOS | -3.768 |
escription | -3.759 |
opsis | -3.673 |
Token | - |
Token ID | 532 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
util | +6.091 |
onen | +5.901 |
idium | +5.662 |
hler | +5.496 |
ussen | +5.418 |
Neg logit contributions | |
ochond | -4.712 |
OTOS | -4.524 |
axes | -4.499 |
escription | -4.439 |
opsis | -4.391 |
Token | g |
Token ID | 70 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
util | +3.618 |
onen | +3.142 |
hler | +3.014 |
idium | +2.962 |
cone | +2.952 |
Neg logit contributions | |
escription | -4.997 |
ochond | -4.974 |
pollut | -4.775 |
axes | -4.766 |
subsequ | -4.718 |
Token | server |
Token ID | 4382 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
util | +8.299 |
onen | +7.975 |
idium | +7.536 |
hler | +7.455 |
ussen | +7.213 |
Neg logit contributions | |
ochond | -6.410 |
OTOS | -6.106 |
axes | -6.081 |
escription | -5.989 |
opsis | -5.930 |
Token | less |
Token ID | 1203 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
util | +0.461 |
onen | +0.437 |
idium | +0.425 |
hler | +0.417 |
cone | +0.408 |
Neg logit contributions | |
ochond | -0.440 |
axes | -0.440 |
escription | -0.424 |
OTOS | -0.423 |
pollut | -0.417 |
Token |
|
Token ID | 198 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
util | +4.328 |
onen | +4.162 |
idium | +3.979 |
hler | +3.941 |
cone | +3.815 |
Neg logit contributions | |
ochond | -3.893 |
axes | -3.872 |
OTOS | -3.776 |
pollut | -3.640 |
opsis | -3.634 |
Token |
|
Token ID | 198 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
ochond | +0.619 |
axes | +0.618 |
escription | +0.611 |
pollut | +0.593 |
OTOS | +0.587 |
Neg logit contributions | |
util | -0.662 |
onen | -0.639 |
idium | -0.619 |
hler | -0.606 |
cone | -0.593 |
Token | You |
Token ID | 1639 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
axes | +3.890 |
ochond | +3.872 |
opsis | +3.747 |
OTOS | +3.708 |
acceler | +3.656 |
Neg logit contributions | |
util | -3.422 |
idium | -3.375 |
onen | -3.370 |
hler | -3.228 |
avorite | -3.219 |
Token | image |
Token ID | 9060 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
util | +2.862 |
onen | +2.638 |
idium | +2.542 |
cone | +2.501 |
hler | +2.443 |
Neg logit contributions | |
ochond | -4.674 |
axes | -4.603 |
OTOS | -4.518 |
pollut | -4.513 |
acceler | -4.493 |
Token | , |
Token ID | 11 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
util | +5.358 |
onen | +5.090 |
idium | +4.998 |
hler | +4.937 |
cone | +4.876 |
Neg logit contributions | |
ochond | -3.896 |
axes | -3.751 |
pollut | -3.678 |
opsis | -3.633 |
acceler | -3.621 |
Token | height |
Token ID | 6001 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
util | +1.959 |
onen | +1.886 |
idium | +1.851 |
hler | +1.799 |
cone | +1.791 |
Neg logit contributions | |
ochond | -1.640 |
axes | -1.571 |
OTOS | -1.544 |
opsis | -1.538 |
escription | -1.517 |
Token | = |
Token ID | 28 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
util | +1.837 |
onen | +1.781 |
idium | +1.752 |
hler | +1.711 |
cone | +1.683 |
Neg logit contributions | |
ochond | -1.261 |
axes | -1.249 |
opsis | -1.189 |
pollut | -1.188 |
OTOS | -1.187 |
Token | 600 |
Token ID | 8054 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
util | +1.847 |
onen | +1.742 |
idium | +1.707 |
hler | +1.658 |
cone | +1.652 |
Neg logit contributions | |
ochond | -2.164 |
axes | -2.118 |
opsis | -2.069 |
pollut | -2.060 |
OTOS | -2.059 |
Token | ) |
Token ID | 8 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
util | +5.249 |
onen | +4.972 |
idium | +4.946 |
hler | +4.778 |
cone | +4.713 |
Neg logit contributions | |
ochond | -5.958 |
pollut | -5.617 |
opsis | -5.581 |
OTOS | -5.577 |
axes | -5.554 |
Token | gray |
Token ID | 12768 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
util | +7.684 |
onen | +7.004 |
cone | +6.901 |
idium | +6.756 |
hler | +6.721 |
Neg logit contributions | |
ochond | -6.919 |
escription | -6.547 |
OTOS | -6.514 |
opsis | -6.291 |
pollut | -6.125 |
Token | = |
Token ID | 796 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
util | +3.592 |
onen | +3.459 |
idium | +3.349 |
hler | +3.283 |
cone | +3.268 |
Neg logit contributions | |
ochond | -3.345 |
axes | -3.316 |
OTOS | -3.198 |
acceler | -3.198 |
pollut | -3.195 |
Token | c |
Token ID | 269 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
util | +2.484 |
onen | +2.372 |
idium | +2.328 |
hler | +2.255 |
cone | +2.252 |
Neg logit contributions | |
ochond | -2.407 |
axes | -2.314 |
OTOS | -2.283 |
opsis | -2.274 |
escription | -2.267 |
Token | v |
Token ID | 85 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
util | +1.968 |
onen | +1.702 |
hler | +1.629 |
idium | +1.622 |
cone | +1.613 |
Neg logit contributions | |
escription | -3.073 |
OTOS | -3.046 |
axes | -3.042 |
pollut | -2.974 |
ochond | -2.973 |
Token | 2 |
Token ID | 17 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
util | +3.138 |
onen | +2.600 |
hler | +2.541 |
idium | +2.536 |
cone | +2.471 |
Neg logit contributions | |
escription | -5.793 |
pollut | -5.438 |
axes | -5.359 |
ochond | -5.351 |
subsequ | -5.281 |
Token | parse |
Token ID | 29572 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
util | +2.553 |
onen | +2.342 |
idium | +2.231 |
hler | +2.204 |
cone | +2.183 |
Neg logit contributions | |
axes | -3.641 |
ochond | -3.635 |
pollut | -3.575 |
escription | -3.575 |
OTOS | -3.560 |
Token | . |
Token ID | 13 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
util | +4.555 |
onen | +4.282 |
idium | +4.146 |
hler | +4.121 |
cone | +3.960 |
Neg logit contributions | |
ochond | -4.191 |
axes | -4.100 |
OTOS | -3.990 |
pollut | -3.969 |
escription | -3.928 |
Token | Arg |
Token ID | 28100 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
util | +1.782 |
onen | +1.713 |
idium | +1.661 |
hler | +1.614 |
cone | +1.570 |
Neg logit contributions | |
ochond | -1.801 |
axes | -1.783 |
pollut | -1.731 |
OTOS | -1.718 |
opsis | -1.706 |
Token | ument |
Token ID | 1713 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
util | +0.625 |
onen | +0.613 |
idium | +0.601 |
hler | +0.584 |
cone | +0.571 |
Neg logit contributions | |
axes | -0.510 |
ochond | -0.507 |
opsis | -0.481 |
OTOS | -0.481 |
pollut | -0.478 |
Token | Parser |
Token ID | 46677 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
axes | +0.287 |
ochond | +0.287 |
opsis | +0.268 |
OTOS | +0.268 |
acceler | +0.264 |
Neg logit contributions | |
util | -0.396 |
onen | -0.392 |
idium | -0.384 |
hler | -0.373 |
cone | -0.366 |
Token | () |
Token ID | 3419 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
util | +5.108 |
onen | +4.805 |
hler | +4.720 |
idium | +4.719 |
cone | +4.487 |
Neg logit contributions | |
ochond | -4.593 |
axes | -4.505 |
pollut | -4.390 |
escription | -4.359 |
OTOS | -4.347 |
Token | ap |
Token ID | 2471 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
util | +8.331 |
onen | +7.663 |
hler | +7.625 |
cone | +7.594 |
idium | +7.472 |
Neg logit contributions | |
ochond | -6.075 |
escription | -5.864 |
OTOS | -5.779 |
opsis | -5.451 |
pollut | -5.387 |
Token | . |
Token ID | 13 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
util | +4.454 |
onen | +4.123 |
idium | +4.026 |
hler | +4.003 |
cone | +3.873 |
Neg logit contributions | |
ochond | -4.606 |
axes | -4.574 |
pollut | -4.492 |
OTOS | -4.431 |
escription | -4.381 |
Token | add |
Token ID | 2860 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
util | +0.819 |
onen | +0.788 |
idium | +0.763 |
hler | +0.741 |
cone | +0.727 |
Neg logit contributions | |
ochond | -0.931 |
axes | -0.928 |
OTOS | -0.897 |
pollut | -0.893 |
acceler | -0.891 |
Token | _ |
Token ID | 62 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
util | +2.893 |
onen | +2.761 |
idium | +2.635 |
hler | +2.596 |
cone | +2.581 |
Neg logit contributions | |
ochond | -3.017 |
axes | -2.981 |
pollut | -2.926 |
acceler | -2.904 |
OTOS | -2.880 |
Token | argument |
Token ID | 49140 |
Feature activation | +7.39e-02 |
Pos logit contributions | |
util | +0.313 |
onen | +0.302 |
idium | +0.295 |
hler | +0.288 |
cone | +0.284 |
Neg logit contributions | |
ochond | -0.250 |
axes | -0.250 |
OTOS | -0.239 |
acceler | -0.237 |
pollut | -0.237 |
Token | . |
Token ID | 13 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
util | +1.531 |
onen | +1.489 |
idium | +1.463 |
hler | +1.424 |
cone | +1.386 |
Neg logit contributions | |
ochond | -1.309 |
axes | -1.306 |
OTOS | -1.247 |
opsis | -1.236 |
pollut | -1.230 |
Token |
|
Token ID | 198 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
axes | +0.449 |
ochond | +0.447 |
OTOS | +0.426 |
opsis | +0.425 |
pollut | +0.424 |
Neg logit contributions | |
util | -0.503 |
onen | -0.491 |
idium | -0.482 |
hler | -0.467 |
cone | -0.457 |
Token |
|
Token ID | 198 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
util | +1.138 |
onen | +1.077 |
idium | +1.028 |
hler | +1.019 |
cone | +0.989 |
Neg logit contributions | |
escription | -1.348 |
ochond | -1.286 |
axes | -1.279 |
pollut | -1.246 |
opsis | -1.221 |
Token | J |
Token ID | 41 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
util | +1.363 |
onen | +1.311 |
idium | +1.273 |
hler | +1.223 |
cone | +1.204 |
Neg logit contributions | |
axes | -1.671 |
ochond | -1.660 |
acceler | -1.597 |
escription | -1.587 |
pollut | -1.584 |
Token | ag |
Token ID | 363 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
util | +4.046 |
onen | +3.926 |
idium | +3.827 |
hler | +3.700 |
cone | +3.595 |
Neg logit contributions | |
axes | -3.351 |
ochond | -3.345 |
acceler | -3.197 |
OTOS | -3.171 |
pollut | -3.168 |
Token | d |
Token ID | 67 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
axes | +2.268 |
ochond | +2.246 |
opsis | +2.167 |
pollut | +2.126 |
acceler | +2.123 |
Neg logit contributions | |
util | -2.015 |
onen | -1.990 |
idium | -1.941 |
hler | -1.902 |
cone | -1.829 |
Token | ish |
Token ID | 680 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
util | +7.109 |
onen | +6.817 |
idium | +6.512 |
unia | +6.453 |
hler | +6.389 |
Neg logit contributions | |
axes | -7.240 |
ochond | -7.195 |
pollut | -7.118 |
OTOS | -7.025 |
acceler | -6.994 |
Token | Sh |
Token ID | 911 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
util | +1.273 |
onen | +1.241 |
idium | +1.209 |
hler | +1.170 |
cone | +1.146 |
Neg logit contributions | |
axes | -1.226 |
ochond | -1.225 |
acceler | -1.164 |
OTOS | -1.163 |
pollut | -1.158 |
Token | ind |
Token ID | 521 |
Feature activation | -8.46e-03 |
Pos logit contributions | |
util | +1.499 |
onen | +1.470 |
idium | +1.433 |
hler | +1.384 |
cone | +1.351 |
Neg logit contributions | |
axes | -1.394 |
ochond | -1.358 |
acceler | -1.323 |
pollut | -1.319 |
OTOS | -1.311 |
Token | e |
Token ID | 68 |
Feature activation | +9.33e-02 |
Pos logit contributions | |
axes | +0.080 |
ochond | +0.080 |
OTOS | +0.076 |
opsis | +0.076 |
pollut | +0.076 |
Neg logit contributions | |
util | -0.088 |
onen | -0.086 |
idium | -0.084 |
hler | -0.082 |
cone | -0.080 |
Token | Senior |
Token ID | 14017 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
util | +0.973 |
onen | +0.953 |
idium | +0.930 |
hler | +0.906 |
cone | +0.882 |
Neg logit contributions | |
axes | -0.879 |
ochond | -0.876 |
OTOS | -0.834 |
opsis | -0.830 |
acceler | -0.828 |
Token | , |
Token ID | 11 |
Feature activation | +1.63e-03 |
Pos logit contributions | |
util | +2.589 |
onen | +2.530 |
idium | +2.466 |
hler | +2.368 |
cone | +2.352 |
Neg logit contributions | |
ochond | -2.344 |
axes | -2.300 |
OTOS | -2.251 |
escription | -2.227 |
opsis | -2.215 |
Token | one |
Token ID | 530 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
util | +0.018 |
onen | +0.017 |
idium | +0.017 |
hler | +0.017 |
cone | +0.016 |
Neg logit contributions | |
ochond | -0.014 |
axes | -0.014 |
OTOS | -0.014 |
opsis | -0.014 |
pollut | -0.014 |
Token | might |
Token ID | 1244 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
util | +1.822 |
onen | +1.772 |
idium | +1.729 |
hler | +1.684 |
cone | +1.682 |
Neg logit contributions | |
ochond | -1.471 |
axes | -1.419 |
escription | -1.411 |
OTOS | -1.404 |
opsis | -1.393 |
Token | ask |
Token ID | 1265 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
util | +2.279 |
onen | +2.193 |
idium | +2.147 |
hler | +2.113 |
cone | +2.056 |
Neg logit contributions | |
ochond | -1.991 |
OTOS | -1.970 |
axes | -1.967 |
escription | -1.901 |
opsis | -1.882 |
Token | , |
Token ID | 11 |
Feature activation | +9.20e-02 |
Pos logit contributions | |
util | +1.350 |
onen | +1.314 |
idium | +1.289 |
hler | +1.246 |
cone | +1.223 |
Neg logit contributions | |
ochond | -1.190 |
axes | -1.187 |
OTOS | -1.131 |
opsis | -1.129 |
pollut | -1.124 |
Token | why |
Token ID | 1521 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
util | +0.942 |
onen | +0.916 |
idium | +0.896 |
hler | +0.865 |
cone | +0.850 |
Neg logit contributions | |
ochond | -0.886 |
axes | -0.879 |
OTOS | -0.844 |
opsis | -0.840 |
escription | -0.834 |
Token | go |
Token ID | 467 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
util | +7.367 |
onen | +7.008 |
idium | +6.795 |
cone | +6.644 |
hler | +6.384 |
Neg logit contributions | |
escription | -6.902 |
ochond | -6.866 |
OTOS | -6.804 |
opsis | -6.655 |
axes | -6.571 |
Token | that |
Token ID | 326 |
Feature activation | +9.93e-02 |
Pos logit contributions | |
util | +0.797 |
onen | +0.780 |
idium | +0.764 |
hler | +0.741 |
cone | +0.729 |
Neg logit contributions | |
ochond | -0.653 |
axes | -0.649 |
OTOS | -0.621 |
opsis | -0.620 |
pollut | -0.616 |
Token | one |
Token ID | 530 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
util | +1.222 |
onen | +1.198 |
idium | +1.173 |
hler | +1.148 |
cone | +1.134 |
Neg logit contributions | |
ochond | -0.743 |
axes | -0.736 |
opsis | -0.702 |
OTOS | -0.697 |
pollut | -0.690 |
Token | small |
Token ID | 1402 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
axes | +0.878 |
ochond | +0.867 |
OTOS | +0.817 |
acceler | +0.816 |
pollut | +0.816 |
Neg logit contributions | |
util | -1.348 |
onen | -1.317 |
idium | -1.300 |
hler | -1.261 |
cone | -1.234 |
Token |
|
Token ID | 198 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
util | +2.359 |
onen | +2.317 |
idium | +2.238 |
cone | +2.192 |
hler | +2.189 |
Neg logit contributions | |
ochond | -1.936 |
axes | -1.893 |
opsis | -1.852 |
OTOS | -1.833 |
escription | -1.804 |
Token | 43 |
Token ID | 5946 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
axes | +1.675 |
ochond | +1.654 |
acceler | +1.586 |
opsis | +1.579 |
pollut | +1.577 |
Neg logit contributions | |
util | -1.829 |
onen | -1.791 |
idium | -1.759 |
hler | -1.700 |
cone | -1.673 |
Token | ( |
Token ID | 357 |
Feature activation | +4.64e-03 |
Pos logit contributions | |
axes | +3.170 |
ochond | +3.027 |
opsis | +3.000 |
acceler | +2.920 |
escription | +2.904 |
Neg logit contributions | |
util | -4.965 |
onen | -4.901 |
idium | -4.828 |
hler | -4.757 |
cone | -4.749 |
Token | S |
Token ID | 50 |
Feature activation | -9.64e-02 |
Pos logit contributions | |
util | +0.042 |
onen | +0.041 |
idium | +0.040 |
hler | +0.039 |
cone | +0.038 |
Neg logit contributions | |
axes | -0.050 |
ochond | -0.050 |
OTOS | -0.047 |
opsis | -0.047 |
pollut | -0.047 |
Token | 4 |
Token ID | 19 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
axes | +1.013 |
ochond | +1.011 |
OTOS | +0.967 |
opsis | +0.965 |
pollut | +0.962 |
Neg logit contributions | |
util | -0.898 |
onen | -0.875 |
idium | -0.854 |
hler | -0.825 |
cone | -0.807 |
Token | ) |
Token ID | 8 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
axes | +2.318 |
ochond | +2.279 |
opsis | +2.172 |
acceler | +2.165 |
pollut | +2.156 |
Neg logit contributions | |
util | -2.678 |
onen | -2.620 |
idium | -2.551 |
hler | -2.449 |
ilogy | -2.431 |
Token | DOI |
Token ID | 40722 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
axes | +4.118 |
ochond | +4.011 |
acceler | +3.907 |
OTOS | +3.837 |
opsis | +3.837 |
Neg logit contributions | |
util | -4.570 |
onen | -4.484 |
idium | -4.359 |
cone | -4.267 |
hler | -4.222 |
Token | : |
Token ID | 25 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
axes | +5.850 |
acceler | +5.711 |
OTOS | +5.586 |
ochond | +5.546 |
pollut | +5.537 |
Neg logit contributions | |
util | -11.592 |
irtual | -11.261 |
idium | -11.261 |
onen | -11.206 |
avorite | -11.143 |
Token | 10 |
Token ID | 838 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
axes | +3.046 |
ochond | +2.947 |
acceler | +2.850 |
pollut | +2.847 |
OTOS | +2.831 |
Neg logit contributions | |
util | -4.920 |
onen | -4.779 |
hler | -4.775 |
idium | -4.742 |
cone | -4.649 |
Token | . |
Token ID | 13 |
Feature activation | -9.54e-02 |
Pos logit contributions | |
axes | +5.030 |
ochond | +5.009 |
OTOS | +4.745 |
acceler | +4.734 |
opsis | +4.710 |
Neg logit contributions | |
onen | -7.314 |
util | -7.306 |
avorite | -7.221 |
idium | -7.211 |
irtual | -6.996 |
Token | 10 |
Token ID | 940 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
axes | +1.103 |
ochond | +1.098 |
opsis | +1.055 |
OTOS | +1.055 |
acceler | +1.052 |
Neg logit contributions | |
util | -0.784 |
onen | -0.765 |
idium | -0.748 |
hler | -0.715 |
cone | -0.700 |
Token | 86 |
Token ID | 4521 |
Feature activation | -9.93e-02 |
Pos logit contributions | |
axes | +3.055 |
ochond | +3.032 |
acceler | +2.903 |
pollut | +2.869 |
opsis | +2.863 |
Neg logit contributions | |
util | -3.022 |
onen | -2.987 |
idium | -2.894 |
hler | -2.797 |
avorite | -2.750 |
Token | and |
Token ID | 290 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
axes | +0.478 |
ochond | +0.475 |
OTOS | +0.451 |
pollut | +0.451 |
acceler | +0.450 |
Neg logit contributions | |
util | -0.581 |
onen | -0.568 |
idium | -0.557 |
hler | -0.540 |
cone | -0.530 |
Token | policy |
Token ID | 2450 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
util | +0.673 |
onen | +0.657 |
idium | +0.645 |
hler | +0.627 |
cone | +0.615 |
Neg logit contributions | |
ochond | -0.484 |
axes | -0.477 |
OTOS | -0.456 |
opsis | -0.453 |
escription | -0.449 |
Token |
|
Token ID | 198 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
util | +0.321 |
onen | +0.314 |
idium | +0.307 |
hler | +0.299 |
cone | +0.292 |
Neg logit contributions | |
ochond | -0.272 |
axes | -0.271 |
OTOS | -0.258 |
opsis | -0.257 |
pollut | -0.256 |
Token |
|
Token ID | 198 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
axes | +1.452 |
ochond | +1.449 |
escription | +1.383 |
pollut | +1.377 |
opsis | +1.374 |
Neg logit contributions | |
util | -1.663 |
onen | -1.618 |
idium | -1.580 |
hler | -1.538 |
cone | -1.506 |
Token | Americans |
Token ID | 17636 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
axes | +0.698 |
ochond | +0.695 |
OTOS | +0.669 |
opsis | +0.665 |
pollut | +0.663 |
Neg logit contributions | |
util | -0.611 |
onen | -0.596 |
idium | -0.583 |
hler | -0.562 |
cone | -0.548 |
Token | for |
Token ID | 329 |
Feature activation | -9.38e-01 |
Pos logit contributions | |
axes | +1.416 |
ochond | +1.402 |
pollut | +1.333 |
acceler | +1.331 |
OTOS | +1.330 |
Neg logit contributions | |
util | -1.763 |
onen | -1.729 |
idium | -1.690 |
hler | -1.640 |
cone | -1.609 |
Token | Prosper |
Token ID | 41342 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
pollut | +5.076 |
axes | +5.052 |
ochond | +4.893 |
DAC | +4.765 |
govern | +4.598 |
Neg logit contributions | |
onen | -12.534 |
avorite | -12.457 |
ilogy | -12.165 |
util | -11.854 |
idium | -11.812 |
Token | ity |
Token ID | 414 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
axes | +3.999 |
ochond | +3.969 |
OTOS | +3.821 |
pollut | +3.813 |
acceler | +3.808 |
Neg logit contributions | |
util | -3.618 |
onen | -3.579 |
idium | -3.462 |
hler | -3.347 |
avorite | -3.304 |
Token | : |
Token ID | 25 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
axes | +2.122 |
ochond | +2.053 |
acceler | +2.013 |
pollut | +1.987 |
OTOS | +1.967 |
Neg logit contributions | |
util | -2.769 |
onen | -2.720 |
idium | -2.650 |
hler | -2.573 |
cone | -2.544 |
Token | Dist |
Token ID | 4307 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
axes | +0.950 |
ochond | +0.942 |
OTOS | +0.900 |
pollut | +0.897 |
acceler | +0.896 |
Neg logit contributions | |
util | -1.054 |
onen | -1.030 |
idium | -1.009 |
hler | -0.977 |
cone | -0.957 |
Token | orting |
Token ID | 24707 |
Feature activation | -8.39e-02 |
Pos logit contributions | |
ochond | +4.457 |
axes | +4.407 |
opsis | +4.284 |
pollut | +4.268 |
escription | +4.163 |
Neg logit contributions | |
util | -2.864 |
onen | -2.845 |
idium | -2.779 |
hler | -2.678 |
cone | -2.655 |
Token |
|
Token ID | 198 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
axes | +3.386 |
ochond | +3.348 |
OTOS | +3.202 |
acceler | +3.187 |
opsis | +3.165 |
Neg logit contributions | |
util | -4.435 |
onen | -4.357 |
idium | -4.282 |
hler | -4.152 |
cone | -4.078 |
Token |
|
Token ID | 198 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
axes | +2.835 |
ochond | +2.823 |
OTOS | +2.685 |
opsis | +2.668 |
acceler | +2.663 |
Neg logit contributions | |
util | -3.772 |
onen | -3.715 |
idium | -3.680 |
avorite | -3.547 |
hler | -3.546 |
Token | Facebook |
Token ID | 12025 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
axes | +2.676 |
ochond | +2.536 |
acceler | +2.446 |
opsis | +2.367 |
OTOS | +2.331 |
Neg logit contributions | |
idium | -5.796 |
util | -5.778 |
irtual | -5.751 |
onen | -5.666 |
hler | -5.536 |
Token |
|
Token ID | 198 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
axes | +4.428 |
ochond | +4.397 |
OTOS | +4.279 |
acceler | +4.221 |
opsis | +4.191 |
Neg logit contributions | |
util | -7.242 |
idium | -7.137 |
avorite | -7.053 |
onen | -7.017 |
irtual | -6.866 |
Token |
|
Token ID | 198 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
axes | +1.614 |
ochond | +1.611 |
escription | +1.538 |
pollut | +1.532 |
OTOS | +1.526 |
Neg logit contributions | |
util | -1.845 |
onen | -1.798 |
idium | -1.753 |
hler | -1.708 |
cone | -1.671 |
Token | St |
Token ID | 1273 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
axes | +3.488 |
ochond | +3.428 |
opsis | +3.299 |
OTOS | +3.298 |
acceler | +3.255 |
Neg logit contributions | |
util | -3.583 |
idium | -3.480 |
onen | -3.446 |
hler | -3.320 |
irtual | -3.264 |
Token | umble |
Token ID | 10344 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
axes | +3.154 |
ait | +3.026 |
yn | +2.905 |
ochond | +2.877 |
opsis | +2.847 |
Neg logit contributions | |
�� | -13.331 |
util | -13.057 |
hler | -13.035 |
cone | -13.015 |
avorite | -12.918 |
Token | Upon |
Token ID | 23792 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
axes | +3.139 |
ochond | +3.043 |
opsis | +2.998 |
acceler | +2.977 |
OTOS | +2.911 |
Neg logit contributions | |
util | -4.981 |
onen | -4.887 |
hler | -4.765 |
idium | -4.760 |
avorite | -4.665 |
Token | What |
Token ID | 1867 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
axes | +2.664 |
ochond | +2.569 |
acceler | +2.485 |
DAC | +2.456 |
opsis | +2.455 |
Neg logit contributions | |
util | -3.977 |
onen | -3.844 |
idium | -3.813 |
cone | -3.740 |
hler | -3.726 |
Token | are |
Token ID | 389 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
axes | +2.963 |
opsis | +2.844 |
OTOS | +2.771 |
acceler | +2.709 |
pollut | +2.705 |
Neg logit contributions | |
util | -4.956 |
onen | -4.947 |
idium | -4.861 |
hler | -4.842 |
ussen | -4.697 |
Token | these |
Token ID | 777 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
axes | +1.444 |
ochond | +1.425 |
acceler | +1.363 |
pollut | +1.343 |
OTOS | +1.342 |
Neg logit contributions | |
util | -2.339 |
idium | -2.284 |
onen | -2.269 |
hler | -2.202 |
cone | -2.177 |
Token | ' |
Token ID | 6 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
util | +1.062 |
idium | +1.037 |
hler | +0.982 |
cone | +0.976 |
onen | +0.971 |
Neg logit contributions | |
ochond | -1.293 |
OTOS | -1.264 |
axes | -1.234 |
escription | -1.219 |
opsis | -1.198 |
Token | 2016 |
Token ID | 1584 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
axes | +0.117 |
ochond | +0.110 |
pollut | +0.110 |
acceler | +0.109 |
OTOS | +0.104 |
Neg logit contributions | |
onen | -0.170 |
util | -0.169 |
idium | -0.166 |
avorite | -0.160 |
hler | -0.158 |
Token | primary |
Token ID | 4165 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
axes | +2.123 |
pollut | +2.047 |
acceler | +2.015 |
pickup | +1.952 |
opsis | +1.940 |
Neg logit contributions | |
util | -3.198 |
onen | -3.093 |
idium | -3.041 |
avorite | -2.998 |
hler | -2.977 |
Token | Sanders |
Token ID | 5831 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
axes | +3.379 |
acceler | +3.200 |
opsis | +3.123 |
pollut | +3.114 |
ochond | +3.054 |
Neg logit contributions | |
util | -3.775 |
onen | -3.701 |
idium | -3.566 |
irtual | -3.485 |
hler | -3.426 |
Token | : |
Token ID | 25 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
axes | +0.843 |
ochond | +0.799 |
acceler | +0.784 |
pollut | +0.778 |
OTOS | +0.763 |
Neg logit contributions | |
util | -1.323 |
onen | -1.295 |
idium | -1.266 |
hler | -1.245 |
avorite | -1.221 |
Token | ' |
Token ID | 705 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
axes | +2.164 |
acceler | +2.096 |
opsis | +1.964 |
ochond | +1.945 |
pollut | +1.919 |
Neg logit contributions | |
util | -5.182 |
onen | -5.069 |
cone | -4.979 |
avorite | -4.973 |
idium | -4.940 |
Token | Damn |
Token ID | 43343 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
axes | +6.427 |
acceler | +5.624 |
yn | +5.490 |
ait | +5.397 |
ochond | +5.397 |
Neg logit contributions | |
avorite | -10.239 |
util | -9.628 |
onen | -9.516 |
unia | -9.467 |
idium | -9.199 |
Token | right |
Token ID | 826 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
axes | +0.570 |
ochond | +0.562 |
pollut | +0.527 |
acceler | +0.527 |
opsis | +0.525 |
Neg logit contributions | |
util | -0.728 |
onen | -0.711 |
idium | -0.702 |
hler | -0.683 |
cone | -0.672 |
Token | ' |
Token ID | 6 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
axes | +1.037 |
ochond | +1.022 |
acceler | +0.973 |
pollut | +0.972 |
opsis | +0.968 |
Neg logit contributions | |
util | -1.411 |
onen | -1.365 |
idium | -1.352 |
hler | -1.308 |
ilogy | -1.287 |
Token | I |
Token ID | 314 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
axes | +1.992 |
acceler | +1.985 |
OTOS | +1.940 |
ochond | +1.927 |
pollut | +1.851 |
Neg logit contributions | |
util | -3.319 |
onen | -3.288 |
idium | -3.232 |
avorite | -3.202 |
cone | -3.120 |
Token | 'll |
Token ID | 1183 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
axes | +3.971 |
ochond | +3.765 |
acceler | +3.621 |
pollut | +3.591 |
govern | +3.547 |
Neg logit contributions | |
onen | -5.944 |
util | -5.680 |
irtual | -5.613 |
idium | -5.589 |
perties | -5.482 |
Token | Trump |
Token ID | 1301 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
axes | +3.952 |
ochond | +3.768 |
OTOS | +3.686 |
acceler | +3.617 |
opsis | +3.517 |
Neg logit contributions | |
util | -9.402 |
idium | -9.295 |
onen | -9.190 |
avorite | -9.173 |
ilogy | -9.031 |
Token | House |
Token ID | 18102 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
axes | +4.210 |
ochond | +4.175 |
OTOS | +4.092 |
opsis | +3.943 |
acceler | +3.935 |
Neg logit contributions | |
onen | -4.600 |
util | -4.587 |
avorite | -4.441 |
idium | -4.399 |
ilogy | -4.358 |
Token | committee |
Token ID | 5583 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
axes | +2.979 |
ochond | +2.768 |
acceler | +2.708 |
OTOS | +2.683 |
opsis | +2.658 |
Neg logit contributions | |
util | -6.915 |
onen | -6.762 |
illance | -6.598 |
irtual | -6.525 |
hler | -6.464 |
Token | believes |
Token ID | 5804 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
axes | +3.289 |
acceler | +3.273 |
ochond | +3.183 |
OTOS | +3.129 |
opsis | +3.075 |
Neg logit contributions | |
util | -4.052 |
onen | -3.951 |
hler | -3.836 |
idium | -3.803 |
ilogy | -3.731 |
Token | it |
Token ID | 340 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
axes | +2.270 |
ochond | +2.231 |
acceler | +2.201 |
OTOS | +2.116 |
opsis | +2.111 |
Neg logit contributions | |
util | -2.957 |
onen | -2.859 |
idium | -2.812 |
hler | -2.784 |
ilogy | -2.737 |
Token | has |
Token ID | 468 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
acceler | +4.119 |
axes | +3.848 |
smokes | +3.665 |
ochond | +3.422 |
drives | +3.348 |
Neg logit contributions | |
onen | -10.024 |
avorite | -9.812 |
hler | -9.700 |
ilogy | -9.616 |
ussen | -9.442 |
Token | evidence |
Token ID | 2370 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
axes | +4.370 |
acceler | +4.114 |
ochond | +4.084 |
pollut | +3.839 |
fung | +3.791 |
Neg logit contributions | |
hler | -11.931 |
onen | -11.693 |
cone | -11.359 |
ilogy | -11.258 |
perties | -11.250 |
Token | Trump |
Token ID | 1301 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
axes | +2.709 |
ochond | +2.672 |
acceler | +2.574 |
pollut | +2.535 |
OTOS | +2.500 |
Neg logit contributions | |
util | -4.041 |
onen | -3.973 |
idium | -3.874 |
hler | -3.800 |
irtual | -3.712 |
Token | requested |
Token ID | 9167 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
axes | +1.525 |
ochond | +1.437 |
acceler | +1.417 |
pollut | +1.405 |
OTOS | +1.381 |
Neg logit contributions | |
util | -2.132 |
onen | -2.092 |
idium | -2.026 |
irtual | -1.991 |
avorite | -1.985 |
Token | putting |
Token ID | 5137 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
axes | +1.736 |
acceler | +1.664 |
OTOS | +1.598 |
ochond | +1.593 |
pollut | +1.577 |
Neg logit contributions | |
util | -2.638 |
onen | -2.636 |
idium | -2.633 |
hler | -2.564 |
unia | -2.496 |
Token | ally |
Token ID | 12525 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
axes | +2.627 |
ochond | +2.511 |
OTOS | +2.502 |
acceler | +2.466 |
pollut | +2.421 |
Neg logit contributions | |
util | -3.651 |
onen | -3.581 |
idium | -3.483 |
ilogy | -3.354 |
hler | -3.330 |
Token |
|
Token ID | 198 |
Feature activation | -8.66e-02 |
Pos logit contributions | |
axes | +1.562 |
ochond | +1.535 |
pollut | +1.459 |
opsis | +1.457 |
acceler | +1.451 |
Neg logit contributions | |
util | -2.055 |
onen | -2.016 |
idium | -1.969 |
hler | -1.923 |
avorite | -1.878 |
Token |
|
Token ID | 198 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
axes | +0.840 |
ochond | +0.840 |
escription | +0.829 |
pollut | +0.802 |
opsis | +0.797 |
Neg logit contributions | |
util | -0.894 |
onen | -0.863 |
idium | -0.838 |
hler | -0.818 |
cone | -0.803 |
Token | d |
Token ID | 67 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
axes | +3.373 |
ochond | +3.360 |
opsis | +3.211 |
pollut | +3.208 |
OTOS | +3.208 |
Neg logit contributions | |
util | -3.036 |
onen | -3.008 |
idium | -2.927 |
hler | -2.842 |
avorite | -2.796 |
Token | [ |
Token ID | 58 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
util | +0.353 |
onen | +0.342 |
idium | +0.334 |
hler | +0.323 |
cone | +0.316 |
Neg logit contributions | |
axes | -0.350 |
ochond | -0.350 |
OTOS | -0.335 |
pollut | -0.334 |
opsis | -0.333 |
Token | CO |
Token ID | 8220 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
axes | +4.030 |
ochond | +3.979 |
pollut | +3.826 |
opsis | +3.817 |
OTOS | +3.793 |
Neg logit contributions | |
util | -3.834 |
onen | -3.783 |
idium | -3.668 |
hler | -3.565 |
avorite | -3.550 |
Token | 2 |
Token ID | 362 |
Feature activation | -8.32e-01 |
Pos logit contributions | |
util | +0.439 |
onen | +0.428 |
idium | +0.419 |
hler | +0.406 |
cone | +0.397 |
Neg logit contributions | |
axes | -0.426 |
ochond | -0.425 |
OTOS | -0.405 |
opsis | -0.404 |
pollut | -0.403 |
Token | ] |
Token ID | 2361 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
axes | +6.510 |
pollut | +6.389 |
ochond | +6.337 |
acceler | +6.293 |
DAC | +5.955 |
Neg logit contributions | |
onen | -8.888 |
util | -8.626 |
avorite | -8.440 |
ilogy | -8.327 |
idium | -8.296 |
Token | / |
Token ID | 14 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
axes | +4.988 |
ochond | +4.923 |
pollut | +4.723 |
acceler | +4.711 |
OTOS | +4.672 |
Neg logit contributions | |
onen | -5.242 |
util | -5.240 |
idium | -5.027 |
hler | -4.923 |
avorite | -4.897 |
Token | dt |
Token ID | 28664 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
axes | +3.989 |
ochond | +3.965 |
pollut | +3.811 |
opsis | +3.783 |
OTOS | +3.772 |
Neg logit contributions | |
util | -3.864 |
onen | -3.853 |
idium | -3.757 |
hler | -3.598 |
avorite | -3.585 |
Token | = |
Token ID | 796 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
axes | +4.061 |
ochond | +3.988 |
pollut | +3.847 |
acceler | +3.834 |
opsis | +3.813 |
Neg logit contributions | |
util | -4.526 |
onen | -4.520 |
idium | -4.420 |
hler | -4.294 |
avorite | -4.191 |
Token | f |
Token ID | 277 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
axes | +2.243 |
ochond | +2.208 |
pollut | +2.123 |
acceler | +2.113 |
OTOS | +2.094 |
Neg logit contributions | |
util | -2.491 |
onen | -2.444 |
idium | -2.381 |
hler | -2.320 |
avorite | -2.262 |
Token | 2011 |
Token ID | 2813 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
axes | +5.137 |
ochond | +4.618 |
acceler | +4.453 |
opsis | +4.432 |
DAC | +4.392 |
Neg logit contributions | |
util | -9.560 |
idium | -9.354 |
onen | -9.234 |
ilogy | -8.992 |
irtual | -8.923 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
ochond | +0.210 |
axes | +0.210 |
escription | +0.200 |
opsis | +0.200 |
OTOS | +0.199 |
Neg logit contributions | |
util | -0.223 |
onen | -0.217 |
idium | -0.212 |
hler | -0.206 |
cone | -0.201 |
Token | 2 |
Token ID | 362 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
util | +1.546 |
onen | +1.506 |
idium | +1.463 |
hler | +1.427 |
cone | +1.400 |
Neg logit contributions | |
ochond | -1.395 |
axes | -1.385 |
opsis | -1.323 |
escription | -1.319 |
pollut | -1.319 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
axes | +3.617 |
ochond | +3.357 |
pollut | +3.161 |
opsis | +3.123 |
acceler | +3.077 |
Neg logit contributions | |
onen | -6.526 |
util | -6.490 |
idium | -6.307 |
hler | -6.230 |
cone | -6.038 |
Token | 7 |
Token ID | 767 |
Feature activation | +9.12e-03 |
Pos logit contributions | |
util | +0.604 |
onen | +0.586 |
idium | +0.572 |
hler | +0.556 |
cone | +0.543 |
Neg logit contributions | |
ochond | -0.577 |
axes | -0.576 |
escription | -0.554 |
opsis | -0.549 |
pollut | -0.547 |
Token | 0 |
Token ID | 657 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
util | +0.099 |
onen | +0.096 |
idium | +0.095 |
hler | +0.092 |
cone | +0.090 |
Neg logit contributions | |
axes | -0.082 |
ochond | -0.082 |
OTOS | -0.078 |
opsis | -0.078 |
pollut | -0.077 |
Token | 2013 |
Token ID | 2211 |
Feature activation | -5.80e-02 |
Pos logit contributions | |
ochond | +5.011 |
axes | +5.011 |
pollut | +4.943 |
escription | +4.923 |
OTOS | +4.786 |
Neg logit contributions | |
util | -9.904 |
idium | -9.814 |
onen | -9.542 |
unia | -9.344 |
cone | -9.336 |
Token | 3 |
Token ID | 513 |
Feature activation | +9.21e-02 |
Pos logit contributions | |
axes | +0.541 |
ochond | +0.540 |
OTOS | +0.513 |
opsis | +0.512 |
pollut | +0.511 |
Neg logit contributions | |
util | -0.612 |
onen | -0.597 |
idium | -0.584 |
hler | -0.567 |
cone | -0.555 |
Token | 0 |
Token ID | 657 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
util | +0.976 |
onen | +0.949 |
idium | +0.926 |
hler | +0.903 |
cone | +0.885 |
Neg logit contributions | |
ochond | -0.855 |
axes | -0.852 |
opsis | -0.810 |
OTOS | -0.808 |
pollut | -0.808 |
Token | 2014 |
Token ID | 1946 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
axes | +4.659 |
ochond | +4.617 |
OTOS | +4.533 |
acceler | +4.421 |
pollut | +4.414 |
Neg logit contributions | |
util | -5.568 |
onen | -5.302 |
hler | -5.211 |
idium | -5.198 |
illance | -5.014 |
Token | 8 |
Token ID | 807 |
Feature activation | -1.05e-03 |
Pos logit contributions | |
axes | +0.146 |
ochond | +0.146 |
opsis | +0.139 |
OTOS | +0.139 |
pollut | +0.138 |
Neg logit contributions | |
util | -0.165 |
onen | -0.161 |
idium | -0.157 |
hler | -0.153 |
cone | -0.150 |
Token | the |
Token ID | 262 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
axes | +3.718 |
ochond | +3.676 |
acceler | +3.475 |
opsis | +3.463 |
OTOS | +3.442 |
Neg logit contributions | |
util | -5.522 |
onen | -5.434 |
idium | -5.389 |
hler | -5.210 |
avorite | -5.181 |
Token | argument |
Token ID | 4578 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
axes | +2.367 |
ochond | +2.344 |
opsis | +2.186 |
pollut | +2.183 |
acceler | +2.180 |
Neg logit contributions | |
util | -4.431 |
onen | -4.348 |
idium | -4.283 |
hler | -4.174 |
cone | -4.109 |
Token | parse |
Token ID | 21136 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
axes | +2.743 |
ochond | +2.617 |
opsis | +2.505 |
pollut | +2.490 |
acceler | +2.489 |
Neg logit contributions | |
util | -5.007 |
onen | -5.002 |
idium | -4.928 |
hler | -4.792 |
avorite | -4.731 |
Token | and |
Token ID | 290 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
axes | +3.123 |
ochond | +3.098 |
OTOS | +2.921 |
acceler | +2.921 |
opsis | +2.916 |
Neg logit contributions | |
util | -4.428 |
onen | -4.344 |
idium | -4.298 |
hler | -4.152 |
avorite | -4.094 |
Token | parse |
Token ID | 21136 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
axes | +3.628 |
ochond | +3.433 |
opsis | +3.376 |
acceler | +3.302 |
pollut | +3.283 |
Neg logit contributions | |
util | -7.243 |
onen | -7.206 |
idium | -7.169 |
hler | -6.937 |
avorite | -6.888 |
Token | the |
Token ID | 262 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
axes | +2.918 |
ochond | +2.901 |
OTOS | +2.741 |
opsis | +2.736 |
acceler | +2.730 |
Neg logit contributions | |
util | -3.977 |
onen | -3.898 |
idium | -3.829 |
hler | -3.718 |
cone | -3.649 |
Token | arguments |
Token ID | 7159 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
axes | +5.031 |
acceler | +4.273 |
ochond | +4.263 |
offsets | +4.164 |
OTOS | +4.064 |
Neg logit contributions | |
onen | -11.193 |
util | -11.162 |
idium | -10.964 |
avorite | -10.791 |
irtual | -10.755 |
Token | ap |
Token ID | 2471 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
axes | +1.150 |
ochond | +1.035 |
pollut | +0.997 |
acceler | +0.989 |
opsis | +0.955 |
Neg logit contributions | |
onen | -3.492 |
util | -3.486 |
idium | -3.479 |
hler | -3.357 |
irtual | -3.285 |
Token | = |
Token ID | 796 |
Feature activation | -7.71e-02 |
Pos logit contributions | |
util | +2.689 |
onen | +2.492 |
hler | +2.446 |
idium | +2.415 |
kov | +2.297 |
Neg logit contributions | |
escription | -3.209 |
pollut | -3.022 |
axes | -3.014 |
ochond | -2.983 |
acceler | -2.892 |
Token | arg |
Token ID | 1822 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
ochond | +0.589 |
axes | +0.582 |
OTOS | +0.559 |
escription | +0.558 |
opsis | +0.550 |
Neg logit contributions | |
util | -0.945 |
onen | -0.920 |
idium | -0.904 |
hler | -0.884 |
cone | -0.869 |
Token | parse |
Token ID | 29572 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
axes | +2.232 |
ochond | +2.221 |
OTOS | +2.135 |
pollut | +2.129 |
opsis | +2.124 |
Neg logit contributions | |
util | -1.848 |
onen | -1.790 |
idium | -1.747 |
hler | -1.687 |
cone | -1.646 |
Token | Trump |
Token ID | 1301 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
axes | +3.872 |
ochond | +3.704 |
OTOS | +3.689 |
acceler | +3.506 |
opsis | +3.484 |
Neg logit contributions | |
util | -9.158 |
onen | -9.017 |
idium | -9.010 |
avorite | -8.969 |
hler | -8.835 |
Token | House |
Token ID | 18102 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
axes | +4.196 |
ochond | +4.164 |
OTOS | +4.106 |
opsis | +3.927 |
acceler | +3.872 |
Neg logit contributions | |
onen | -4.726 |
util | -4.682 |
avorite | -4.610 |
ilogy | -4.526 |
idium | -4.488 |
Token | committee |
Token ID | 5583 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
axes | +3.038 |
acceler | +2.750 |
ochond | +2.746 |
OTOS | +2.683 |
pollut | +2.613 |
Neg logit contributions | |
util | -7.263 |
onen | -7.083 |
illance | -6.925 |
irtual | -6.869 |
avorite | -6.855 |
Token | believes |
Token ID | 5804 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
axes | +2.594 |
acceler | +2.540 |
ochond | +2.505 |
OTOS | +2.462 |
opsis | +2.421 |
Neg logit contributions | |
util | -3.023 |
onen | -2.957 |
hler | -2.834 |
idium | -2.824 |
cone | -2.773 |
Token | it |
Token ID | 340 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
axes | +2.263 |
ochond | +2.230 |
acceler | +2.169 |
OTOS | +2.116 |
pollut | +2.105 |
Neg logit contributions | |
util | -2.838 |
onen | -2.758 |
idium | -2.711 |
hler | -2.669 |
ilogy | -2.613 |
Token | has |
Token ID | 468 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
acceler | +3.735 |
axes | +3.589 |
smokes | +3.234 |
ochond | +3.173 |
chops | +2.932 |
Neg logit contributions | |
avorite | -10.252 |
onen | -10.194 |
hler | -10.087 |
ilogy | -9.738 |
irtual | -9.733 |
Token | evidence |
Token ID | 2370 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
axes | +4.241 |
ochond | +4.051 |
acceler | +3.999 |
pollut | +3.876 |
fung | +3.830 |
Neg logit contributions | |
hler | -11.726 |
onen | -11.474 |
cone | -11.218 |
util | -10.966 |
perties | -10.927 |
Token | Trump |
Token ID | 1301 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
axes | +2.752 |
ochond | +2.715 |
acceler | +2.607 |
pollut | +2.558 |
OTOS | +2.536 |
Neg logit contributions | |
util | -4.370 |
onen | -4.280 |
idium | -4.206 |
hler | -4.092 |
irtual | -4.040 |
Token | requested |
Token ID | 9167 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
axes | +1.903 |
ochond | +1.770 |
pollut | +1.741 |
opsis | +1.727 |
acceler | +1.723 |
Neg logit contributions | |
util | -2.787 |
onen | -2.729 |
irtual | -2.624 |
idium | -2.606 |
cone | -2.579 |
Token | putting |
Token ID | 5137 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
axes | +1.740 |
acceler | +1.662 |
pollut | +1.562 |
ochond | +1.561 |
OTOS | +1.549 |
Neg logit contributions | |
idium | -3.155 |
onen | -3.153 |
util | -3.147 |
hler | -3.070 |
unia | -3.004 |
Token | ally |
Token ID | 12525 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
axes | +2.678 |
ochond | +2.582 |
OTOS | +2.545 |
acceler | +2.504 |
pollut | +2.473 |
Neg logit contributions | |
util | -3.558 |
onen | -3.473 |
idium | -3.394 |
hler | -3.255 |
ilogy | -3.247 |
Token | s |
Token ID | 264 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
axes | +4.238 |
OTOS | +4.159 |
acceler | +4.110 |
pollut | +3.944 |
ochond | +3.914 |
Neg logit contributions | |
idium | -7.700 |
util | -7.661 |
onen | -7.647 |
ilogy | -7.613 |
cone | -7.568 |
Token | . |
Token ID | 13 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
axes | +1.527 |
ochond | +1.522 |
pollut | +1.448 |
OTOS | +1.447 |
escription | +1.444 |
Neg logit contributions | |
util | -1.670 |
onen | -1.622 |
idium | -1.587 |
hler | -1.543 |
cone | -1.508 |
Token | t |
Token ID | 83 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
ochond | +3.226 |
axes | +3.203 |
opsis | +3.055 |
OTOS | +3.038 |
acceler | +3.029 |
Neg logit contributions | |
util | -3.744 |
onen | -3.707 |
idium | -3.667 |
avorite | -3.548 |
hler | -3.506 |
Token | . |
Token ID | 13 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
axes | +2.870 |
ochond | +2.868 |
OTOS | +2.739 |
opsis | +2.726 |
acceler | +2.701 |
Neg logit contributions | |
util | -3.666 |
onen | -3.622 |
idium | -3.585 |
avorite | -3.501 |
hler | -3.443 |
Token | I |
Token ID | 314 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
axes | +2.425 |
ochond | +2.365 |
OTOS | +2.332 |
acceler | +2.318 |
pollut | +2.296 |
Neg logit contributions | |
util | -3.612 |
onen | -3.595 |
idium | -3.530 |
avorite | -3.472 |
hler | -3.429 |
Token | TA |
Token ID | 5603 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
util | +0.244 |
onen | +0.231 |
idium | +0.228 |
hler | +0.222 |
cone | +0.217 |
Neg logit contributions | |
ochond | -0.283 |
axes | -0.283 |
escription | -0.278 |
pollut | -0.273 |
opsis | -0.267 |
Token | 11 |
Token ID | 1367 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
axes | +4.769 |
OTOS | +4.218 |
opsis | +4.084 |
pollut | +4.038 |
acceler | +3.972 |
Neg logit contributions | |
idium | -10.480 |
util | -9.940 |
onen | -9.833 |
ilogy | -9.757 |
unia | -9.607 |
Token | Matte |
Token ID | 38789 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
util | +1.211 |
onen | +1.181 |
idium | +1.154 |
hler | +1.119 |
cone | +1.091 |
Neg logit contributions | |
ochond | -1.170 |
axes | -1.168 |
pollut | -1.111 |
opsis | -1.109 |
OTOS | -1.106 |
Token | o |
Token ID | 78 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
axes | +1.823 |
ochond | +1.819 |
OTOS | +1.736 |
opsis | +1.732 |
pollut | +1.731 |
Neg logit contributions | |
util | -1.732 |
onen | -1.687 |
idium | -1.652 |
hler | -1.597 |
cone | -1.559 |
Token | Trent |
Token ID | 24269 |
Feature activation | -5.76e-02 |
Pos logit contributions | |
axes | +1.583 |
ochond | +1.554 |
opsis | +1.485 |
pollut | +1.482 |
acceler | +1.475 |
Neg logit contributions | |
util | -2.545 |
onen | -2.496 |
idium | -2.462 |
hler | -2.392 |
cone | -2.364 |
Token | in |
Token ID | 259 |
Feature activation | -8.64e-02 |
Pos logit contributions | |
axes | +0.380 |
ochond | +0.366 |
OTOS | +0.357 |
pollut | +0.347 |
opsis | +0.338 |
Neg logit contributions | |
util | -0.782 |
onen | -0.775 |
idium | -0.742 |
ussen | -0.729 |
cone | -0.728 |
Token | two |
Token ID | 734 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
util | +0.682 |
onen | +0.667 |
idium | +0.654 |
hler | +0.632 |
cone | +0.621 |
Neg logit contributions | |
ochond | -0.599 |
axes | -0.595 |
OTOS | -0.570 |
opsis | -0.569 |
pollut | -0.564 |
Token | quantum |
Token ID | 14821 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
axes | +1.107 |
ochond | +1.083 |
acceler | +1.039 |
pollut | +1.033 |
OTOS | +1.024 |
Neg logit contributions | |
util | -1.363 |
onen | -1.330 |
idium | -1.307 |
hler | -1.267 |
cone | -1.238 |
Token | states |
Token ID | 2585 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
util | +0.794 |
onen | +0.775 |
idium | +0.760 |
hler | +0.738 |
cone | +0.724 |
Neg logit contributions | |
ochond | -0.633 |
axes | -0.620 |
opsis | -0.600 |
OTOS | -0.597 |
escription | -0.592 |
Token | during |
Token ID | 1141 |
Feature activation | -6.38e-02 |
Pos logit contributions | |
util | +0.742 |
onen | +0.724 |
idium | +0.709 |
hler | +0.688 |
cone | +0.675 |
Neg logit contributions | |
ochond | -0.673 |
axes | -0.667 |
OTOS | -0.642 |
opsis | -0.640 |
pollut | -0.635 |
Token | the |
Token ID | 262 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
axes | +0.543 |
ochond | +0.539 |
OTOS | +0.510 |
pollut | +0.509 |
opsis | +0.509 |
Neg logit contributions | |
util | -0.725 |
onen | -0.709 |
idium | -0.697 |
hler | -0.678 |
cone | -0.664 |
Token | pseud |
Token ID | 25038 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
util | +0.251 |
onen | +0.245 |
idium | +0.241 |
hler | +0.233 |
cone | +0.229 |
Neg logit contributions | |
ochond | -0.199 |
axes | -0.198 |
OTOS | -0.188 |
opsis | -0.188 |
pollut | -0.186 |
Token | og |
Token ID | 519 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ochond | +5.490 |
opsis | +4.918 |
axes | +4.774 |
OTOS | +4.599 |
pollut | +4.572 |
Neg logit contributions | |
util | -9.845 |
idium | -9.599 |
onen | -9.571 |
avorite | -9.527 |
hler | -9.321 |
Token | ap |
Token ID | 499 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
axes | +1.754 |
ochond | +1.728 |
OTOS | +1.687 |
escription | +1.680 |
pollut | +1.674 |
Neg logit contributions | |
util | -1.215 |
onen | -1.179 |
idium | -1.126 |
hler | -1.089 |
cone | -1.075 |
Token | , |
Token ID | 11 |
Feature activation | +8.92e-02 |
Pos logit contributions | |
axes | +1.286 |
ochond | +1.274 |
acceler | +1.214 |
pollut | +1.209 |
OTOS | +1.202 |
Neg logit contributions | |
util | -1.554 |
onen | -1.518 |
idium | -1.490 |
hler | -1.449 |
cone | -1.410 |
Token | one |
Token ID | 530 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
util | +0.930 |
onen | +0.907 |
idium | +0.886 |
hler | +0.862 |
cone | +0.846 |
Neg logit contributions | |
ochond | -0.840 |
axes | -0.830 |
opsis | -0.801 |
OTOS | -0.800 |
escription | -0.792 |
Token | of |
Token ID | 286 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
util | +0.625 |
onen | +0.612 |
idium | +0.600 |
hler | +0.580 |
cone | +0.572 |
Neg logit contributions | |
ochond | -0.525 |
axes | -0.521 |
OTOS | -0.499 |
opsis | -0.498 |
escription | -0.493 |
Token |
|
Token ID | 198 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
axes | +3.213 |
ochond | +3.185 |
OTOS | +3.042 |
acceler | +3.020 |
opsis | +3.018 |
Neg logit contributions | |
util | -4.086 |
onen | -4.008 |
idium | -3.932 |
hler | -3.818 |
cone | -3.748 |
Token |
|
Token ID | 198 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
axes | +2.496 |
ochond | +2.486 |
OTOS | +2.363 |
opsis | +2.352 |
acceler | +2.345 |
Neg logit contributions | |
util | -3.170 |
onen | -3.110 |
idium | -3.067 |
hler | -2.965 |
avorite | -2.916 |
Token | Facebook |
Token ID | 12025 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
axes | +2.466 |
ochond | +2.347 |
acceler | +2.279 |
opsis | +2.192 |
OTOS | +2.184 |
Neg logit contributions | |
util | -4.839 |
idium | -4.815 |
onen | -4.732 |
irtual | -4.719 |
hler | -4.616 |
Token |
|
Token ID | 198 |
Feature activation | -9.76e-02 |
Pos logit contributions | |
axes | +4.285 |
ochond | +4.282 |
OTOS | +4.179 |
acceler | +4.080 |
opsis | +4.073 |
Neg logit contributions | |
util | -6.829 |
idium | -6.738 |
onen | -6.652 |
avorite | -6.643 |
hler | -6.468 |
Token |
|
Token ID | 198 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
axes | +0.947 |
ochond | +0.946 |
escription | +0.933 |
pollut | +0.907 |
opsis | +0.896 |
Neg logit contributions | |
util | -1.007 |
onen | -0.975 |
idium | -0.943 |
hler | -0.924 |
cone | -0.903 |
Token | St |
Token ID | 1273 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
axes | +3.312 |
ochond | +3.264 |
OTOS | +3.140 |
opsis | +3.128 |
acceler | +3.102 |
Neg logit contributions | |
util | -3.359 |
idium | -3.259 |
onen | -3.233 |
hler | -3.117 |
irtual | -3.065 |
Token | umble |
Token ID | 10344 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
axes | +3.162 |
ochond | +2.981 |
ait | +2.897 |
opsis | +2.870 |
yn | +2.851 |
Neg logit contributions | |
�� | -11.548 |
util | -11.538 |
hler | -11.450 |
onen | -11.425 |
cone | -11.425 |
Token | Upon |
Token ID | 23792 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
axes | +2.839 |
ochond | +2.788 |
opsis | +2.696 |
acceler | +2.679 |
OTOS | +2.657 |
Neg logit contributions | |
util | -4.083 |
onen | -3.998 |
idium | -3.906 |
hler | -3.869 |
avorite | -3.757 |
Token | What |
Token ID | 1867 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
axes | +2.263 |
ochond | +2.220 |
acceler | +2.135 |
opsis | +2.134 |
pollut | +2.120 |
Neg logit contributions | |
util | -3.020 |
onen | -2.923 |
idium | -2.905 |
hler | -2.830 |
cone | -2.793 |
Token | are |
Token ID | 389 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
axes | +2.973 |
opsis | +2.846 |
OTOS | +2.798 |
ochond | +2.756 |
pollut | +2.748 |
Neg logit contributions | |
util | -4.806 |
onen | -4.769 |
idium | -4.710 |
hler | -4.662 |
cone | -4.545 |
Token | these |
Token ID | 777 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
axes | +1.106 |
ochond | +1.100 |
acceler | +1.036 |
OTOS | +1.035 |
opsis | +1.035 |
Neg logit contributions | |
util | -1.663 |
onen | -1.623 |
idium | -1.608 |
hler | -1.562 |
cone | -1.536 |
Token | Rodham |
Token ID | 41848 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
ochond | +1.457 |
OTOS | +1.376 |
axes | +1.337 |
acceler | +1.268 |
govern | +1.230 |
Neg logit contributions | |
idium | -7.581 |
util | -7.563 |
onen | -7.491 |
avorite | -7.457 |
irtual | -7.222 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
axes | +2.758 |
ochond | +2.756 |
OTOS | +2.589 |
acceler | +2.577 |
pollut | +2.558 |
Neg logit contributions | |
util | -4.678 |
onen | -4.607 |
idium | -4.546 |
hler | -4.431 |
avorite | -4.411 |
Token | Sanders |
Token ID | 26747 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
axes | +0.312 |
ochond | +0.309 |
OTOS | +0.295 |
acceler | +0.293 |
opsis | +0.292 |
Neg logit contributions | |
util | -0.362 |
onen | -0.356 |
idium | -0.348 |
hler | -0.339 |
avorite | -0.334 |
Token | : |
Token ID | 25 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
axes | +1.338 |
ochond | +1.307 |
acceler | +1.282 |
pollut | +1.249 |
OTOS | +1.241 |
Neg logit contributions | |
util | -1.854 |
onen | -1.802 |
idium | -1.771 |
hler | -1.734 |
avorite | -1.697 |
Token | ' |
Token ID | 705 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
axes | +1.324 |
acceler | +1.274 |
ochond | +1.222 |
OTOS | +1.211 |
opsis | +1.182 |
Neg logit contributions | |
util | -2.806 |
onen | -2.723 |
idium | -2.712 |
hler | -2.660 |
avorite | -2.657 |
Token | I |
Token ID | 40 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
axes | +5.175 |
ochond | +4.740 |
acceler | +4.596 |
bec | +4.126 |
offsets | +4.095 |
Neg logit contributions | |
avorite | -9.375 |
util | -9.269 |
unia | -9.118 |
onen | -9.094 |
idium | -9.085 |
Token | fully |
Token ID | 3938 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
axes | +5.595 |
ochond | +4.950 |
govern | +4.937 |
acceler | +4.538 |
pollut | +4.510 |
Neg logit contributions | |
idium | -9.931 |
onen | -9.806 |
irtual | -9.800 |
util | -9.750 |
cone | -9.610 |
Token | expect |
Token ID | 1607 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
axes | +3.479 |
ochond | +3.304 |
acceler | +3.235 |
pollut | +3.130 |
OTOS | +3.068 |
Neg logit contributions | |
util | -5.143 |
idium | -5.110 |
onen | -5.102 |
hler | -4.878 |
ilogy | -4.827 |
Token | ' |
Token ID | 6 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
axes | +2.307 |
pollut | +2.095 |
acceler | +2.083 |
ochond | +2.078 |
opsis | +2.065 |
Neg logit contributions | |
util | -3.308 |
onen | -3.201 |
illance | -3.139 |
idium | -3.131 |
irtual | -3.046 |
Token | fair |
Token ID | 3148 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
ochond | +0.152 |
axes | +0.150 |
escription | +0.145 |
opsis | +0.145 |
pollut | +0.141 |
Neg logit contributions | |
util | -0.251 |
onen | -0.247 |
idium | -0.240 |
hler | -0.238 |
cone | -0.232 |
Token | treatment |
Token ID | 3513 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
axes | +1.468 |
ochond | +1.436 |
OTOS | +1.366 |
opsis | +1.363 |
acceler | +1.361 |
Neg logit contributions | |
util | -2.242 |
onen | -2.193 |
idium | -2.172 |
hler | -2.101 |
cone | -2.073 |
Token | [ |
Token ID | 58 |
Feature activation | -8.61e-03 |
Pos logit contributions | |
axes | +1.793 |
ochond | +1.774 |
opsis | +1.707 |
OTOS | +1.703 |
acceler | +1.688 |
Neg logit contributions | |
util | -1.836 |
onen | -1.813 |
idium | -1.772 |
hler | -1.716 |
cone | -1.673 |
Token | index |
Token ID | 6376 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
axes | +0.091 |
ochond | +0.091 |
OTOS | +0.087 |
opsis | +0.087 |
pollut | +0.087 |
Neg logit contributions | |
util | -0.080 |
onen | -0.078 |
idium | -0.076 |
hler | -0.073 |
cone | -0.071 |
Token | State |
Token ID | 9012 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
axes | +3.068 |
ochond | +3.067 |
OTOS | +2.949 |
opsis | +2.926 |
acceler | +2.882 |
Neg logit contributions | |
util | -2.598 |
onen | -2.576 |
idium | -2.535 |
hler | -2.460 |
avorite | -2.370 |
Token | [ |
Token ID | 58 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
util | +1.279 |
onen | +1.249 |
idium | +1.225 |
hler | +1.192 |
cone | +1.168 |
Neg logit contributions | |
ochond | -0.968 |
axes | -0.968 |
pollut | -0.914 |
opsis | -0.913 |
OTOS | -0.912 |
Token | Keys |
Token ID | 40729 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
axes | +2.806 |
ochond | +2.777 |
OTOS | +2.659 |
acceler | +2.656 |
opsis | +2.643 |
Neg logit contributions | |
util | -2.426 |
onen | -2.356 |
idium | -2.333 |
hler | -2.260 |
avorite | -2.224 |
Token | [ |
Token ID | 58 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
util | +2.192 |
onen | +2.124 |
idium | +2.068 |
hler | +2.003 |
cone | +1.966 |
Neg logit contributions | |
ochond | -2.281 |
axes | -2.274 |
pollut | -2.181 |
OTOS | -2.173 |
opsis | -2.172 |
Token | step |
Token ID | 9662 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
axes | +6.364 |
ochond | +6.338 |
escription | +6.062 |
acceler | +5.941 |
opsis | +5.916 |
Neg logit contributions | |
idium | -7.626 |
util | -7.573 |
avorite | -7.530 |
onen | -7.427 |
hler | -7.309 |
Token | New |
Token ID | 3791 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
util | +0.530 |
onen | +0.515 |
idium | +0.503 |
hler | +0.482 |
cone | +0.468 |
Neg logit contributions | |
axes | -0.768 |
ochond | -0.767 |
OTOS | -0.738 |
opsis | -0.735 |
pollut | -0.732 |
Token | ][ |
Token ID | 7131 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
axes | +0.472 |
ochond | +0.469 |
opsis | +0.443 |
OTOS | +0.442 |
acceler | +0.441 |
Neg logit contributions | |
util | -0.581 |
onen | -0.569 |
idium | -0.562 |
hler | -0.543 |
cone | -0.532 |
Token | [ |
Token ID | 58 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
axes | +4.060 |
ochond | +3.963 |
acceler | +3.817 |
OTOS | +3.775 |
escription | +3.765 |
Neg logit contributions | |
util | -3.733 |
idium | -3.633 |
onen | -3.628 |
avorite | -3.511 |
hler | -3.500 |
Token | i |
Token ID | 72 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
axes | +4.623 |
ochond | +4.524 |
acceler | +4.329 |
opsis | +4.319 |
OTOS | +4.305 |
Neg logit contributions | |
util | -4.120 |
onen | -4.009 |
idium | -3.985 |
avorite | -3.873 |
hler | -3.872 |
Token |
|
Token ID | 198 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
axes | +4.506 |
OTOS | +4.319 |
DAC | +4.176 |
acceler | +4.146 |
ochond | +4.091 |
Neg logit contributions | |
idium | -8.495 |
onen | -8.472 |
util | -8.462 |
irtual | -8.233 |
ussen | -8.124 |
Token |
|
Token ID | 198 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
axes | +3.620 |
ochond | +3.605 |
OTOS | +3.458 |
opsis | +3.399 |
acceler | +3.390 |
Neg logit contributions | |
avorite | -5.732 |
onen | -5.703 |
util | -5.698 |
idium | -5.697 |
irtual | -5.591 |
Token | 14 |
Token ID | 1415 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
OTOS | +6.082 |
axes | +6.042 |
ochond | +5.949 |
opsis | +5.789 |
acceler | +5.551 |
Neg logit contributions | |
onen | -6.841 |
idium | -6.753 |
util | -6.676 |
irtual | -6.511 |
ilogy | -6.434 |
Token | Recommend |
Token ID | 30361 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
axes | +3.133 |
ochond | +2.985 |
OTOS | +2.969 |
pollut | +2.939 |
acceler | +2.887 |
Neg logit contributions | |
util | -4.171 |
idium | -4.131 |
onen | -4.101 |
hler | -3.892 |
ilogy | -3.887 |
Token |
|
Token ID | 198 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
axes | +3.718 |
ochond | +3.651 |
OTOS | +3.503 |
opsis | +3.481 |
acceler | +3.427 |
Neg logit contributions | |
util | -5.480 |
onen | -5.367 |
idium | -5.350 |
avorite | -5.204 |
irtual | -5.145 |
Token |
|
Token ID | 198 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
axes | +3.520 |
ochond | +3.502 |
OTOS | +3.344 |
opsis | +3.299 |
acceler | +3.288 |
Neg logit contributions | |
util | -5.188 |
onen | -5.161 |
idium | -5.146 |
avorite | -5.107 |
irtual | -4.971 |
Token | Recommend |
Token ID | 41248 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
OTOS | +6.036 |
axes | +5.703 |
ochond | +5.421 |
opsis | +5.413 |
DAC | +5.332 |
Neg logit contributions | |
onen | -8.866 |
idium | -8.863 |
util | -8.588 |
irtual | -8.448 |
ussen | -8.396 |
Token | Share |
Token ID | 8734 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
axes | +3.162 |
opsis | +2.871 |
ochond | +2.764 |
DAC | +2.711 |
OTOS | +2.688 |
Neg logit contributions | |
util | -7.861 |
idium | -7.713 |
onen | -7.612 |
irtual | -7.484 |
hler | -7.353 |
Token | this |
Token ID | 428 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
axes | +3.265 |
ochond | +3.196 |
opsis | +3.085 |
acceler | +3.021 |
OTOS | +2.998 |
Neg logit contributions | |
util | -5.350 |
onen | -5.280 |
idium | -5.209 |
hler | -5.038 |
cone | -4.969 |
Token | comment |
Token ID | 2912 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
axes | +3.341 |
acceler | +2.977 |
OTOS | +2.970 |
pollut | +2.914 |
DAC | +2.899 |
Neg logit contributions | |
onen | -8.598 |
idium | -8.594 |
util | -8.523 |
avorite | -8.372 |
hler | -8.169 |
Token | on |
Token ID | 319 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
axes | +1.576 |
ochond | +1.531 |
acceler | +1.492 |
OTOS | +1.485 |
pollut | +1.479 |
Neg logit contributions | |
util | -2.115 |
idium | -2.073 |
onen | -2.065 |
hler | -1.993 |
avorite | -1.951 |
Token | required |
Token ID | 2672 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
axes | +0.210 |
ochond | +0.200 |
pollut | +0.195 |
acceler | +0.194 |
OTOS | +0.190 |
Neg logit contributions | |
util | -0.269 |
onen | -0.267 |
idium | -0.261 |
hler | -0.253 |
irtual | -0.249 |
Token | = |
Token ID | 28 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
ochond | +0.211 |
axes | +0.211 |
escription | +0.209 |
pollut | +0.203 |
acceler | +0.200 |
Neg logit contributions | |
util | -0.281 |
onen | -0.270 |
idium | -0.263 |
hler | -0.260 |
cone | -0.254 |
Token | True |
Token ID | 17821 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
util | +0.209 |
onen | +0.199 |
idium | +0.190 |
hler | +0.183 |
cone | +0.178 |
Neg logit contributions | |
ochond | -0.357 |
escription | -0.356 |
axes | -0.353 |
pollut | -0.346 |
opsis | -0.342 |
Token | , |
Token ID | 11 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
util | +4.328 |
onen | +3.921 |
hler | +3.680 |
hey | +3.558 |
kov | +3.528 |
Neg logit contributions | |
escription | -8.189 |
dilig | -7.571 |
subsequ | -7.453 |
ochond | -7.432 |
pollut | -7.309 |
Token | help |
Token ID | 1037 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
ochond | +0.272 |
axes | +0.263 |
escription | +0.258 |
OTOS | +0.258 |
opsis | +0.255 |
Neg logit contributions | |
util | -0.259 |
onen | -0.248 |
hler | -0.235 |
idium | -0.235 |
cone | -0.225 |
Token | =" |
Token ID | 2625 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
ochond | +0.195 |
axes | +0.195 |
escription | +0.190 |
pollut | +0.187 |
acceler | +0.183 |
Neg logit contributions | |
util | -0.306 |
onen | -0.296 |
idium | -0.289 |
hler | -0.283 |
cone | -0.276 |
Token | path |
Token ID | 6978 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
axes | +5.681 |
ochond | +5.575 |
opsis | +5.154 |
pollut | +5.111 |
OTOS | +5.099 |
Neg logit contributions | |
avorite | -9.042 |
idium | -8.947 |
onen | -8.716 |
util | -8.710 |
ilogy | -8.552 |
Token | to |
Token ID | 284 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
axes | +3.859 |
ochond | +3.822 |
acceler | +3.588 |
OTOS | +3.579 |
opsis | +3.572 |
Neg logit contributions | |
util | -6.292 |
onen | -6.210 |
idium | -6.181 |
avorite | -6.021 |
hler | -5.993 |
Token | images |
Token ID | 4263 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
axes | +2.427 |
ochond | +2.380 |
OTOS | +2.264 |
acceler | +2.249 |
pollut | +2.243 |
Neg logit contributions | |
util | -3.762 |
onen | -3.697 |
idium | -3.635 |
hler | -3.545 |
cone | -3.483 |
Token | directory |
Token ID | 8619 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
ochond | +0.196 |
axes | +0.189 |
escription | +0.188 |
OTOS | +0.185 |
opsis | +0.184 |
Neg logit contributions | |
util | -0.215 |
onen | -0.206 |
idium | -0.202 |
hler | -0.195 |
cone | -0.195 |
Token | ") |
Token ID | 4943 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
ochond | +1.100 |
axes | +1.097 |
pollut | +1.050 |
OTOS | +1.050 |
escription | +1.049 |
Neg logit contributions | |
util | -1.158 |
onen | -1.121 |
idium | -1.096 |
hler | -1.068 |
cone | -1.036 |
Token | ' |
Token ID | 6 |
Feature activation | +8.11e-02 |
Pos logit contributions | |
util | +1.393 |
idium | +1.351 |
hler | +1.290 |
cone | +1.278 |
onen | +1.277 |
Neg logit contributions | |
ochond | -1.618 |
OTOS | -1.574 |
axes | -1.559 |
escription | -1.525 |
opsis | -1.508 |
Token | 2016 |
Token ID | 1584 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
util | +0.922 |
onen | +0.913 |
idium | +0.899 |
avorite | +0.855 |
hler | +0.850 |
Neg logit contributions | |
axes | -0.701 |
ochond | -0.661 |
pollut | -0.657 |
acceler | -0.656 |
OTOS | -0.635 |
Token | primary |
Token ID | 4165 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
axes | +2.653 |
pollut | +2.553 |
acceler | +2.534 |
opsis | +2.475 |
pickup | +2.463 |
Neg logit contributions | |
util | -2.970 |
onen | -2.890 |
idium | -2.862 |
avorite | -2.751 |
irtual | -2.750 |
Token | Sanders |
Token ID | 5831 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
axes | +3.381 |
acceler | +3.184 |
opsis | +3.136 |
DAC | +3.097 |
pollut | +3.092 |
Neg logit contributions | |
util | -4.100 |
onen | -4.013 |
idium | -3.883 |
irtual | -3.857 |
avorite | -3.725 |
Token | : |
Token ID | 25 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
axes | +1.090 |
acceler | +1.017 |
ochond | +1.007 |
pollut | +0.992 |
OTOS | +0.965 |
Neg logit contributions | |
util | -1.810 |
onen | -1.767 |
idium | -1.717 |
hler | -1.708 |
avorite | -1.685 |
Token | ' |
Token ID | 705 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
axes | +1.958 |
acceler | +1.878 |
ochond | +1.769 |
opsis | +1.765 |
pollut | +1.746 |
Neg logit contributions | |
util | -4.671 |
onen | -4.573 |
avorite | -4.474 |
idium | -4.458 |
cone | -4.449 |
Token | Damn |
Token ID | 43343 |
Feature activation | -6.52e-02 |
Pos logit contributions | |
axes | +6.171 |
acceler | +5.521 |
ochond | +5.335 |
yn | +5.287 |
ait | +5.181 |
Neg logit contributions | |
avorite | -9.402 |
util | -8.987 |
onen | -8.789 |
unia | -8.725 |
idium | -8.552 |
Token | right |
Token ID | 826 |
Feature activation | -7.17e-02 |
Pos logit contributions | |
axes | +0.581 |
ochond | +0.575 |
pollut | +0.540 |
acceler | +0.540 |
opsis | +0.539 |
Neg logit contributions | |
util | -0.720 |
onen | -0.703 |
idium | -0.693 |
hler | -0.674 |
cone | -0.662 |
Token | ' |
Token ID | 6 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
axes | +0.609 |
ochond | +0.604 |
pollut | +0.572 |
acceler | +0.571 |
opsis | +0.571 |
Neg logit contributions | |
util | -0.817 |
onen | -0.795 |
idium | -0.784 |
hler | -0.760 |
cone | -0.747 |
Token | I |
Token ID | 314 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
axes | +1.489 |
acceler | +1.473 |
OTOS | +1.463 |
ochond | +1.455 |
pollut | +1.397 |
Neg logit contributions | |
util | -2.480 |
onen | -2.429 |
idium | -2.412 |
avorite | -2.371 |
cone | -2.334 |
Token | 'll |
Token ID | 1183 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
axes | +3.977 |
ochond | +3.745 |
acceler | +3.638 |
pollut | +3.578 |
govern | +3.519 |
Neg logit contributions | |
onen | -5.890 |
util | -5.643 |
idium | -5.562 |
irtual | -5.557 |
perties | -5.440 |
Token | 2009 |
Token ID | 3717 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
axes | +2.974 |
ochond | +2.962 |
OTOS | +2.873 |
pollut | +2.863 |
acceler | +2.837 |
Neg logit contributions | |
util | -4.160 |
idium | -4.053 |
onen | -4.008 |
cone | -3.847 |
avorite | -3.825 |
Token | 10 |
Token ID | 838 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
util | +0.554 |
onen | +0.536 |
idium | +0.522 |
hler | +0.508 |
cone | +0.496 |
Neg logit contributions | |
ochond | -0.547 |
axes | -0.543 |
escription | -0.527 |
opsis | -0.520 |
OTOS | -0.518 |
Token | 2 |
Token ID | 362 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
util | +0.303 |
onen | +0.295 |
idium | +0.289 |
hler | +0.281 |
cone | +0.275 |
Neg logit contributions | |
axes | -0.261 |
ochond | -0.260 |
opsis | -0.247 |
OTOS | -0.247 |
pollut | -0.246 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
axes | +2.736 |
ochond | +2.631 |
pollut | +2.535 |
acceler | +2.521 |
opsis | +2.481 |
Neg logit contributions | |
util | -3.984 |
onen | -3.879 |
idium | -3.814 |
hler | -3.772 |
ussen | -3.674 |
Token | 12 |
Token ID | 1105 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
util | +1.429 |
onen | +1.374 |
idium | +1.337 |
hler | +1.301 |
cone | +1.268 |
Neg logit contributions | |
ochond | -1.487 |
axes | -1.473 |
escription | -1.453 |
opsis | -1.415 |
pollut | -1.413 |
Token | 2 |
Token ID | 362 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
util | +0.746 |
onen | +0.727 |
idium | +0.709 |
hler | +0.689 |
cone | +0.676 |
Neg logit contributions | |
ochond | -0.663 |
axes | -0.661 |
opsis | -0.629 |
OTOS | -0.628 |
escription | -0.627 |
Token | 2011 |
Token ID | 2813 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
axes | +5.137 |
ochond | +4.618 |
acceler | +4.453 |
opsis | +4.432 |
DAC | +4.392 |
Neg logit contributions | |
util | -9.560 |
idium | -9.354 |
onen | -9.234 |
ilogy | -8.992 |
irtual | -8.923 |
Token | 6 |
Token ID | 718 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
ochond | +0.210 |
axes | +0.210 |
escription | +0.200 |
opsis | +0.200 |
OTOS | +0.199 |
Neg logit contributions | |
util | -0.223 |
onen | -0.217 |
idium | -0.212 |
hler | -0.206 |
cone | -0.201 |
Token | 2 |
Token ID | 362 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
util | +1.546 |
onen | +1.506 |
idium | +1.463 |
hler | +1.427 |
cone | +1.400 |
Neg logit contributions | |
ochond | -1.395 |
axes | -1.385 |
opsis | -1.323 |
escription | -1.319 |
pollut | -1.319 |
Token | 2012 |
Token ID | 2321 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
axes | +3.617 |
ochond | +3.357 |
pollut | +3.161 |
opsis | +3.123 |
acceler | +3.077 |
Neg logit contributions | |
onen | -6.526 |
util | -6.490 |
idium | -6.307 |
hler | -6.230 |
cone | -6.038 |
Token | 7 |
Token ID | 767 |
Feature activation | +9.12e-03 |
Pos logit contributions | |
util | +0.604 |
onen | +0.586 |
idium | +0.572 |
hler | +0.556 |
cone | +0.543 |
Neg logit contributions | |
ochond | -0.577 |
axes | -0.576 |
escription | -0.554 |
opsis | -0.549 |
pollut | -0.547 |
Token | former |
Token ID | 1966 |
Feature activation | +9.21e-02 |
Pos logit contributions | |
axes | +1.281 |
ochond | +1.265 |
OTOS | +1.205 |
pollut | +1.204 |
acceler | +1.202 |
Neg logit contributions | |
util | -1.530 |
onen | -1.496 |
idium | -1.473 |
hler | -1.423 |
cone | -1.399 |
Token | President |
Token ID | 1992 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
util | +1.051 |
onen | +1.028 |
idium | +1.005 |
hler | +0.984 |
cone | +0.960 |
Neg logit contributions | |
ochond | -0.774 |
axes | -0.756 |
opsis | -0.738 |
escription | -0.724 |
OTOS | -0.724 |
Token | Barack |
Token ID | 8732 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
util | +0.209 |
onen | +0.203 |
idium | +0.198 |
hler | +0.193 |
cone | +0.188 |
Neg logit contributions | |
ochond | -0.187 |
axes | -0.185 |
opsis | -0.178 |
pollut | -0.178 |
OTOS | -0.177 |
Token | Obama |
Token ID | 2486 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
ochond | +0.962 |
axes | +0.951 |
escription | +0.914 |
pollut | +0.904 |
opsis | +0.904 |
Neg logit contributions | |
util | -1.331 |
onen | -1.289 |
idium | -1.262 |
hler | -1.233 |
cone | -1.206 |
Token | Barack |
Token ID | 8732 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
util | +0.328 |
onen | +0.320 |
idium | +0.315 |
hler | +0.305 |
cone | +0.299 |
Neg logit contributions | |
axes | -0.273 |
ochond | -0.271 |
OTOS | -0.258 |
opsis | -0.257 |
pollut | -0.257 |
Token | Hussein |
Token ID | 22983 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
axes | +4.511 |
ochond | +4.349 |
OTOS | +4.206 |
opsis | +4.187 |
acceler | +4.130 |
Neg logit contributions | |
onen | -5.739 |
idium | -5.603 |
util | -5.579 |
irtual | -5.467 |
avorite | -5.425 |
Token | Obama |
Token ID | 2486 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
axes | +3.922 |
ochond | +3.775 |
OTOS | +3.695 |
acceler | +3.562 |
pollut | +3.262 |
Neg logit contributions | |
onen | -10.890 |
util | -10.821 |
idium | -10.781 |
avorite | -10.609 |
hler | -10.562 |
Token | With |
Token ID | 3152 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
axes | +4.689 |
ochond | +4.619 |
OTOS | +4.521 |
acceler | +4.432 |
pollut | +4.329 |
Neg logit contributions | |
onen | -3.981 |
util | -3.939 |
hler | -3.818 |
idium | -3.809 |
avorite | -3.731 |
Token | low |
Token ID | 1877 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
axes | +2.847 |
ochond | +2.778 |
OTOS | +2.702 |
pollut | +2.685 |
acceler | +2.683 |
Neg logit contributions | |
util | -3.713 |
onen | -3.694 |
idium | -3.616 |
hler | -3.492 |
irtual | -3.423 |
Token | birth |
Token ID | 4082 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
axes | +3.382 |
ochond | +3.357 |
acceler | +3.179 |
OTOS | +3.153 |
pollut | +3.149 |
Neg logit contributions | |
util | -4.686 |
onen | -4.591 |
idium | -4.514 |
hler | -4.375 |
avorite | -4.287 |
Token | rate |
Token ID | 2494 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
ochond | +1.022 |
axes | +1.019 |
OTOS | +0.982 |
opsis | +0.976 |
pollut | +0.972 |
Neg logit contributions | |
util | -0.967 |
onen | -0.938 |
idium | -0.921 |
hler | -0.887 |
cone | -0.878 |
Token | . |
Token ID | 13 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
axes | +1.230 |
ochond | +1.224 |
escription | +1.186 |
pollut | +1.174 |
OTOS | +1.162 |
Neg logit contributions | |
util | -1.284 |
onen | -1.245 |
idium | -1.212 |
hler | -1.183 |
cone | -1.151 |
Token | The |
Token ID | 383 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
ochond | +3.017 |
axes | +3.011 |
OTOS | +2.876 |
opsis | +2.860 |
acceler | +2.836 |
Neg logit contributions | |
util | -3.967 |
onen | -3.918 |
idium | -3.880 |
hler | -3.731 |
avorite | -3.730 |
Token | player |
Token ID | 2137 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
axes | +1.231 |
ochond | +1.227 |
OTOS | +1.151 |
escription | +1.143 |
opsis | +1.137 |
Neg logit contributions | |
util | -2.867 |
onen | -2.813 |
idium | -2.754 |
hler | -2.703 |
cone | -2.659 |
Token | must |
Token ID | 1276 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
axes | +3.734 |
ochond | +3.677 |
acceler | +3.554 |
pollut | +3.448 |
opsis | +3.428 |
Neg logit contributions | |
util | -5.013 |
onen | -4.920 |
idium | -4.903 |
avorite | -4.759 |
hler | -4.685 |
Token | know |
Token ID | 760 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
axes | +2.180 |
ochond | +2.178 |
govern | +1.975 |
OTOS | +1.947 |
acceler | +1.945 |
Neg logit contributions | |
onen | -4.139 |
util | -4.105 |
idium | -4.079 |
cone | -3.991 |
ilogy | -3.913 |
Token | choose |
Token ID | 3853 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
axes | +4.662 |
ochond | +4.603 |
pollut | +4.387 |
acceler | +4.382 |
opsis | +4.318 |
Neg logit contributions | |
util | -4.714 |
onen | -4.701 |
idium | -4.649 |
hler | -4.489 |
cone | -4.390 |
Token | ) |
Token ID | 1267 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
axes | +6.657 |
ochond | +6.225 |
acceler | +6.050 |
pollut | +5.956 |
opsis | +5.816 |
Neg logit contributions | |
onen | -7.980 |
util | -7.825 |
idium | -7.739 |
hler | -7.521 |
cone | -7.343 |
Token | Permanent |
Token ID | 36814 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
axes | +2.356 |
ochond | +2.304 |
OTOS | +2.213 |
acceler | +2.212 |
pollut | +2.190 |
Neg logit contributions | |
util | -2.454 |
onen | -2.436 |
idium | -2.370 |
hler | -2.294 |
cone | -2.271 |
Token | Voices |
Token ID | 40440 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
axes | +3.670 |
ochond | +3.483 |
acceler | +3.467 |
pollut | +3.432 |
OTOS | +3.333 |
Neg logit contributions | |
util | -4.229 |
onen | -4.194 |
idium | -4.023 |
hler | -3.943 |
ilogy | -3.942 |
Token | in |
Token ID | 287 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
axes | +1.289 |
ochond | +1.268 |
acceler | +1.215 |
pollut | +1.213 |
opsis | +1.206 |
Neg logit contributions | |
util | -1.685 |
onen | -1.652 |
idium | -1.631 |
hler | -1.574 |
ilogy | -1.544 |
Token | Your |
Token ID | 3406 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
axes | +0.345 |
ochond | +0.342 |
OTOS | +0.325 |
pollut | +0.324 |
opsis | +0.324 |
Neg logit contributions | |
util | -0.436 |
onen | -0.426 |
idium | -0.418 |
hler | -0.406 |
cone | -0.398 |
Token | trials |
Token ID | 9867 |
Feature activation | -6.88e-03 |
Pos logit contributions | |
util | +2.134 |
onen | +2.077 |
idium | +2.021 |
hler | +1.965 |
cone | +1.937 |
Neg logit contributions | |
ochond | -1.981 |
axes | -1.963 |
OTOS | -1.890 |
opsis | -1.883 |
escription | -1.877 |
Token | identifying |
Token ID | 13720 |
Feature activation | -9.52e-03 |
Pos logit contributions | |
axes | +0.063 |
ochond | +0.063 |
OTOS | +0.060 |
opsis | +0.059 |
pollut | +0.059 |
Neg logit contributions | |
util | -0.074 |
onen | -0.072 |
idium | -0.071 |
hler | -0.069 |
cone | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
axes | +0.089 |
ochond | +0.089 |
acceler | +0.084 |
pollut | +0.084 |
OTOS | +0.084 |
Neg logit contributions | |
util | -0.100 |
onen | -0.098 |
idium | -0.096 |
hler | -0.093 |
cone | -0.091 |
Token | enroll |
Token ID | 14627 |
Feature activation | +4.34e-02 |
Pos logit contributions | |
util | +4.536 |
onen | +4.297 |
idium | +4.151 |
hler | +4.132 |
illance | +4.055 |
Neg logit contributions | |
ochond | -4.934 |
axes | -4.823 |
OTOS | -4.757 |
opsis | -4.744 |
escription | -4.628 |
Token | ing |
Token ID | 278 |
Feature activation | +8.59e-02 |
Pos logit contributions | |
util | +0.572 |
onen | +0.560 |
idium | +0.551 |
hler | +0.539 |
cone | +0.529 |
Neg logit contributions | |
axes | -0.291 |
ochond | -0.288 |
OTOS | -0.271 |
opsis | -0.270 |
pollut | -0.267 |
Token | patients |
Token ID | 3871 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
util | +0.917 |
onen | +0.895 |
idium | +0.877 |
hler | +0.852 |
cone | +0.835 |
Neg logit contributions | |
ochond | -0.787 |
axes | -0.787 |
OTOS | -0.748 |
opsis | -0.745 |
pollut | -0.742 |
Token | with |
Token ID | 351 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
util | +4.366 |
onen | +4.212 |
idium | +4.082 |
hler | +4.001 |
cone | +3.960 |
Neg logit contributions | |
axes | -4.230 |
ochond | -4.214 |
OTOS | -4.132 |
escription | -4.014 |
pollut | -3.963 |
Token | C |
Token ID | 327 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
util | +3.470 |
onen | +3.360 |
idium | +3.300 |
hler | +3.190 |
cone | +3.158 |
Neg logit contributions | |
ochond | -3.422 |
axes | -3.389 |
escription | -3.276 |
OTOS | -3.260 |
opsis | -3.248 |
Token | IR |
Token ID | 4663 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
util | +0.159 |
onen | +0.155 |
idium | +0.153 |
hler | +0.149 |
cone | +0.146 |
Neg logit contributions | |
axes | -0.084 |
ochond | -0.083 |
pollut | -0.078 |
opsis | -0.077 |
acceler | -0.077 |
Token | CI |
Token ID | 25690 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
axes | +2.279 |
ochond | +2.272 |
OTOS | +2.185 |
opsis | +2.181 |
acceler | +2.174 |
Neg logit contributions | |
util | -1.547 |
onen | -1.505 |
idium | -1.456 |
hler | -1.403 |
cone | -1.357 |
Token | ). |
Token ID | 737 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
axes | +0.228 |
ochond | +0.227 |
OTOS | +0.216 |
opsis | +0.216 |
pollut | +0.216 |
Neg logit contributions | |
util | -0.245 |
onen | -0.239 |
idium | -0.234 |
hler | -0.227 |
cone | -0.222 |
Token | enrollment |
Token ID | 20753 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
util | +1.697 |
onen | +1.647 |
idium | +1.610 |
hler | +1.577 |
cone | +1.545 |
Neg logit contributions | |
ochond | -1.383 |
axes | -1.353 |
OTOS | -1.315 |
escription | -1.303 |
opsis | -1.299 |
Token | as |
Token ID | 355 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
util | +2.964 |
onen | +2.882 |
idium | +2.769 |
cone | +2.726 |
hler | +2.722 |
Neg logit contributions | |
ochond | -2.818 |
escription | -2.723 |
axes | -2.703 |
OTOS | -2.688 |
opsis | -2.656 |
Token | part |
Token ID | 636 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
util | +1.236 |
onen | +1.200 |
idium | +1.182 |
hler | +1.150 |
cone | +1.128 |
Neg logit contributions | |
ochond | -1.067 |
axes | -1.063 |
OTOS | -1.017 |
opsis | -1.014 |
pollut | -1.003 |
Token | of |
Token ID | 286 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
util | +2.258 |
onen | +2.157 |
hler | +2.053 |
idium | +2.024 |
cone | +2.002 |
Neg logit contributions | |
escription | -2.599 |
axes | -2.415 |
ochond | -2.386 |
pollut | -2.328 |
opsis | -2.314 |
Token | the |
Token ID | 262 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
util | +3.101 |
onen | +2.988 |
idium | +2.914 |
hler | +2.872 |
cone | +2.807 |
Neg logit contributions | |
ochond | -2.580 |
axes | -2.542 |
opsis | -2.452 |
OTOS | -2.442 |
escription | -2.413 |
Token | 2011 |
Token ID | 2813 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
util | +1.835 |
onen | +1.785 |
idium | +1.734 |
hler | +1.699 |
cone | +1.657 |
Neg logit contributions | |
ochond | -1.531 |
axes | -1.494 |
OTOS | -1.455 |
opsis | -1.445 |
escription | -1.440 |
Token | - |
Token ID | 12 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
util | +4.624 |
onen | +4.379 |
idium | +4.294 |
hler | +4.167 |
cone | +4.120 |
Neg logit contributions | |
ochond | -4.291 |
axes | -4.078 |
escription | -4.063 |
OTOS | -4.060 |
opsis | -3.999 |
Token | 13 |
Token ID | 1485 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
axes | +1.696 |
ochond | +1.687 |
OTOS | +1.626 |
pollut | +1.624 |
opsis | +1.623 |
Neg logit contributions | |
util | -1.097 |
onen | -1.079 |
idium | -1.055 |
hler | -1.011 |
ilogy | -0.969 |
Token | state |
Token ID | 1181 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
util | +2.663 |
onen | +2.556 |
idium | +2.492 |
hler | +2.424 |
cone | +2.385 |
Neg logit contributions | |
ochond | -2.552 |
axes | -2.472 |
escription | -2.417 |
OTOS | -2.411 |
opsis | -2.402 |
Token | budget |
Token ID | 4466 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
util | +0.976 |
onen | +0.936 |
idium | +0.913 |
hler | +0.891 |
cone | +0.874 |
Neg logit contributions | |
ochond | -1.121 |
axes | -1.108 |
OTOS | -1.070 |
opsis | -1.070 |
escription | -1.066 |
Token | , |
Token ID | 11 |
Feature activation | +9.02e-02 |
Pos logit contributions | |
util | +2.270 |
onen | +2.183 |
idium | +2.114 |
hler | +2.058 |
cone | +2.056 |
Neg logit contributions | |
ochond | -2.194 |
axes | -2.125 |
escription | -2.087 |
opsis | -2.057 |
OTOS | -2.044 |
Token | " |
Token ID | 366 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
util | +2.487 |
onen | +2.405 |
idium | +2.318 |
hler | +2.225 |
ilogy | +2.144 |
Neg logit contributions | |
ochond | -3.056 |
axes | -3.000 |
escription | -2.944 |
OTOS | -2.912 |
opsis | -2.911 |
Token | P |
Token ID | 47 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
util | +0.926 |
onen | +0.845 |
idium | +0.773 |
cone | +0.735 |
hler | +0.731 |
Neg logit contributions | |
escription | -2.555 |
axes | -2.509 |
ochond | -2.503 |
pollut | -2.449 |
acceler | -2.406 |
Token | ulse |
Token ID | 9615 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
axes | +1.574 |
ochond | +1.569 |
OTOS | +1.503 |
opsis | +1.501 |
pollut | +1.499 |
Neg logit contributions | |
util | -1.307 |
onen | -1.270 |
idium | -1.241 |
hler | -1.196 |
cone | -1.167 |
Token | period |
Token ID | 2278 |
Feature activation | +7.57e-02 |
Pos logit contributions | |
axes | +2.453 |
ochond | +2.426 |
pollut | +2.290 |
acceler | +2.280 |
opsis | +2.273 |
Neg logit contributions | |
util | -3.936 |
onen | -3.863 |
idium | -3.805 |
hler | -3.704 |
cone | -3.625 |
Token | " |
Token ID | 1 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
util | +0.712 |
onen | +0.684 |
idium | +0.659 |
hler | +0.643 |
cone | +0.622 |
Neg logit contributions | |
escription | -0.811 |
axes | -0.803 |
ochond | -0.794 |
pollut | -0.772 |
OTOS | -0.770 |
Token | , |
Token ID | 837 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
util | +4.228 |
onen | +3.936 |
idium | +3.759 |
hler | +3.729 |
kov | +3.603 |
Neg logit contributions | |
escription | -4.589 |
ochond | -4.160 |
pollut | -4.110 |
axes | -4.099 |
subsequ | -3.995 |
Token | Float |
Token ID | 48436 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
util | +4.129 |
onen | +3.849 |
idium | +3.631 |
hler | +3.620 |
cone | +3.545 |
Neg logit contributions | |
escription | -5.481 |
ochond | -5.238 |
axes | -5.056 |
opsis | -5.048 |
OTOS | -4.987 |
Token | ) |
Token ID | 1267 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
util | +3.671 |
onen | +3.500 |
hler | +3.440 |
idium | +3.405 |
cone | +3.248 |
Neg logit contributions | |
escription | -2.689 |
axes | -2.393 |
ochond | -2.387 |
pollut | -2.376 |
subsequ | -2.265 |
Token | = |
Token ID | 796 |
Feature activation | +8.87e-02 |
Pos logit contributions | |
util | +0.633 |
onen | +0.602 |
idium | +0.583 |
hler | +0.579 |
cone | +0.554 |
Neg logit contributions | |
escription | -0.634 |
axes | -0.620 |
ochond | -0.617 |
pollut | -0.601 |
opsis | -0.584 |
Token | 1 |
Token ID | 352 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
util | +0.821 |
onen | +0.797 |
idium | +0.771 |
hler | +0.744 |
cone | +0.721 |
Neg logit contributions | |
escription | -0.961 |
ochond | -0.958 |
axes | -0.930 |
OTOS | -0.908 |
pollut | -0.904 |
Token | // |
Token ID | 3373 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
util | +2.979 |
onen | +2.548 |
hler | +2.511 |
idium | +2.353 |
uristic | +2.294 |
Neg logit contributions | |
escription | -6.670 |
ochond | -6.283 |
axes | -6.216 |
pollut | -6.131 |
phies | -6.055 |
Token | itself |
Token ID | 2346 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
util | +0.788 |
onen | +0.769 |
idium | +0.754 |
hler | +0.731 |
cone | +0.717 |
Neg logit contributions | |
ochond | -0.646 |
axes | -0.644 |
OTOS | -0.616 |
opsis | -0.614 |
pollut | -0.610 |
Token | will |
Token ID | 481 |
Feature activation | +6.54e-03 |
Pos logit contributions | |
axes | +1.105 |
ochond | +1.092 |
acceler | +1.040 |
opsis | +1.034 |
pollut | +1.034 |
Neg logit contributions | |
util | -1.399 |
onen | -1.369 |
idium | -1.347 |
hler | -1.305 |
cone | -1.283 |
Token | be |
Token ID | 307 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
util | +0.077 |
onen | +0.075 |
idium | +0.074 |
hler | +0.072 |
cone | +0.070 |
Neg logit contributions | |
ochond | -0.053 |
axes | -0.053 |
OTOS | -0.050 |
opsis | -0.050 |
pollut | -0.050 |
Token | subject |
Token ID | 2426 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
util | +1.676 |
onen | +1.621 |
idium | +1.578 |
hler | +1.542 |
cone | +1.500 |
Neg logit contributions | |
ochond | -1.441 |
axes | -1.425 |
opsis | -1.382 |
OTOS | -1.373 |
pollut | -1.352 |
Token | to |
Token ID | 284 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
util | +1.434 |
onen | +1.410 |
idium | +1.384 |
hler | +1.350 |
cone | +1.334 |
Neg logit contributions | |
ochond | -0.961 |
axes | -0.955 |
OTOS | -0.899 |
pollut | -0.895 |
acceler | -0.894 |
Token | sh |
Token ID | 427 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
util | +2.370 |
onen | +2.293 |
idium | +2.242 |
hler | +2.182 |
cone | +2.110 |
Neg logit contributions | |
ochond | -2.014 |
axes | -1.997 |
opsis | -1.932 |
OTOS | -1.905 |
escription | -1.882 |
Token | aria |
Token ID | 10312 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
util | +3.222 |
onen | +3.150 |
idium | +3.079 |
unia | +2.742 |
hler | +2.724 |
Neg logit contributions | |
axes | -5.119 |
ochond | -5.027 |
OTOS | -5.010 |
pollut | -4.973 |
acceler | -4.967 |
Token | in |
Token ID | 287 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
util | +1.945 |
onen | +1.893 |
idium | +1.857 |
hler | +1.799 |
cone | +1.756 |
Neg logit contributions | |
ochond | -1.548 |
axes | -1.518 |
opsis | -1.470 |
OTOS | -1.459 |
escription | -1.431 |
Token | its |
Token ID | 663 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
util | +1.384 |
onen | +1.343 |
idium | +1.313 |
hler | +1.275 |
cone | +1.249 |
Neg logit contributions | |
ochond | -1.131 |
axes | -1.120 |
OTOS | -1.076 |
opsis | -1.071 |
pollut | -1.060 |
Token | dealings |
Token ID | 29043 |
Feature activation | +5.53e-03 |
Pos logit contributions | |
util | +2.311 |
onen | +2.266 |
idium | +2.213 |
hler | +2.126 |
cone | +2.101 |
Neg logit contributions | |
ochond | -1.603 |
axes | -1.563 |
OTOS | -1.533 |
opsis | -1.513 |
escription | -1.512 |
Token | on |
Token ID | 319 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
util | +0.063 |
onen | +0.061 |
idium | +0.061 |
hler | +0.059 |
cone | +0.058 |
Neg logit contributions | |
axes | -0.047 |
ochond | -0.047 |
opsis | -0.044 |
acceler | -0.044 |
OTOS | -0.044 |
Token | had |
Token ID | 550 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
util | +4.273 |
onen | +4.130 |
idium | +4.019 |
hler | +3.843 |
cone | +3.785 |
Neg logit contributions | |
ochond | -4.291 |
escription | -4.240 |
OTOS | -4.227 |
pollut | -4.079 |
axes | -4.065 |
Token | lost |
Token ID | 2626 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
util | +3.762 |
onen | +3.585 |
idium | +3.470 |
hler | +3.321 |
cone | +3.269 |
Neg logit contributions | |
ochond | -4.277 |
escription | -4.168 |
OTOS | -4.166 |
axes | -4.068 |
opsis | -4.068 |
Token | when |
Token ID | 618 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
util | +2.557 |
onen | +2.483 |
idium | +2.383 |
hler | +2.311 |
cone | +2.309 |
Neg logit contributions | |
ochond | -2.572 |
axes | -2.494 |
OTOS | -2.452 |
pollut | -2.440 |
opsis | -2.421 |
Token | he |
Token ID | 339 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
util | +0.329 |
onen | +0.322 |
idium | +0.315 |
hler | +0.306 |
cone | +0.300 |
Neg logit contributions | |
ochond | -0.282 |
axes | -0.282 |
OTOS | -0.268 |
opsis | -0.267 |
pollut | -0.267 |
Token | murdered |
Token ID | 12864 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
util | +3.132 |
onen | +3.021 |
idium | +2.936 |
hler | +2.854 |
cone | +2.790 |
Neg logit contributions | |
ochond | -3.240 |
OTOS | -3.187 |
escription | -3.134 |
axes | -3.105 |
pollut | -3.096 |
Token | Yoshi |
Token ID | 38936 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
util | +1.321 |
onen | +1.291 |
idium | +1.261 |
hler | +1.226 |
cone | +1.201 |
Neg logit contributions | |
ochond | -1.029 |
axes | -1.026 |
OTOS | -0.976 |
opsis | -0.972 |
pollut | -0.969 |
Token | . |
Token ID | 13 |
Feature activation | -7.97e-04 |
Pos logit contributions | |
util | +4.141 |
onen | +4.086 |
idium | +3.892 |
hler | +3.856 |
cone | +3.752 |
Neg logit contributions | |
ochond | -4.385 |
axes | -4.297 |
pollut | -4.180 |
OTOS | -4.103 |
escription | -4.099 |
Token | S |
Token ID | 311 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
axes | +0.008 |
ochond | +0.008 |
pollut | +0.007 |
OTOS | +0.007 |
opsis | +0.007 |
Neg logit contributions | |
util | -0.008 |
onen | -0.008 |
idium | -0.008 |
hler | -0.008 |
cone | -0.007 |
Token | aki |
Token ID | 8182 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
util | +1.297 |
onen | +1.225 |
idium | +1.204 |
hler | +1.143 |
cone | +1.133 |
Neg logit contributions | |
axes | -1.885 |
escription | -1.847 |
pollut | -1.841 |
ochond | -1.821 |
acceler | -1.789 |
Token | refuses |
Token ID | 17567 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
axes | +1.250 |
ochond | +1.223 |
acceler | +1.173 |
opsis | +1.160 |
pollut | +1.156 |
Neg logit contributions | |
util | -1.714 |
onen | -1.677 |
idium | -1.651 |
hler | -1.602 |
cone | -1.575 |
Token | and |
Token ID | 290 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
axes | +0.427 |
ochond | +0.421 |
OTOS | +0.400 |
acceler | +0.400 |
opsis | +0.399 |
Neg logit contributions | |
util | -0.539 |
onen | -0.527 |
idium | -0.518 |
hler | -0.503 |
cone | -0.492 |
Token | : |
Token ID | 25 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
util | +3.090 |
onen | +3.009 |
idium | +2.920 |
hler | +2.865 |
cone | +2.775 |
Neg logit contributions | |
ochond | -2.929 |
axes | -2.904 |
pollut | -2.799 |
opsis | -2.787 |
OTOS | -2.771 |
Token | how |
Token ID | 703 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
util | +3.923 |
onen | +3.772 |
idium | +3.655 |
hler | +3.593 |
cone | +3.478 |
Neg logit contributions | |
ochond | -3.962 |
axes | -3.842 |
OTOS | -3.740 |
pollut | -3.703 |
opsis | -3.701 |
Token | to |
Token ID | 284 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
util | +2.012 |
onen | +1.965 |
idium | +1.909 |
hler | +1.869 |
cone | +1.816 |
Neg logit contributions | |
ochond | -1.707 |
axes | -1.679 |
OTOS | -1.623 |
opsis | -1.607 |
pollut | -1.605 |
Token | teach |
Token ID | 4545 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
util | +2.268 |
onen | +2.206 |
idium | +2.144 |
hler | +2.110 |
cone | +2.044 |
Neg logit contributions | |
ochond | -1.661 |
axes | -1.639 |
OTOS | -1.587 |
escription | -1.574 |
opsis | -1.555 |
Token | yourself |
Token ID | 3511 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
util | +0.926 |
onen | +0.905 |
idium | +0.883 |
hler | +0.862 |
cone | +0.839 |
Neg logit contributions | |
ochond | -0.746 |
axes | -0.737 |
OTOS | -0.707 |
opsis | -0.704 |
pollut | -0.702 |
Token | to |
Token ID | 284 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
util | +2.095 |
onen | +2.048 |
idium | +1.985 |
hler | +1.943 |
cone | +1.881 |
Neg logit contributions | |
ochond | -1.710 |
axes | -1.686 |
OTOS | -1.627 |
opsis | -1.617 |
pollut | -1.606 |
Token | code |
Token ID | 2438 |
Feature activation | +8.42e-03 |
Pos logit contributions | |
util | +1.430 |
onen | +1.402 |
idium | +1.364 |
hler | +1.343 |
cone | +1.312 |
Neg logit contributions | |
ochond | -0.763 |
axes | -0.760 |
OTOS | -0.715 |
opsis | -0.707 |
escription | -0.707 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
util | +0.092 |
onen | +0.090 |
idium | +0.088 |
hler | +0.085 |
cone | +0.084 |
Neg logit contributions | |
axes | -0.076 |
ochond | -0.075 |
OTOS | -0.071 |
opsis | -0.071 |
pollut | -0.071 |
Token |
|
Token ID | 198 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
escription | +0.131 |
axes | +0.131 |
ochond | +0.131 |
pollut | +0.126 |
opsis | +0.124 |
Neg logit contributions | |
util | -0.133 |
onen | -0.127 |
idium | -0.123 |
hler | -0.121 |
cone | -0.118 |
Token | Apple |
Token ID | 16108 |
Feature activation | -4.61e-03 |
Pos logit contributions | |
util | +0.263 |
onen | +0.255 |
idium | +0.248 |
hler | +0.240 |
cone | +0.234 |
Neg logit contributions | |
axes | -0.314 |
ochond | -0.313 |
pollut | -0.299 |
OTOS | -0.299 |
opsis | -0.299 |
Token | � |
Token ID | 447 |
Feature activation | +9.69e-02 |
Pos logit contributions | |
ochond | +0.043 |
axes | +0.043 |
OTOS | +0.041 |
pollut | +0.041 |
opsis | +0.041 |
Neg logit contributions | |
util | -0.048 |
onen | -0.047 |
idium | -0.046 |
hler | -0.045 |
cone | -0.044 |
Token | Facebook |
Token ID | 12025 |
Feature activation | +8.58e-02 |
Pos logit contributions | |
util | +0.183 |
onen | +0.177 |
idium | +0.172 |
hler | +0.166 |
cone | +0.162 |
Neg logit contributions | |
axes | -0.218 |
ochond | -0.216 |
pollut | -0.208 |
opsis | -0.207 |
acceler | -0.207 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
util | +0.888 |
onen | +0.868 |
idium | +0.845 |
hler | +0.820 |
cone | +0.801 |
Neg logit contributions | |
axes | -0.820 |
ochond | -0.815 |
opsis | -0.774 |
pollut | -0.774 |
OTOS | -0.773 |
Token | Pinterest |
Token ID | 17334 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
axes | +2.276 |
ochond | +2.267 |
OTOS | +2.152 |
opsis | +2.148 |
pollut | +2.144 |
Neg logit contributions | |
util | -2.731 |
onen | -2.668 |
idium | -2.617 |
hler | -2.540 |
cone | -2.488 |
Token | Liverpool |
Token ID | 11761 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
util | +1.286 |
onen | +1.251 |
idium | +1.213 |
hler | +1.183 |
cone | +1.150 |
Neg logit contributions | |
axes | -1.226 |
ochond | -1.225 |
pollut | -1.168 |
opsis | -1.166 |
OTOS | -1.157 |
Token | � |
Token ID | 447 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
axes | +0.255 |
ochond | +0.254 |
OTOS | +0.241 |
opsis | +0.240 |
pollut | +0.240 |
Neg logit contributions | |
util | -0.315 |
onen | -0.308 |
idium | -0.302 |
hler | -0.293 |
cone | -0.287 |
Token | � |
Token ID | 247 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
util | +0.751 |
onen | +0.725 |
idium | +0.700 |
hler | +0.692 |
cone | +0.660 |
Neg logit contributions | |
ochond | -1.140 |
axes | -1.134 |
pollut | -1.099 |
escription | -1.098 |
OTOS | -1.096 |
Token | s |
Token ID | 82 |
Feature activation | +9.95e-02 |
Pos logit contributions | |
util | +0.204 |
onen | +0.199 |
idium | +0.194 |
hler | +0.188 |
cone | +0.184 |
Neg logit contributions | |
axes | -0.178 |
ochond | -0.178 |
OTOS | -0.169 |
pollut | -0.169 |
opsis | -0.169 |
Token | Adam |
Token ID | 7244 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
util | +1.048 |
onen | +1.016 |
idium | +0.994 |
hler | +0.964 |
cone | +0.939 |
Neg logit contributions | |
ochond | -0.929 |
axes | -0.921 |
opsis | -0.887 |
OTOS | -0.887 |
pollut | -0.878 |
Token | L |
Token ID | 406 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
axes | +0.924 |
ochond | +0.922 |
OTOS | +0.872 |
opsis | +0.872 |
pollut | +0.868 |
Neg logit contributions | |
util | -1.190 |
onen | -1.162 |
idium | -1.143 |
hler | -1.107 |
cone | -1.091 |
Token | all |
Token ID | 439 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
util | +1.274 |
onen | +1.224 |
idium | +1.196 |
hler | +1.156 |
ussen | +1.112 |
Neg logit contributions | |
axes | -1.931 |
ochond | -1.909 |
OTOS | -1.879 |
pollut | -1.864 |
opsis | -1.860 |
Token | ana |
Token ID | 2271 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
util | +0.961 |
onen | +0.937 |
idium | +0.871 |
hler | +0.836 |
cone | +0.806 |
Neg logit contributions | |
axes | -1.700 |
ochond | -1.665 |
OTOS | -1.665 |
pollut | -1.639 |
escription | -1.630 |
Token | sound |
Token ID | 2128 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
util | +1.186 |
onen | +1.157 |
idium | +1.132 |
hler | +1.099 |
cone | +1.074 |
Neg logit contributions | |
ochond | -1.053 |
axes | -1.051 |
OTOS | -1.000 |
opsis | -0.996 |
pollut | -0.994 |
Token | tracks |
Token ID | 46074 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
axes | +0.079 |
ochond | +0.079 |
OTOS | +0.074 |
opsis | +0.074 |
pollut | +0.073 |
Neg logit contributions | |
util | -0.145 |
onen | -0.142 |
idium | -0.139 |
hler | -0.136 |
cone | -0.134 |
Token | for |
Token ID | 329 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
util | +1.597 |
onen | +1.557 |
idium | +1.526 |
hler | +1.488 |
cone | +1.455 |
Neg logit contributions | |
ochond | -1.269 |
axes | -1.266 |
OTOS | -1.206 |
pollut | -1.194 |
opsis | -1.192 |
Token | seasons |
Token ID | 7028 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
util | +0.218 |
onen | +0.213 |
idium | +0.209 |
hler | +0.202 |
cone | +0.198 |
Neg logit contributions | |
axes | -0.196 |
ochond | -0.195 |
OTOS | -0.186 |
opsis | -0.185 |
pollut | -0.185 |
Token | 9 |
Token ID | 860 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
axes | +1.477 |
ochond | +1.451 |
acceler | +1.387 |
opsis | +1.385 |
pollut | +1.378 |
Neg logit contributions | |
util | -1.787 |
onen | -1.745 |
idium | -1.714 |
hler | -1.661 |
cone | -1.629 |
Token | through |
Token ID | 832 |
Feature activation | +9.82e-02 |
Pos logit contributions | |
util | +2.486 |
onen | +2.413 |
idium | +2.378 |
hler | +2.321 |
cone | +2.272 |
Neg logit contributions | |
ochond | -2.201 |
axes | -2.199 |
OTOS | -2.097 |
pollut | -2.088 |
opsis | -2.081 |
Token | 27 |
Token ID | 2681 |
Feature activation | +8.48e-02 |
Pos logit contributions | |
util | +0.993 |
onen | +0.960 |
idium | +0.934 |
hler | +0.908 |
cone | +0.892 |
Neg logit contributions | |
ochond | -0.963 |
axes | -0.954 |
escription | -0.919 |
OTOS | -0.916 |
opsis | -0.913 |
Token | ( |
Token ID | 357 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
util | +0.903 |
onen | +0.880 |
idium | +0.865 |
hler | +0.841 |
cone | +0.823 |
Neg logit contributions | |
axes | -0.777 |
ochond | -0.776 |
OTOS | -0.737 |
pollut | -0.736 |
opsis | -0.732 |
Token | with |
Token ID | 4480 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
util | +0.410 |
onen | +0.397 |
idium | +0.387 |
hler | +0.375 |
cone | +0.368 |
Neg logit contributions | |
axes | -0.462 |
ochond | -0.460 |
pollut | -0.441 |
opsis | -0.441 |
OTOS | -0.441 |
Token | the |
Token ID | 262 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
axes | +1.618 |
ochond | +1.574 |
acceler | +1.512 |
pollut | +1.510 |
opsis | +1.505 |
Neg logit contributions | |
util | -1.919 |
onen | -1.899 |
idium | -1.859 |
hler | -1.776 |
cone | -1.768 |
Token | exception |
Token ID | 6631 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
axes | +0.719 |
ochond | +0.706 |
pollut | +0.674 |
acceler | +0.673 |
opsis | +0.672 |
Neg logit contributions | |
util | -0.838 |
onen | -0.822 |
idium | -0.808 |
hler | -0.778 |
cone | -0.766 |
Token | do |
Token ID | 466 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
util | +3.504 |
onen | +3.461 |
idium | +3.373 |
hler | +3.305 |
cone | +3.238 |
Neg logit contributions | |
ochond | -2.362 |
axes | -2.341 |
OTOS | -2.216 |
opsis | -2.214 |
escription | -2.189 |
Token | with |
Token ID | 351 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
util | +1.965 |
onen | +1.936 |
idium | +1.838 |
hler | +1.808 |
cone | +1.763 |
Neg logit contributions | |
escription | -2.124 |
ochond | -2.063 |
axes | -2.042 |
OTOS | -2.004 |
opsis | -1.976 |
Token | the |
Token ID | 262 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
util | +1.607 |
onen | +1.563 |
idium | +1.537 |
hler | +1.489 |
cone | +1.457 |
Neg logit contributions | |
ochond | -1.365 |
axes | -1.351 |
OTOS | -1.295 |
opsis | -1.290 |
pollut | -1.280 |
Token | requests |
Token ID | 7007 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
util | +1.326 |
onen | +1.291 |
idium | +1.267 |
hler | +1.229 |
cone | +1.204 |
Neg logit contributions | |
ochond | -1.148 |
axes | -1.136 |
OTOS | -1.090 |
opsis | -1.088 |
pollut | -1.075 |
Token | of |
Token ID | 286 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
util | +0.410 |
onen | +0.402 |
idium | +0.393 |
hler | +0.383 |
cone | +0.375 |
Neg logit contributions | |
axes | -0.305 |
ochond | -0.302 |
opsis | -0.285 |
acceler | -0.285 |
pollut | -0.285 |
Token | other |
Token ID | 584 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
util | +1.449 |
onen | +1.408 |
idium | +1.383 |
hler | +1.338 |
cone | +1.310 |
Neg logit contributions | |
ochond | -1.345 |
axes | -1.340 |
OTOS | -1.284 |
opsis | -1.280 |
pollut | -1.270 |
Token | autonomous |
Token ID | 18284 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
util | +1.971 |
onen | +1.921 |
idium | +1.882 |
hler | +1.827 |
cone | +1.798 |
Neg logit contributions | |
ochond | -1.650 |
axes | -1.628 |
OTOS | -1.578 |
opsis | -1.567 |
escription | -1.554 |
Token | communities |
Token ID | 5348 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
util | +1.939 |
onen | +1.900 |
idium | +1.852 |
hler | +1.794 |
cone | +1.764 |
Neg logit contributions | |
ochond | -1.576 |
axes | -1.551 |
OTOS | -1.503 |
opsis | -1.484 |
pollut | -1.479 |
Token | . |
Token ID | 13 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
axes | +0.383 |
ochond | +0.380 |
opsis | +0.361 |
OTOS | +0.361 |
acceler | +0.361 |
Neg logit contributions | |
util | -0.449 |
onen | -0.438 |
idium | -0.431 |
hler | -0.417 |
cone | -0.409 |
Token | � |
Token ID | 447 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
axes | +2.282 |
ochond | +2.281 |
OTOS | +2.195 |
opsis | +2.175 |
acceler | +2.161 |
Neg logit contributions | |
util | -2.079 |
onen | -2.041 |
idium | -2.030 |
avorite | -1.958 |
hler | -1.933 |
Token | � |
Token ID | 251 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
axes | +0.089 |
ochond | +0.088 |
opsis | +0.084 |
OTOS | +0.083 |
acceler | +0.082 |
Neg logit contributions | |
util | -0.124 |
onen | -0.120 |
idium | -0.119 |
irtual | -0.114 |
hler | -0.113 |
Token | said |
Token ID | 531 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ochond | +1.698 |
axes | +1.679 |
opsis | +1.599 |
acceler | +1.597 |
pollut | +1.584 |
Neg logit contributions | |
util | -1.595 |
onen | -1.561 |
idium | -1.548 |
avorite | -1.465 |
illance | -1.449 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
ochond | +1.862 |
axes | +1.822 |
opsis | +1.726 |
acceler | +1.712 |
pollut | +1.697 |
Neg logit contributions | |
util | -2.641 |
onen | -2.610 |
idium | -2.570 |
hler | -2.478 |
irtual | -2.459 |
Token | � |
Token ID | 564 |
Feature activation | -8.62e-02 |
Pos logit contributions | |
axes | +0.975 |
ochond | +0.973 |
OTOS | +0.926 |
opsis | +0.924 |
acceler | +0.919 |
Neg logit contributions | |
util | -1.092 |
onen | -1.074 |
idium | -1.058 |
hler | -1.019 |
cone | -1.000 |
Token | � |
Token ID | 250 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
ochond | +1.045 |
axes | +1.043 |
pollut | +1.004 |
escription | +1.001 |
OTOS | +1.000 |
Neg logit contributions | |
util | -0.673 |
onen | -0.651 |
idium | -0.630 |
hler | -0.609 |
cone | -0.588 |
Token | We |
Token ID | 1135 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
axes | +0.235 |
ochond | +0.234 |
OTOS | +0.224 |
opsis | +0.224 |
pollut | +0.224 |
Neg logit contributions | |
util | -0.207 |
onen | -0.201 |
idium | -0.197 |
hler | -0.190 |
cone | -0.186 |
Token | were |
Token ID | 547 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
axes | +1.927 |
ochond | +1.923 |
opsis | +1.823 |
pollut | +1.817 |
acceler | +1.812 |
Neg logit contributions | |
util | -2.221 |
onen | -2.191 |
idium | -2.158 |
hler | -2.062 |
cone | -2.048 |
Token | picking |
Token ID | 10868 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
util | +0.209 |
onen | +0.204 |
idium | +0.200 |
hler | +0.194 |
cone | +0.190 |
Neg logit contributions | |
axes | -0.182 |
ochond | -0.182 |
OTOS | -0.173 |
opsis | -0.172 |
pollut | -0.172 |
Token | some |
Token ID | 617 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
axes | +1.647 |
ochond | +1.618 |
acceler | +1.540 |
opsis | +1.537 |
pollut | +1.533 |
Neg logit contributions | |
util | -1.973 |
onen | -1.933 |
idium | -1.904 |
hler | -1.850 |
cone | -1.800 |
Token | of |
Token ID | 286 |
Feature activation | +1.09e-03 |
Pos logit contributions | |
axes | +1.529 |
ochond | +1.497 |
acceler | +1.428 |
opsis | +1.427 |
pollut | +1.426 |
Neg logit contributions | |
util | -1.949 |
onen | -1.905 |
idium | -1.873 |
hler | -1.831 |
ilogy | -1.775 |
Token | our |
Token ID | 674 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
util | +0.012 |
onen | +0.012 |
idium | +0.012 |
hler | +0.011 |
cone | +0.011 |
Neg logit contributions | |
axes | -0.010 |
ochond | -0.009 |
opsis | -0.009 |
pollut | -0.009 |
acceler | -0.009 |
Token | grapes |
Token ID | 36656 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
axes | +1.549 |
ochond | +1.504 |
acceler | +1.449 |
pollut | +1.445 |
opsis | +1.437 |
Neg logit contributions | |
util | -1.806 |
onen | -1.769 |
idium | -1.737 |
hler | -1.697 |
cone | -1.646 |
Token | � |
Token ID | 251 |
Feature activation | +2.39e-03 |
Pos logit contributions | |
axes | +0.729 |
ochond | +0.727 |
OTOS | +0.686 |
opsis | +0.685 |
pollut | +0.684 |
Neg logit contributions | |
util | -1.015 |
onen | -0.993 |
idium | -0.976 |
hler | -0.949 |
cone | -0.931 |
Token | , |
Token ID | 11 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
util | +0.026 |
onen | +0.026 |
idium | +0.025 |
hler | +0.024 |
cone | +0.024 |
Neg logit contributions | |
axes | -0.021 |
ochond | -0.021 |
opsis | -0.020 |
OTOS | -0.020 |
acceler | -0.020 |
Token | it |
Token ID | 340 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
axes | +1.483 |
ochond | +1.452 |
acceler | +1.390 |
pollut | +1.376 |
OTOS | +1.371 |
Neg logit contributions | |
util | -2.166 |
onen | -2.137 |
idium | -2.085 |
hler | -2.039 |
cone | -2.010 |
Token | reads |
Token ID | 9743 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
axes | +1.029 |
ochond | +1.007 |
acceler | +0.959 |
opsis | +0.943 |
OTOS | +0.937 |
Neg logit contributions | |
util | -2.002 |
onen | -1.967 |
idium | -1.931 |
cone | -1.882 |
hler | -1.881 |
Token | . |
Token ID | 13 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
util | +2.171 |
onen | +2.126 |
idium | +2.080 |
hler | +2.022 |
cone | +1.987 |
Neg logit contributions | |
axes | -1.785 |
ochond | -1.773 |
opsis | -1.688 |
OTOS | -1.684 |
pollut | -1.677 |
Token |
|
Token ID | 198 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
axes | +1.751 |
ochond | +1.708 |
OTOS | +1.686 |
acceler | +1.625 |
pollut | +1.621 |
Neg logit contributions | |
util | -2.609 |
onen | -2.603 |
idium | -2.560 |
hler | -2.496 |
cone | -2.466 |
Token |
|
Token ID | 198 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
ochond | +1.109 |
axes | +1.109 |
escription | +1.084 |
pollut | +1.058 |
opsis | +1.051 |
Neg logit contributions | |
util | -1.203 |
onen | -1.163 |
idium | -1.130 |
hler | -1.106 |
cone | -1.079 |
Token | Audio |
Token ID | 21206 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
axes | +0.461 |
ochond | +0.460 |
OTOS | +0.445 |
opsis | +0.440 |
pollut | +0.438 |
Neg logit contributions | |
util | -0.375 |
onen | -0.367 |
idium | -0.359 |
hler | -0.346 |
cone | -0.337 |
Token | evidence |
Token ID | 2370 |
Feature activation | -7.56e-02 |
Pos logit contributions | |
util | +0.466 |
onen | +0.455 |
idium | +0.448 |
hler | +0.435 |
cone | +0.427 |
Neg logit contributions | |
axes | -0.340 |
ochond | -0.340 |
OTOS | -0.320 |
opsis | -0.318 |
pollut | -0.318 |
Token |
|
Token ID | 198 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
axes | +0.657 |
ochond | +0.654 |
OTOS | +0.618 |
opsis | +0.618 |
pollut | +0.617 |
Neg logit contributions | |
util | -0.844 |
onen | -0.828 |
idium | -0.811 |
hler | -0.789 |
cone | -0.773 |
Token |
|
Token ID | 198 |
Feature activation | +5.85e-02 |
Pos logit contributions | |
ochond | +0.324 |
axes | +0.324 |
escription | +0.323 |
pollut | +0.311 |
opsis | +0.307 |
Neg logit contributions | |
util | -0.331 |
onen | -0.318 |
idium | -0.308 |
hler | -0.301 |
cone | -0.295 |
Token | ' |
Token ID | 705 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
axes | +1.958 |
ochond | +1.890 |
acceler | +1.836 |
pollut | +1.834 |
OTOS | +1.810 |
Neg logit contributions | |
util | -2.643 |
onen | -2.611 |
idium | -2.544 |
hler | -2.479 |
cone | -2.430 |
Token | 44 |
Token ID | 2598 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
axes | +2.372 |
ochond | +2.361 |
OTOS | +2.271 |
pollut | +2.264 |
acceler | +2.255 |
Neg logit contributions | |
util | -1.881 |
idium | -1.811 |
onen | -1.804 |
hler | -1.688 |
ussen | -1.673 |
Token | ' |
Token ID | 6 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
axes | +1.511 |
ochond | +1.462 |
pollut | +1.434 |
acceler | +1.418 |
OTOS | +1.413 |
Neg logit contributions | |
util | -1.637 |
onen | -1.631 |
idium | -1.583 |
hler | -1.505 |
cone | -1.475 |
Token | on |
Token ID | 319 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
util | +0.353 |
onen | +0.344 |
idium | +0.337 |
hler | +0.327 |
cone | +0.320 |
Neg logit contributions | |
axes | -0.328 |
ochond | -0.327 |
OTOS | -0.311 |
opsis | -0.311 |
pollut | -0.310 |
Token | sleeve |
Token ID | 23179 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
axes | +3.959 |
ochond | +3.742 |
opsis | +3.606 |
OTOS | +3.603 |
acceler | +3.590 |
Neg logit contributions | |
onen | -6.012 |
util | -5.977 |
idium | -5.730 |
hler | -5.598 |
irtual | -5.574 |
Token | at |
Token ID | 379 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
axes | +2.587 |
ochond | +2.547 |
OTOS | +2.524 |
opsis | +2.466 |
acceler | +2.465 |
Neg logit contributions | |
util | -3.464 |
idium | -3.388 |
onen | -3.377 |
cone | -3.250 |
hler | -3.234 |
Token | basketball |
Token ID | 9669 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
axes | +2.253 |
ochond | +2.240 |
OTOS | +2.138 |
pollut | +2.135 |
opsis | +2.134 |
Neg logit contributions | |
util | -2.200 |
onen | -2.141 |
idium | -2.099 |
hler | -2.032 |
cone | -1.981 |
Token | game |
Token ID | 983 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
axes | +3.418 |
ochond | +3.315 |
pollut | +3.207 |
acceler | +3.191 |
OTOS | +3.153 |
Neg logit contributions | |
util | -4.020 |
onen | -3.902 |
idium | -3.867 |
hler | -3.774 |
avorite | -3.677 |
Token | MORE |
Token ID | 12011 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
axes | +2.302 |
ochond | +2.271 |
OTOS | +2.228 |
acceler | +2.200 |
pollut | +2.182 |
Neg logit contributions | |
util | -3.401 |
idium | -3.301 |
onen | -3.257 |
irtual | -3.173 |
avorite | -3.143 |
Token | and |
Token ID | 290 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
axes | +2.404 |
ochond | +2.344 |
OTOS | +2.253 |
acceler | +2.251 |
pollut | +2.243 |
Neg logit contributions | |
util | -3.174 |
onen | -3.115 |
idium | -3.069 |
hler | -2.928 |
cone | -2.927 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
axes | +2.748 |
ochond | +2.666 |
pollut | +2.563 |
acceler | +2.562 |
OTOS | +2.540 |
Neg logit contributions | |
util | -3.428 |
onen | -3.393 |
idium | -3.326 |
hler | -3.187 |
cone | -3.146 |
Token | don |
Token ID | 836 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
util | +0.205 |
onen | +0.200 |
idium | +0.196 |
hler | +0.190 |
cone | +0.186 |
Neg logit contributions | |
axes | -0.173 |
ochond | -0.173 |
OTOS | -0.164 |
opsis | -0.164 |
pollut | -0.163 |
Token | � |
Token ID | 447 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
util | +1.550 |
onen | +1.504 |
hler | +1.399 |
idium | +1.395 |
cone | +1.317 |
Neg logit contributions | |
escription | -2.200 |
axes | -2.149 |
ochond | -2.137 |
pollut | -2.093 |
OTOS | -2.069 |
Token | � |
Token ID | 247 |
Feature activation | -7.22e-02 |
Pos logit contributions | |
axes | +1.665 |
ochond | +1.653 |
OTOS | +1.584 |
opsis | +1.581 |
acceler | +1.579 |
Neg logit contributions | |
util | -1.505 |
onen | -1.468 |
idium | -1.432 |
hler | -1.376 |
cone | -1.350 |
Token | t |
Token ID | 83 |
Feature activation | +8.73e-02 |
Pos logit contributions | |
axes | +0.684 |
ochond | +0.683 |
opsis | +0.648 |
OTOS | +0.646 |
pollut | +0.645 |
Neg logit contributions | |
util | -0.746 |
onen | -0.728 |
idium | -0.713 |
hler | -0.690 |
cone | -0.676 |
Token | short |
Token ID | 1790 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
util | +0.982 |
onen | +0.955 |
idium | +0.939 |
hler | +0.916 |
cone | +0.893 |
Neg logit contributions | |
ochond | -0.748 |
axes | -0.746 |
OTOS | -0.722 |
escription | -0.708 |
opsis | -0.704 |
Token | change |
Token ID | 3803 |
Feature activation | -7.44e-02 |
Pos logit contributions | |
axes | +0.983 |
ochond | +0.979 |
pollut | +0.929 |
opsis | +0.929 |
OTOS | +0.928 |
Neg logit contributions | |
util | -1.085 |
onen | -1.060 |
idium | -1.043 |
hler | -1.010 |
cone | -0.987 |
Token | the |
Token ID | 262 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
axes | +0.623 |
ochond | +0.620 |
OTOS | +0.586 |
opsis | +0.584 |
pollut | +0.584 |
Neg logit contributions | |
util | -0.854 |
onen | -0.835 |
idium | -0.821 |
hler | -0.797 |
cone | -0.782 |
Token | race |
Token ID | 3234 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
util | +2.249 |
onen | +2.225 |
idium | +2.179 |
hler | +2.124 |
cone | +2.057 |
Neg logit contributions | |
ochond | -1.707 |
axes | -1.673 |
opsis | -1.636 |
OTOS | -1.632 |
escription | -1.629 |
Token | . |
Token ID | 13 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
util | +1.077 |
onen | +1.055 |
idium | +1.030 |
hler | +1.001 |
cone | +0.978 |
Neg logit contributions | |
ochond | -0.946 |
axes | -0.941 |
OTOS | -0.904 |
pollut | -0.895 |
opsis | -0.893 |
Token | They |
Token ID | 1119 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
axes | +0.203 |
ochond | +0.202 |
OTOS | +0.192 |
opsis | +0.191 |
pollut | +0.191 |
Neg logit contributions | |
util | -0.233 |
onen | -0.228 |
idium | -0.223 |
hler | -0.216 |
cone | -0.212 |
Token | criticized |
Token ID | 12318 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
util | +0.350 |
onen | +0.342 |
idium | +0.335 |
hler | +0.326 |
cone | +0.318 |
Neg logit contributions | |
axes | -0.296 |
ochond | -0.295 |
OTOS | -0.282 |
opsis | -0.280 |
pollut | -0.280 |
Token | ( |
Token ID | 357 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
axes | +0.057 |
ochond | +0.057 |
OTOS | +0.054 |
opsis | +0.054 |
pollut | +0.054 |
Neg logit contributions | |
util | -0.062 |
onen | -0.060 |
idium | -0.059 |
hler | -0.057 |
cone | -0.056 |
Token | 31 |
Token ID | 3132 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
util | +3.533 |
onen | +3.340 |
idium | +3.275 |
hler | +3.181 |
cone | +3.118 |
Neg logit contributions | |
ochond | -4.445 |
axes | -4.406 |
pollut | -4.311 |
opsis | -4.260 |
acceler | -4.230 |
Token | ) |
Token ID | 8 |
Feature activation | -5.20e-03 |
Pos logit contributions | |
util | +4.071 |
onen | +3.959 |
idium | +3.899 |
hler | +3.788 |
cone | +3.700 |
Neg logit contributions | |
ochond | -3.365 |
axes | -3.354 |
opsis | -3.188 |
OTOS | -3.187 |
pollut | -3.179 |
Token |
|
Token ID | 198 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
axes | +0.046 |
ochond | +0.045 |
OTOS | +0.043 |
acceler | +0.043 |
opsis | +0.043 |
Neg logit contributions | |
util | -0.058 |
onen | -0.057 |
idium | -0.055 |
hler | -0.054 |
cone | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
util | +2.980 |
onen | +2.725 |
hler | +2.583 |
idium | +2.539 |
cone | +2.517 |
Neg logit contributions | |
escription | -4.501 |
axes | -3.996 |
ochond | -3.996 |
dilig | -3.971 |
pollut | -3.953 |
Token | Save |
Token ID | 16928 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
util | +0.076 |
onen | +0.074 |
idium | +0.072 |
hler | +0.069 |
cone | +0.067 |
Neg logit contributions | |
axes | -0.123 |
ochond | -0.123 |
opsis | -0.118 |
pollut | -0.118 |
OTOS | -0.118 |
Token | a |
Token ID | 257 |
Feature activation | -5.78e-03 |
Pos logit contributions | |
axes | +1.403 |
ochond | +1.394 |
OTOS | +1.326 |
pollut | +1.322 |
acceler | +1.321 |
Neg logit contributions | |
util | -1.619 |
onen | -1.583 |
idium | -1.549 |
hler | -1.512 |
cone | -1.475 |
Token | turret |
Token ID | 28101 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
axes | +0.052 |
ochond | +0.052 |
OTOS | +0.049 |
opsis | +0.049 |
pollut | +0.049 |
Neg logit contributions | |
util | -0.063 |
onen | -0.061 |
idium | -0.060 |
hler | -0.058 |
cone | -0.057 |
Token | from |
Token ID | 422 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
axes | +1.273 |
ochond | +1.262 |
opsis | +1.199 |
OTOS | +1.199 |
acceler | +1.196 |
Neg logit contributions | |
util | -1.598 |
onen | -1.560 |
idium | -1.533 |
hler | -1.491 |
cone | -1.455 |
Token | redemption |
Token ID | 26831 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
axes | +0.710 |
ochond | +0.704 |
OTOS | +0.667 |
pollut | +0.666 |
acceler | +0.666 |
Neg logit contributions | |
util | -0.935 |
onen | -0.915 |
idium | -0.898 |
hler | -0.874 |
cone | -0.855 |
Token | ( |
Token ID | 357 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
axes | +1.158 |
ochond | +1.145 |
OTOS | +1.091 |
opsis | +1.091 |
acceler | +1.090 |
Neg logit contributions | |
util | -1.322 |
onen | -1.290 |
idium | -1.263 |
hler | -1.232 |
cone | -1.200 |
Token | said |
Token ID | 531 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
util | +0.888 |
onen | +0.864 |
idium | +0.846 |
hler | +0.818 |
cone | +0.798 |
Neg logit contributions | |
ochond | -0.966 |
axes | -0.959 |
OTOS | -0.922 |
escription | -0.917 |
opsis | -0.917 |
Token | the |
Token ID | 262 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
util | +1.516 |
onen | +1.475 |
idium | +1.450 |
hler | +1.413 |
cone | +1.381 |
Neg logit contributions | |
ochond | -1.285 |
axes | -1.279 |
opsis | -1.216 |
OTOS | -1.213 |
pollut | -1.209 |
Token | board |
Token ID | 3096 |
Feature activation | -6.93e-02 |
Pos logit contributions | |
util | +1.689 |
onen | +1.645 |
idium | +1.617 |
hler | +1.574 |
cone | +1.541 |
Neg logit contributions | |
ochond | -1.443 |
axes | -1.418 |
opsis | -1.369 |
OTOS | -1.364 |
escription | -1.356 |
Token | 's |
Token ID | 338 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
axes | +0.629 |
ochond | +0.627 |
OTOS | +0.596 |
opsis | +0.594 |
pollut | +0.593 |
Neg logit contributions | |
util | -0.747 |
onen | -0.729 |
idium | -0.715 |
hler | -0.694 |
cone | -0.680 |
Token | ruling |
Token ID | 6922 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
util | +1.202 |
onen | +1.168 |
idium | +1.150 |
hler | +1.113 |
cone | +1.086 |
Neg logit contributions | |
ochond | -1.109 |
axes | -1.094 |
OTOS | -1.056 |
opsis | -1.050 |
pollut | -1.040 |
Token | went |
Token ID | 1816 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
axes | +1.137 |
ochond | +1.126 |
acceler | +1.069 |
opsis | +1.067 |
pollut | +1.067 |
Neg logit contributions | |
util | -1.431 |
onen | -1.398 |
idium | -1.373 |
hler | -1.332 |
cone | -1.304 |
Token | the |
Token ID | 262 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
axes | +0.520 |
ochond | +0.518 |
OTOS | +0.489 |
opsis | +0.488 |
pollut | +0.487 |
Neg logit contributions | |
util | -0.756 |
onen | -0.740 |
idium | -0.727 |
hler | -0.708 |
cone | -0.694 |
Token | right |
Token ID | 826 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
axes | +1.056 |
ochond | +1.035 |
pollut | +0.992 |
acceler | +0.990 |
OTOS | +0.989 |
Neg logit contributions | |
util | -1.214 |
onen | -1.180 |
idium | -1.162 |
hler | -1.125 |
cone | -1.097 |
Token | way |
Token ID | 835 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
ochond | +0.115 |
axes | +0.114 |
OTOS | +0.109 |
opsis | +0.109 |
pollut | +0.108 |
Neg logit contributions | |
util | -0.136 |
onen | -0.134 |
idium | -0.131 |
hler | -0.127 |
cone | -0.125 |
Token | . |
Token ID | 13 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
util | +1.621 |
onen | +1.582 |
idium | +1.542 |
hler | +1.500 |
cone | +1.485 |
Neg logit contributions | |
ochond | -1.561 |
axes | -1.547 |
OTOS | -1.485 |
pollut | -1.475 |
opsis | -1.471 |
Token | He |
Token ID | 679 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
axes | +0.149 |
ochond | +0.149 |
OTOS | +0.144 |
opsis | +0.142 |
acceler | +0.140 |
Neg logit contributions | |
util | -0.202 |
onen | -0.198 |
idium | -0.196 |
hler | -0.189 |
avorite | -0.187 |
Token | Warning |
Token ID | 20361 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
ochond | +0.752 |
axes | +0.748 |
OTOS | +0.727 |
opsis | +0.724 |
pollut | +0.720 |
Neg logit contributions | |
util | -0.368 |
onen | -0.361 |
idium | -0.350 |
hler | -0.332 |
cone | -0.324 |
Token | - |
Token ID | 532 |
Feature activation | +9.56e-02 |
Pos logit contributions | |
onen | +0.324 |
util | +0.322 |
idium | +0.314 |
hler | +0.308 |
cone | +0.301 |
Neg logit contributions | |
ochond | -0.300 |
axes | -0.298 |
pollut | -0.283 |
OTOS | -0.283 |
opsis | -0.282 |
Token | Message |
Token ID | 12837 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
util | +0.885 |
onen | +0.831 |
idium | +0.814 |
hler | +0.788 |
cone | +0.757 |
Neg logit contributions | |
axes | -1.055 |
ochond | -1.030 |
escription | -1.017 |
pollut | -1.013 |
acceler | -1.011 |
Token | " |
Token ID | 366 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
ochond | +1.674 |
axes | +1.645 |
escription | +1.568 |
OTOS | +1.560 |
opsis | +1.557 |
Neg logit contributions | |
onen | -2.151 |
util | -2.123 |
idium | -2.085 |
hler | -2.046 |
cone | -2.031 |
Token | F |
Token ID | 37 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
axes | +2.376 |
ochond | +2.326 |
OTOS | +2.260 |
opsis | +2.235 |
acceler | +2.228 |
Neg logit contributions | |
util | -1.873 |
onen | -1.863 |
idium | -1.845 |
hler | -1.765 |
cone | -1.714 |
Token | ailed |
Token ID | 6255 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
axes | +2.912 |
ochond | +2.906 |
OTOS | +2.812 |
pollut | +2.808 |
acceler | +2.804 |
Neg logit contributions | |
util | -1.207 |
onen | -1.151 |
idium | -1.108 |
hler | -1.046 |
cone | -0.999 |
Token | to |
Token ID | 284 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
axes | +3.727 |
escription | +3.412 |
acceler | +3.368 |
ochond | +3.306 |
opsis | +3.154 |
Neg logit contributions | |
onen | -8.581 |
idium | -8.554 |
ussen | -8.472 |
util | -8.113 |
hler | -8.026 |
Token | $ |
Token ID | 720 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
axes | +4.003 |
acceler | +3.620 |
pollut | +3.597 |
ochond | +3.576 |
opsis | +3.567 |
Neg logit contributions | |
idium | -6.341 |
onen | -6.223 |
util | -6.186 |
ussen | -6.007 |
hler | -6.000 |
Token | ($ |
Token ID | 16763 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
axes | +2.919 |
ochond | +2.896 |
opsis | +2.807 |
OTOS | +2.795 |
escription | +2.742 |
Neg logit contributions | |
idium | -3.406 |
util | -3.405 |
onen | -3.400 |
hler | -3.224 |
ussen | -3.193 |
Token | _. |
Token ID | 44807 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
axes | +4.903 |
ochond | +4.873 |
opsis | +4.784 |
OTOS | +4.753 |
escription | +4.687 |
Neg logit contributions | |
idium | -2.775 |
onen | -2.742 |
util | -2.653 |
hler | -2.510 |
ussen | -2.498 |
Token | Exception |
Token ID | 16922 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
axes | +2.120 |
ochond | +2.090 |
OTOS | +2.030 |
opsis | +2.015 |
acceler | +1.986 |
Neg logit contributions | |
util | -1.827 |
onen | -1.802 |
idium | -1.776 |
hler | -1.708 |
ilogy | -1.665 |
Token | thought |
Token ID | 1807 |
Feature activation | -7.29e-02 |
Pos logit contributions | |
util | +0.912 |
onen | +0.878 |
idium | +0.858 |
hler | +0.845 |
cone | +0.821 |
Neg logit contributions | |
ochond | -0.868 |
axes | -0.847 |
OTOS | -0.842 |
escription | -0.830 |
opsis | -0.822 |
Token | he |
Token ID | 339 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
axes | +0.642 |
ochond | +0.638 |
OTOS | +0.604 |
pollut | +0.602 |
opsis | +0.602 |
Neg logit contributions | |
util | -0.807 |
onen | -0.789 |
idium | -0.774 |
hler | -0.752 |
cone | -0.736 |
Token | 'd |
Token ID | 1549 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
axes | +0.499 |
ochond | +0.496 |
OTOS | +0.466 |
opsis | +0.466 |
pollut | +0.465 |
Neg logit contributions | |
util | -0.771 |
onen | -0.755 |
idium | -0.742 |
hler | -0.722 |
cone | -0.709 |
Token | be |
Token ID | 307 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
axes | +1.115 |
ochond | +1.105 |
acceler | +1.035 |
opsis | +1.035 |
pollut | +1.034 |
Neg logit contributions | |
util | -1.850 |
onen | -1.816 |
idium | -1.790 |
hler | -1.736 |
cone | -1.711 |
Token | a |
Token ID | 257 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
util | +1.103 |
onen | +1.077 |
idium | +1.046 |
hler | +1.033 |
cone | +1.009 |
Neg logit contributions | |
ochond | -0.924 |
axes | -0.909 |
OTOS | -0.882 |
opsis | -0.879 |
escription | -0.869 |
Token | hockey |
Token ID | 12217 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
util | +1.461 |
onen | +1.439 |
idium | +1.392 |
hler | +1.368 |
cone | +1.329 |
Neg logit contributions | |
ochond | -1.322 |
axes | -1.313 |
OTOS | -1.271 |
opsis | -1.264 |
escription | -1.242 |
Token | dad |
Token ID | 9955 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
axes | +4.249 |
ochond | +4.108 |
acceler | +3.952 |
pollut | +3.928 |
OTOS | +3.602 |
Neg logit contributions | |
util | -7.772 |
idium | -7.616 |
onen | -7.616 |
irtual | -7.315 |
ilogy | -7.304 |
Token | when |
Token ID | 618 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
axes | +1.837 |
ochond | +1.819 |
acceler | +1.729 |
opsis | +1.728 |
OTOS | +1.722 |
Neg logit contributions | |
util | -2.261 |
onen | -2.208 |
idium | -2.174 |
hler | -2.105 |
cone | -2.067 |
Token | his |
Token ID | 465 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
axes | +2.330 |
ochond | +2.237 |
acceler | +2.154 |
OTOS | +2.131 |
pollut | +2.110 |
Neg logit contributions | |
util | -3.367 |
onen | -3.288 |
idium | -3.220 |
hler | -3.125 |
ilogy | -3.093 |
Token | kids |
Token ID | 3988 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
axes | +0.528 |
ochond | +0.526 |
OTOS | +0.499 |
opsis | +0.498 |
pollut | +0.498 |
Neg logit contributions | |
util | -0.614 |
onen | -0.599 |
idium | -0.587 |
hler | -0.570 |
cone | -0.558 |
Token | were |
Token ID | 547 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
axes | +0.106 |
ochond | +0.106 |
OTOS | +0.101 |
opsis | +0.100 |
pollut | +0.100 |
Neg logit contributions | |
util | -0.125 |
onen | -0.122 |
idium | -0.120 |
hler | -0.116 |
cone | -0.114 |
Token | connection |
Token ID | 38659 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
axes | +3.049 |
ochond | +2.922 |
opsis | +2.777 |
pollut | +2.700 |
acceler | +2.695 |
Neg logit contributions | |
util | -6.422 |
onen | -6.337 |
idium | -6.269 |
avorite | -6.195 |
hler | -6.157 |
Token | ( |
Token ID | 357 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
util | +0.162 |
onen | +0.158 |
idium | +0.155 |
hler | +0.150 |
cone | +0.147 |
Neg logit contributions | |
axes | -0.149 |
ochond | -0.148 |
OTOS | -0.141 |
opsis | -0.140 |
pollut | -0.140 |
Token | OS |
Token ID | 2640 |
Feature activation | -4.36e-02 |
Pos logit contributions | |
ochond | +2.521 |
axes | +2.515 |
OTOS | +2.457 |
opsis | +2.395 |
acceler | +2.371 |
Neg logit contributions | |
util | -2.713 |
idium | -2.636 |
onen | -2.630 |
hler | -2.562 |
ilogy | -2.521 |
Token | I |
Token ID | 40 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
axes | +0.470 |
ochond | +0.468 |
OTOS | +0.448 |
opsis | +0.447 |
pollut | +0.447 |
Neg logit contributions | |
util | -0.397 |
onen | -0.386 |
idium | -0.377 |
hler | -0.364 |
cone | -0.355 |
Token | ) |
Token ID | 8 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
axes | +3.248 |
ochond | +3.076 |
acceler | +2.999 |
OTOS | +2.932 |
pollut | +2.901 |
Neg logit contributions | |
util | -4.382 |
onen | -4.333 |
idium | -4.275 |
avorite | -4.204 |
hler | -4.117 |
Token | layers |
Token ID | 11685 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
axes | +1.018 |
ochond | +0.995 |
acceler | +0.949 |
pollut | +0.945 |
OTOS | +0.939 |
Neg logit contributions | |
util | -1.288 |
onen | -1.261 |
idium | -1.237 |
hler | -1.203 |
cone | -1.177 |
Token | . |
Token ID | 13 |
Feature activation | -2.45e-04 |
Pos logit contributions | |
axes | +4.473 |
ochond | +4.293 |
acceler | +4.212 |
opsis | +4.054 |
pollut | +4.023 |
Neg logit contributions | |
util | -6.115 |
onen | -6.035 |
idium | -5.967 |
ilogy | -5.782 |
hler | -5.731 |
Token | Second |
Token ID | 5498 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
axes | +0.002 |
ochond | +0.002 |
OTOS | +0.002 |
opsis | +0.002 |
pollut | +0.002 |
Neg logit contributions | |
util | -0.003 |
onen | -0.003 |
idium | -0.002 |
hler | -0.002 |
cone | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
util | +1.294 |
onen | +1.264 |
idium | +1.238 |
hler | +1.206 |
cone | +1.174 |
Neg logit contributions | |
axes | -1.068 |
ochond | -1.063 |
OTOS | -1.005 |
opsis | -1.005 |
acceler | -1.003 |
Token | attacks |
Token ID | 3434 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
util | +2.311 |
onen | +2.256 |
idium | +2.200 |
hler | +2.129 |
cone | +2.098 |
Neg logit contributions | |
ochond | -1.983 |
axes | -1.962 |
escription | -1.896 |
opsis | -1.889 |
OTOS | -1.872 |
Token | from |
Token ID | 422 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
util | +1.349 |
onen | +1.314 |
idium | +1.284 |
hler | +1.254 |
cone | +1.234 |
Neg logit contributions | |
ochond | -1.086 |
axes | -1.085 |
OTOS | -1.046 |
opsis | -1.031 |
pollut | -1.025 |
Token | ' |
Token ID | 6 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
util | +2.093 |
idium | +2.072 |
hler | +1.947 |
cone | +1.937 |
ussen | +1.929 |
Neg logit contributions | |
ochond | -2.821 |
OTOS | -2.793 |
escription | -2.694 |
axes | -2.660 |
opsis | -2.577 |
Token | 2016 |
Token ID | 1584 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
util | +1.949 |
onen | +1.904 |
idium | +1.868 |
hler | +1.814 |
cone | +1.778 |
Neg logit contributions | |
axes | -1.584 |
ochond | -1.579 |
OTOS | -1.498 |
opsis | -1.494 |
pollut | -1.491 |
Token | primary |
Token ID | 4165 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
axes | +0.878 |
pollut | +0.846 |
acceler | +0.836 |
ochond | +0.813 |
opsis | +0.808 |
Neg logit contributions | |
util | -1.409 |
onen | -1.368 |
idium | -1.342 |
hler | -1.319 |
avorite | -1.306 |
Token | Sanders |
Token ID | 5831 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
axes | +2.347 |
acceler | +2.210 |
opsis | +2.176 |
pollut | +2.163 |
ochond | +2.159 |
Neg logit contributions | |
util | -2.586 |
onen | -2.533 |
idium | -2.429 |
irtual | -2.363 |
hler | -2.338 |
Token | : |
Token ID | 25 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
axes | +0.143 |
ochond | +0.137 |
acceler | +0.134 |
pollut | +0.133 |
OTOS | +0.131 |
Neg logit contributions | |
util | -0.218 |
onen | -0.214 |
idium | -0.209 |
hler | -0.206 |
cone | -0.201 |
Token | ' |
Token ID | 705 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
axes | +0.948 |
acceler | +0.911 |
ochond | +0.896 |
pollut | +0.873 |
opsis | +0.871 |
Neg logit contributions | |
util | -1.904 |
onen | -1.866 |
idium | -1.818 |
cone | -1.798 |
avorite | -1.787 |
Token | Damn |
Token ID | 43343 |
Feature activation | +4.11e-03 |
Pos logit contributions | |
axes | +5.190 |
ochond | +4.640 |
acceler | +4.589 |
OTOS | +4.382 |
ait | +4.355 |
Neg logit contributions | |
avorite | -7.026 |
util | -6.871 |
onen | -6.643 |
unia | -6.457 |
idium | -6.345 |
Token | right |
Token ID | 826 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
util | +0.045 |
onen | +0.044 |
idium | +0.044 |
hler | +0.042 |
cone | +0.042 |
Neg logit contributions | |
axes | -0.037 |
ochond | -0.036 |
pollut | -0.034 |
opsis | -0.034 |
acceler | -0.034 |
Token | ' |
Token ID | 6 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
util | +0.689 |
onen | +0.676 |
idium | +0.661 |
hler | +0.644 |
cone | +0.630 |
Neg logit contributions | |
axes | -0.535 |
ochond | -0.534 |
OTOS | -0.507 |
opsis | -0.504 |
pollut | -0.502 |
Token | I |
Token ID | 314 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
axes | +0.814 |
ochond | +0.799 |
acceler | +0.787 |
OTOS | +0.777 |
pollut | +0.766 |
Neg logit contributions | |
util | -1.250 |
onen | -1.224 |
idium | -1.202 |
avorite | -1.171 |
cone | -1.165 |
Token | 'll |
Token ID | 1183 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
axes | +3.087 |
ochond | +2.986 |
acceler | +2.858 |
pollut | +2.834 |
opsis | +2.774 |
Neg logit contributions | |
onen | -4.149 |
util | -4.013 |
idium | -3.933 |
irtual | -3.846 |
hler | -3.813 |
Token | T |
Token ID | 51 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
axes | +2.690 |
ochond | +2.682 |
OTOS | +2.567 |
escription | +2.558 |
acceler | +2.548 |
Neg logit contributions | |
util | -2.264 |
onen | -2.249 |
idium | -2.191 |
hler | -2.113 |
ussen | -2.102 |
Token | ( |
Token ID | 7 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
axes | +0.231 |
ochond | +0.228 |
pollut | +0.216 |
OTOS | +0.216 |
acceler | +0.216 |
Neg logit contributions | |
util | -0.303 |
onen | -0.301 |
idium | -0.297 |
hler | -0.288 |
cone | -0.280 |
Token | t |
Token ID | 83 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
axes | +2.253 |
ochond | +2.243 |
OTOS | +2.142 |
opsis | +2.135 |
pollut | +2.133 |
Neg logit contributions | |
util | -2.347 |
onen | -2.283 |
idium | -2.237 |
hler | -2.168 |
cone | -2.121 |
Token | )- |
Token ID | 13219 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
util | +0.945 |
onen | +0.934 |
idium | +0.918 |
hler | +0.887 |
cone | +0.869 |
Neg logit contributions | |
ochond | -0.804 |
axes | -0.803 |
opsis | -0.755 |
OTOS | -0.749 |
escription | -0.748 |
Token | T |
Token ID | 309 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
axes | +1.525 |
ochond | +1.521 |
OTOS | +1.457 |
acceler | +1.435 |
pollut | +1.435 |
Neg logit contributions | |
util | -2.295 |
onen | -2.281 |
idium | -2.226 |
hler | -2.168 |
cone | -2.148 |
Token | 0 |
Token ID | 657 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
axes | +2.003 |
ochond | +1.911 |
acceler | +1.849 |
OTOS | +1.838 |
pollut | +1.835 |
Neg logit contributions | |
util | -3.603 |
onen | -3.580 |
idium | -3.503 |
hler | -3.444 |
cone | -3.386 |
Token | ) |
Token ID | 1267 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
axes | +2.650 |
ochond | +2.411 |
acceler | +2.224 |
pollut | +2.109 |
OTOS | +2.049 |
Neg logit contributions | |
onen | -10.717 |
util | -10.278 |
idium | -10.169 |
cone | -9.966 |
illance | -9.943 |
Token |
|
Token ID | 198 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
axes | +4.391 |
ochond | +4.233 |
acceler | +4.148 |
pollut | +4.090 |
opsis | +3.980 |
Neg logit contributions | |
onen | -5.676 |
util | -5.653 |
idium | -5.516 |
hler | -5.340 |
avorite | -5.265 |
Token |
|
Token ID | 198 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
axes | +2.312 |
ochond | +2.303 |
OTOS | +2.186 |
opsis | +2.181 |
pollut | +2.174 |
Neg logit contributions | |
util | -2.836 |
onen | -2.773 |
idium | -2.725 |
hler | -2.642 |
cone | -2.589 |
Token | The |
Token ID | 464 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
axes | +3.904 |
ochond | +3.883 |
OTOS | +3.700 |
pollut | +3.685 |
opsis | +3.677 |
Neg logit contributions | |
util | -4.240 |
onen | -4.228 |
idium | -4.158 |
avorite | -4.021 |
hler | -4.008 |
Token | year |
Token ID | 614 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
axes | +1.780 |
ochond | +1.752 |
acceler | +1.677 |
pollut | +1.677 |
opsis | +1.652 |
Neg logit contributions | |
util | -2.269 |
onen | -2.207 |
idium | -2.175 |
hler | -2.111 |
cone | -2.070 |