Token | resolve |
Token ID | 10568 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
own | +0.446 |
ally | +0.433 |
error | +0.431 |
STE | +0.429 |
brand | +0.420 |
Neg logit contributions | |
arag | -0.373 |
entary | -0.352 |
hran | -0.334 |
chens | -0.318 |
ptic | -0.305 |
Token | the |
Token ID | 262 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
arag | +0.779 |
entary | +0.736 |
hran | +0.700 |
chens | +0.672 |
ptic | +0.655 |
Neg logit contributions | |
own | -0.844 |
error | -0.819 |
STE | -0.817 |
ally | -0.809 |
brand | -0.797 |
Token | mess |
Token ID | 2085 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
own | +0.378 |
error | +0.367 |
STE | +0.366 |
ally | +0.364 |
brand | +0.357 |
Neg logit contributions | |
arag | -0.295 |
entary | -0.278 |
hran | -0.263 |
chens | -0.251 |
ptic | -0.244 |
Token | over |
Token ID | 625 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
arag | +0.541 |
entary | +0.514 |
hran | +0.490 |
chens | +0.471 |
ptic | +0.460 |
Neg logit contributions | |
own | -0.523 |
error | -0.507 |
STE | -0.504 |
ally | -0.502 |
brand | -0.492 |
Token | Mer |
Token ID | 4638 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
arag | +1.173 |
entary | +1.105 |
hran | +1.052 |
chens | +1.007 |
ptic | +0.982 |
Neg logit contributions | |
own | -1.311 |
error | -1.274 |
STE | -1.271 |
ally | -1.260 |
brand | -1.241 |
Token | rick |
Token ID | 5557 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
arag | +2.885 |
entary | +2.742 |
hran | +2.644 |
chens | +2.560 |
ptic | +2.505 |
Neg logit contributions | |
own | -2.243 |
STE | -2.188 |
error | -2.182 |
ally | -2.144 |
Interstitial | -2.111 |
Token | Garland |
Token ID | 35466 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
own | +4.393 |
OWN | +3.750 |
STE | +3.617 |
error | +3.411 |
ally | +3.321 |
Neg logit contributions | |
arag | -12.330 |
hran | -11.974 |
entary | -11.951 |
chens | -11.372 |
ocular | -11.364 |
Token | � |
Token ID | 447 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
own | +0.074 |
error | +0.071 |
STE | +0.071 |
ally | +0.071 |
brand | +0.070 |
Neg logit contributions | |
arag | -0.060 |
entary | -0.057 |
hran | -0.054 |
chens | -0.051 |
ptic | -0.050 |
Token | � |
Token ID | 247 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
arag | +0.540 |
entary | +0.509 |
hran | +0.479 |
chens | +0.456 |
ptic | +0.442 |
Neg logit contributions | |
own | -0.725 |
error | -0.704 |
STE | -0.701 |
ally | -0.699 |
brand | -0.688 |
Token | s |
Token ID | 82 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
arag | +0.805 |
entary | +0.764 |
hran | +0.728 |
chens | +0.700 |
ptic | +0.683 |
Neg logit contributions | |
own | -0.790 |
error | -0.764 |
STE | -0.761 |
ally | -0.757 |
brand | -0.742 |
Token | nomination |
Token ID | 11872 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
own | +1.691 |
error | +1.635 |
ally | +1.631 |
STE | +1.614 |
brand | +1.577 |
Neg logit contributions | |
arag | -1.455 |
entary | -1.386 |
hran | -1.315 |
chens | -1.248 |
ptic | -1.221 |
Token | oppose |
Token ID | 12856 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
arag | +0.269 |
entary | +0.254 |
hran | +0.242 |
chens | +0.230 |
ptic | +0.222 |
Neg logit contributions | |
own | -0.312 |
error | -0.303 |
ally | -0.302 |
STE | -0.301 |
brand | -0.295 |
Token | the |
Token ID | 262 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
arag | +1.913 |
entary | +1.806 |
hran | +1.704 |
chens | +1.636 |
ptic | +1.598 |
Neg logit contributions | |
own | -2.259 |
error | -2.200 |
STE | -2.185 |
ally | -2.168 |
brand | -2.137 |
Token | confirmation |
Token ID | 12641 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
arag | +0.413 |
entary | +0.391 |
hran | +0.370 |
chens | +0.354 |
ptic | +0.344 |
Neg logit contributions | |
own | -0.500 |
error | -0.485 |
STE | -0.483 |
ally | -0.481 |
brand | -0.472 |
Token | of |
Token ID | 286 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
own | +0.899 |
ally | +0.875 |
STE | +0.869 |
error | +0.866 |
brand | +0.849 |
Neg logit contributions | |
arag | -0.709 |
entary | -0.668 |
hran | -0.634 |
chens | -0.608 |
ptic | -0.586 |
Token | Mer |
Token ID | 4638 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
own | +0.787 |
ally | +0.768 |
STE | +0.768 |
error | +0.760 |
brand | +0.745 |
Neg logit contributions | |
arag | -0.698 |
entary | -0.662 |
hran | -0.635 |
chens | -0.601 |
ptic | -0.578 |
Token | rick |
Token ID | 5557 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
arag | +1.699 |
entary | +1.635 |
hran | +1.578 |
chens | +1.534 |
ptic | +1.507 |
Neg logit contributions | |
own | -0.820 |
error | -0.780 |
STE | -0.774 |
ally | -0.768 |
brand | -0.744 |
Token | Garland |
Token ID | 35466 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
own | +4.540 |
STE | +4.049 |
OWN | +4.040 |
ally | +3.754 |
error | +3.712 |
Neg logit contributions | |
arag | -11.689 |
hran | -11.669 |
entary | -11.213 |
ocular | -10.837 |
chens | -10.767 |
Token | to |
Token ID | 284 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
own | +0.610 |
STE | +0.590 |
error | +0.587 |
ally | +0.586 |
brand | +0.575 |
Neg logit contributions | |
arag | -0.548 |
entary | -0.522 |
hran | -0.499 |
chens | -0.473 |
ptic | -0.460 |
Token | the |
Token ID | 262 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
arag | +0.357 |
entary | +0.339 |
hran | +0.325 |
chens | +0.309 |
ptic | +0.301 |
Neg logit contributions | |
own | -0.366 |
error | -0.354 |
STE | -0.352 |
ally | -0.351 |
brand | -0.343 |
Token | Supreme |
Token ID | 5617 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
own | +0.380 |
error | +0.370 |
ally | +0.369 |
STE | +0.368 |
brand | +0.358 |
Neg logit contributions | |
arag | -0.316 |
entary | -0.298 |
hran | -0.286 |
chens | -0.272 |
ptic | -0.261 |
Token | Court |
Token ID | 3078 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
arag | +2.990 |
entary | +2.803 |
hran | +2.616 |
chens | +2.548 |
ptic | +2.495 |
Neg logit contributions | |
own | -3.765 |
STE | -3.666 |
error | -3.650 |
Interstitial | -3.582 |
brand | -3.563 |
Token | it |
Token ID | 270 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
own | +0.333 |
error | +0.322 |
STE | +0.321 |
ally | +0.320 |
brand | +0.313 |
Neg logit contributions | |
arag | -0.332 |
entary | -0.316 |
hran | -0.300 |
chens | -0.289 |
ptic | -0.282 |
Token | ou |
Token ID | 280 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
own | +0.442 |
error | +0.423 |
STE | +0.418 |
ally | +0.418 |
brand | +0.407 |
Neg logit contributions | |
arag | -0.695 |
entary | -0.666 |
hran | -0.639 |
chens | -0.619 |
ptic | -0.607 |
Token | & |
Token ID | 1222 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
arag | +1.492 |
entary | +1.412 |
hran | +1.342 |
chens | +1.291 |
ptic | +1.256 |
Neg logit contributions | |
own | -1.616 |
error | -1.567 |
STE | -1.562 |
ally | -1.551 |
brand | -1.523 |
Token | Br |
Token ID | 1709 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
own | +0.844 |
error | +0.814 |
STE | +0.810 |
ally | +0.810 |
brand | +0.792 |
Neg logit contributions | |
arag | -0.849 |
entary | -0.809 |
hran | -0.768 |
chens | -0.739 |
ptic | -0.720 |
Token | é |
Token ID | 2634 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
own | +1.906 |
error | +1.817 |
ally | +1.816 |
STE | +1.786 |
brand | +1.763 |
Neg logit contributions | |
arag | -2.484 |
entary | -2.379 |
hran | -2.281 |
chens | -2.212 |
ptic | -2.162 |
Token | on |
Token ID | 261 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
own | +4.283 |
ally | +4.177 |
error | +4.111 |
brand | +4.056 |
STE | +3.957 |
Neg logit contributions | |
arag | -4.324 |
entary | -4.013 |
hran | -3.759 |
chens | -3.631 |
ptic | -3.613 |
Token | assumes |
Token ID | 18533 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
own | +7.962 |
ally | +7.880 |
error | +7.692 |
STE | +7.595 |
brand | +7.585 |
Neg logit contributions | |
arag | -7.508 |
entary | -7.329 |
hran | -6.944 |
ptic | -6.443 |
erate | -6.366 |
Token | that |
Token ID | 326 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
own | +1.269 |
ally | +1.231 |
error | +1.226 |
STE | +1.220 |
brand | +1.181 |
Neg logit contributions | |
arag | -1.373 |
entary | -1.298 |
hran | -1.246 |
chens | -1.189 |
ptic | -1.162 |
Token | the |
Token ID | 262 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
arag | +0.611 |
entary | +0.578 |
hran | +0.550 |
chens | +0.528 |
ptic | +0.514 |
Neg logit contributions | |
own | -0.651 |
error | -0.631 |
STE | -0.628 |
ally | -0.626 |
brand | -0.613 |
Token | air |
Token ID | 1633 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
arag | +0.711 |
entary | +0.671 |
hran | +0.635 |
chens | +0.608 |
ptic | +0.591 |
Neg logit contributions | |
own | -0.864 |
error | -0.839 |
STE | -0.836 |
ally | -0.833 |
brand | -0.816 |
Token | in |
Token ID | 287 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
arag | +0.682 |
entary | +0.645 |
hran | +0.612 |
chens | +0.586 |
ptic | +0.571 |
Neg logit contributions | |
own | -0.771 |
error | -0.748 |
STE | -0.745 |
ally | -0.742 |
brand | -0.728 |
Token | the |
Token ID | 262 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
arag | +2.048 |
entary | +1.937 |
hran | +1.840 |
chens | +1.770 |
ptic | +1.725 |
Neg logit contributions | |
own | -2.205 |
error | -2.145 |
STE | -2.130 |
ally | -2.115 |
brand | -2.082 |
Token | tom |
Token ID | 16667 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
arag | +0.401 |
entary | +0.379 |
hran | +0.360 |
chens | +0.344 |
ptic | +0.335 |
Neg logit contributions | |
own | -0.457 |
error | -0.442 |
STE | -0.441 |
ally | -0.440 |
brand | -0.431 |
Token | bs |
Token ID | 1443 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
arag | +2.731 |
entary | +2.554 |
hran | +2.382 |
chens | +2.273 |
ptic | +2.205 |
Neg logit contributions | |
own | -4.463 |
error | -4.363 |
STE | -4.352 |
ally | -4.317 |
brand | -4.257 |
Token | in |
Token ID | 287 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
arag | +1.739 |
entary | +1.639 |
hran | +1.551 |
chens | +1.487 |
ptic | +1.444 |
Neg logit contributions | |
own | -2.150 |
error | -2.092 |
STE | -2.084 |
ally | -2.069 |
brand | -2.036 |
Token | Mer |
Token ID | 4638 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
arag | +0.678 |
entary | +0.643 |
hran | +0.612 |
chens | +0.587 |
ptic | +0.571 |
Neg logit contributions | |
own | -0.696 |
error | -0.672 |
STE | -0.670 |
ally | -0.666 |
brand | -0.652 |
Token | rick |
Token ID | 5557 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
arag | +1.266 |
entary | +1.204 |
hran | +1.153 |
chens | +1.112 |
ptic | +1.088 |
Neg logit contributions | |
own | -1.085 |
STE | -1.053 |
error | -1.053 |
ally | -1.039 |
brand | -1.018 |
Token | Cemetery |
Token ID | 35637 |
Feature activation | +7.50e-02 |
Pos logit contributions | |
own | +7.515 |
ally | +6.910 |
STE | +6.830 |
OWN | +6.738 |
error | +6.629 |
Neg logit contributions | |
arag | -8.147 |
entary | -7.943 |
hran | -7.723 |
ocular | -6.976 |
chens | -6.972 |
Token | on |
Token ID | 319 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
own | +0.195 |
error | +0.187 |
ally | +0.187 |
STE | +0.187 |
brand | +0.182 |
Neg logit contributions | |
arag | -0.173 |
entary | -0.164 |
hran | -0.155 |
chens | -0.147 |
ptic | -0.144 |
Token | St |
Token ID | 520 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
own | +1.344 |
error | +1.291 |
ally | +1.285 |
STE | +1.284 |
brand | +1.255 |
Neg logit contributions | |
arag | -1.323 |
entary | -1.256 |
hran | -1.197 |
chens | -1.146 |
ptic | -1.115 |
Token | . |
Token ID | 13 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
own | +0.491 |
error | +0.480 |
STE | +0.479 |
ally | +0.473 |
brand | +0.466 |
Neg logit contributions | |
arag | -0.418 |
entary | -0.392 |
hran | -0.371 |
chens | -0.357 |
ptic | -0.347 |
Token | Bernard |
Token ID | 16197 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
own | +0.518 |
error | +0.502 |
STE | +0.499 |
ally | +0.497 |
brand | +0.488 |
Neg logit contributions | |
arag | -0.485 |
entary | -0.459 |
hran | -0.437 |
chens | -0.419 |
ptic | -0.408 |
Token | Misty |
Token ID | 47330 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
arag | +0.113 |
entary | +0.107 |
hran | +0.101 |
chens | +0.097 |
ptic | +0.095 |
Neg logit contributions | |
own | -0.129 |
error | -0.126 |
STE | -0.125 |
ally | -0.125 |
brand | -0.123 |
Token | Mountains |
Token ID | 21124 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
arag | +1.538 |
entary | +1.409 |
hran | +1.331 |
chens | +1.284 |
ptic | +1.210 |
Neg logit contributions | |
own | -2.574 |
error | -2.514 |
STE | -2.483 |
ally | -2.472 |
brand | -2.429 |
Token | through |
Token ID | 832 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
own | +1.044 |
error | +1.010 |
ally | +1.005 |
STE | +1.004 |
brand | +0.986 |
Neg logit contributions | |
arag | -0.957 |
entary | -0.911 |
hran | -0.858 |
chens | -0.827 |
ptic | -0.809 |
Token | the |
Token ID | 262 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
own | +0.768 |
error | +0.744 |
STE | +0.738 |
ally | +0.737 |
brand | +0.722 |
Neg logit contributions | |
arag | -0.730 |
entary | -0.694 |
hran | -0.658 |
chens | -0.634 |
ptic | -0.620 |
Token | Red |
Token ID | 2297 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
own | +0.123 |
error | +0.119 |
STE | +0.119 |
ally | +0.119 |
brand | +0.116 |
Neg logit contributions | |
arag | -0.106 |
entary | -0.101 |
hran | -0.095 |
chens | -0.092 |
ptic | -0.090 |
Token | horn |
Token ID | 25311 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
arag | +0.314 |
entary | +0.295 |
hran | +0.278 |
chens | +0.264 |
ptic | +0.256 |
Neg logit contributions | |
own | -0.449 |
error | -0.437 |
STE | -0.435 |
ally | -0.434 |
brand | -0.427 |
Token | Pass |
Token ID | 6251 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
own | +6.896 |
brand | +6.647 |
ally | +6.631 |
error | +6.470 |
STE | +6.442 |
Neg logit contributions | |
arag | -6.731 |
entary | -6.635 |
hran | -6.089 |
chens | -5.847 |
ptic | -5.830 |
Token | , |
Token ID | 11 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
arag | +1.104 |
entary | +1.044 |
hran | +0.994 |
chens | +0.953 |
ptic | +0.925 |
Neg logit contributions | |
own | -1.233 |
error | -1.195 |
STE | -1.193 |
ally | -1.183 |
brand | -1.161 |
Token | the |
Token ID | 262 |
Feature activation | +7.74e-02 |
Pos logit contributions | |
own | +0.084 |
error | +0.081 |
STE | +0.080 |
ally | +0.080 |
brand | +0.078 |
Neg logit contributions | |
arag | -0.100 |
entary | -0.095 |
hran | -0.091 |
chens | -0.088 |
ptic | -0.086 |
Token | Company |
Token ID | 5834 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
own | +0.190 |
error | +0.185 |
STE | +0.183 |
ally | +0.183 |
brand | +0.179 |
Neg logit contributions | |
arag | -0.187 |
entary | -0.178 |
hran | -0.169 |
chens | -0.163 |
ptic | -0.159 |
Token | are |
Token ID | 389 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
own | +1.715 |
error | +1.663 |
ally | +1.659 |
STE | +1.657 |
brand | +1.629 |
Neg logit contributions | |
arag | -1.460 |
entary | -1.388 |
hran | -1.307 |
chens | -1.249 |
ptic | -1.214 |
Token | the |
Token ID | 262 |
Feature activation | +9.07e-02 |
Pos logit contributions | |
arag | +1.389 |
entary | +1.316 |
hran | +1.250 |
chens | +1.204 |
ptic | +1.172 |
Neg logit contributions | |
own | -1.428 |
error | -1.385 |
STE | -1.379 |
ally | -1.368 |
brand | -1.343 |
Token | team |
Token ID | 1074 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
own | +0.222 |
error | +0.215 |
ally | +0.214 |
STE | +0.214 |
brand | +0.209 |
Neg logit contributions | |
arag | -0.221 |
entary | -0.210 |
hran | -0.200 |
chens | -0.192 |
ptic | -0.187 |
Token | � |
Token ID | 447 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
own | +2.858 |
ally | +2.772 |
error | +2.720 |
STE | +2.692 |
brand | +2.685 |
Neg logit contributions | |
arag | -2.676 |
entary | -2.553 |
hran | -2.394 |
chens | -2.277 |
ptic | -2.222 |
Token | � |
Token ID | 247 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
own | +0.664 |
error | +0.634 |
STE | +0.627 |
ally | +0.627 |
brand | +0.613 |
Neg logit contributions | |
arag | -0.978 |
entary | -0.942 |
hran | -0.897 |
chens | -0.869 |
ptic | -0.850 |
Token | s |
Token ID | 82 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
arag | +0.388 |
entary | +0.368 |
hran | +0.350 |
chens | +0.336 |
ptic | +0.327 |
Neg logit contributions | |
own | -0.407 |
error | -0.395 |
STE | -0.393 |
ally | -0.391 |
brand | -0.384 |
Token | offense |
Token ID | 6907 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
own | +2.286 |
ally | +2.218 |
error | +2.196 |
STE | +2.171 |
brand | +2.132 |
Neg logit contributions | |
arag | -2.206 |
entary | -2.095 |
hran | -2.000 |
chens | -1.912 |
ptic | -1.838 |
Token | , |
Token ID | 11 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
own | +6.579 |
ally | +6.436 |
error | +6.110 |
STE | +6.008 |
brand | +5.983 |
Neg logit contributions | |
arag | -7.109 |
entary | -6.963 |
hran | -6.367 |
chens | -6.161 |
ptic | -6.106 |
Token | especially |
Token ID | 2592 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
arag | +0.827 |
entary | +0.781 |
hran | +0.741 |
chens | +0.710 |
ptic | +0.693 |
Neg logit contributions | |
own | -0.926 |
error | -0.899 |
STE | -0.895 |
ally | -0.891 |
brand | -0.874 |
Token | given |
Token ID | 1813 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
arag | +0.536 |
entary | +0.510 |
hran | +0.486 |
chens | +0.467 |
ptic | +0.456 |
Neg logit contributions | |
own | -0.520 |
error | -0.503 |
STE | -0.500 |
ally | -0.499 |
brand | -0.488 |
Token | his |
Token ID | 465 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
arag | +0.524 |
entary | +0.496 |
hran | +0.472 |
chens | +0.455 |
ptic | +0.443 |
Neg logit contributions | |
own | -0.518 |
error | -0.502 |
STE | -0.501 |
ally | -0.495 |
brand | -0.487 |
Token | excellent |
Token ID | 6275 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
own | +0.511 |
error | +0.493 |
ally | +0.492 |
STE | +0.491 |
brand | +0.480 |
Neg logit contributions | |
arag | -0.466 |
entary | -0.441 |
hran | -0.419 |
chens | -0.403 |
ptic | -0.391 |
Token | future |
Token ID | 2003 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
own | +2.316 |
ally | +2.222 |
STE | +2.217 |
error | +2.202 |
brand | +2.171 |
Neg logit contributions | |
arag | -2.063 |
entary | -1.991 |
hran | -1.873 |
chens | -1.807 |
ptic | -1.727 |
Token | . |
Token ID | 13 |
Feature activation | +5.03e-02 |
Pos logit contributions | |
own | +0.069 |
STE | +0.066 |
error | +0.066 |
ally | +0.066 |
brand | +0.065 |
Neg logit contributions | |
arag | -0.058 |
entary | -0.055 |
hran | -0.052 |
chens | -0.050 |
ptic | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
own | +0.115 |
error | +0.111 |
STE | +0.110 |
ally | +0.109 |
brand | +0.107 |
Neg logit contributions | |
arag | -0.131 |
entary | -0.125 |
hran | -0.119 |
chens | -0.115 |
ptic | -0.112 |
Token |
|
Token ID | 198 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
own | +1.223 |
error | +1.181 |
STE | +1.179 |
ally | +1.169 |
brand | +1.146 |
Neg logit contributions | |
arag | -1.327 |
entary | -1.265 |
hran | -1.207 |
chens | -1.156 |
ptic | -1.126 |
Token | COM |
Token ID | 9858 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
own | +0.838 |
STE | +0.806 |
error | +0.802 |
ally | +0.792 |
brand | +0.774 |
Neg logit contributions | |
arag | -1.403 |
entary | -1.349 |
hran | -1.302 |
chens | -1.258 |
ptic | -1.230 |
Token | IC |
Token ID | 2149 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
own | +0.391 |
error | +0.371 |
STE | +0.369 |
ally | +0.365 |
brand | +0.354 |
Neg logit contributions | |
arag | -0.883 |
entary | -0.850 |
hran | -0.822 |
chens | -0.799 |
ptic | -0.785 |
Token | V |
Token ID | 569 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
STE | +6.613 |
own | +6.590 |
error | +6.375 |
ally | +6.309 |
OWN | +6.273 |
Neg logit contributions | |
arag | -7.223 |
entary | -6.924 |
hran | -6.625 |
chens | -6.351 |
ptic | -6.054 |
Token | INE |
Token ID | 8881 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
own | +3.404 |
ally | +3.323 |
STE | +3.312 |
error | +3.284 |
OWN | +3.156 |
Neg logit contributions | |
arag | -4.717 |
entary | -4.502 |
hran | -4.334 |
chens | -4.192 |
ptic | -4.052 |
Token | : |
Token ID | 25 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
arag | +1.253 |
entary | +1.178 |
hran | +1.103 |
chens | +1.066 |
ptic | +1.035 |
Neg logit contributions | |
own | -1.737 |
error | -1.693 |
ally | -1.678 |
STE | -1.672 |
brand | -1.647 |
Token | When |
Token ID | 1649 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
own | +1.244 |
STE | +1.207 |
error | +1.199 |
ally | +1.189 |
brand | +1.172 |
Neg logit contributions | |
arag | -1.511 |
entary | -1.449 |
hran | -1.390 |
chens | -1.328 |
ptic | -1.297 |
Token | you |
Token ID | 345 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
own | +1.605 |
ally | +1.540 |
error | +1.539 |
STE | +1.538 |
brand | +1.498 |
Neg logit contributions | |
arag | -1.960 |
entary | -1.906 |
hran | -1.801 |
chens | -1.745 |
ptic | -1.703 |
Token | . |
Token ID | 13 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
own | +0.374 |
error | +0.362 |
STE | +0.361 |
ally | +0.359 |
brand | +0.352 |
Neg logit contributions | |
arag | -0.308 |
entary | -0.291 |
hran | -0.275 |
chens | -0.263 |
ptic | -0.255 |
Token | BET |
Token ID | 38651 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
arag | +0.100 |
entary | +0.095 |
hran | +0.090 |
chens | +0.086 |
ptic | +0.084 |
Neg logit contributions | |
own | -0.099 |
error | -0.096 |
STE | -0.095 |
ally | -0.095 |
brand | -0.093 |
Token | TY |
Token ID | 9936 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
arag | +0.688 |
entary | +0.660 |
hran | +0.636 |
chens | +0.616 |
ptic | +0.604 |
Neg logit contributions | |
own | -0.406 |
error | -0.388 |
STE | -0.386 |
ally | -0.383 |
brand | -0.373 |
Token | & |
Token ID | 1222 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
STE | +3.089 |
own | +3.062 |
error | +2.978 |
ally | +2.944 |
OWN | +2.915 |
Neg logit contributions | |
arag | -3.244 |
entary | -3.062 |
hran | -2.938 |
chens | -2.766 |
ptic | -2.722 |
Token | VER |
Token ID | 33310 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
own | +1.557 |
STE | +1.540 |
error | +1.516 |
ally | +1.501 |
brand | +1.475 |
Neg logit contributions | |
arag | -1.629 |
entary | -1.556 |
hran | -1.470 |
chens | -1.411 |
ptic | -1.382 |
Token | ON |
Token ID | 1340 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
own | +0.301 |
STE | +0.291 |
error | +0.290 |
ally | +0.287 |
brand | +0.281 |
Neg logit contributions | |
arag | -0.436 |
entary | -0.417 |
hran | -0.400 |
chens | -0.386 |
ptic | -0.379 |
Token | ICA |
Token ID | 25241 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
STE | +5.777 |
own | +5.604 |
error | +5.438 |
ally | +5.434 |
OWN | +5.314 |
Neg logit contributions | |
arag | -8.082 |
entary | -7.656 |
hran | -7.452 |
chens | -7.138 |
ptic | -7.032 |
Token | ( |
Token ID | 357 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
own | +0.595 |
STE | +0.579 |
error | +0.575 |
ally | +0.571 |
brand | +0.558 |
Neg logit contributions | |
arag | -0.608 |
entary | -0.578 |
hran | -0.550 |
chens | -0.525 |
ptic | -0.514 |
Token | Ar |
Token ID | 3163 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
own | +0.544 |
STE | +0.522 |
error | +0.521 |
ally | +0.514 |
brand | +0.504 |
Neg logit contributions | |
arag | -0.805 |
entary | -0.775 |
hran | -0.743 |
chens | -0.717 |
ptic | -0.703 |
Token | chie |
Token ID | 3043 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
arag | +1.033 |
entary | +0.986 |
hran | +0.948 |
chens | +0.916 |
ptic | +0.897 |
Neg logit contributions | |
own | -0.769 |
error | -0.740 |
STE | -0.737 |
ally | -0.730 |
brand | -0.714 |
Token | ) |
Token ID | 8 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
own | +0.866 |
STE | +0.830 |
error | +0.830 |
ally | +0.826 |
brand | +0.810 |
Neg logit contributions | |
arag | -1.034 |
entary | -0.982 |
hran | -0.942 |
chens | -0.905 |
ptic | -0.881 |
Token | the |
Token ID | 262 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
own | +0.054 |
error | +0.052 |
STE | +0.052 |
ally | +0.052 |
brand | +0.051 |
Neg logit contributions | |
arag | -0.051 |
entary | -0.048 |
hran | -0.046 |
chens | -0.044 |
ptic | -0.043 |
Token | Tal |
Token ID | 7193 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
own | +1.387 |
error | +1.342 |
STE | +1.336 |
ally | +1.335 |
brand | +1.308 |
Neg logit contributions | |
arag | -1.282 |
entary | -1.223 |
hran | -1.160 |
chens | -1.117 |
ptic | -1.086 |
Token | ion |
Token ID | 295 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
arag | +2.815 |
entary | +2.679 |
hran | +2.558 |
chens | +2.456 |
ptic | +2.406 |
Neg logit contributions | |
own | -2.402 |
STE | -2.338 |
error | -2.322 |
ally | -2.290 |
Interstitial | -2.256 |
Token | , |
Token ID | 11 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
own | +5.101 |
ally | +4.883 |
error | +4.880 |
brand | +4.861 |
STE | +4.711 |
Neg logit contributions | |
arag | -4.721 |
entary | -4.483 |
hran | -4.255 |
chens | -4.046 |
ptic | -3.990 |
Token | or |
Token ID | 393 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
own | +0.645 |
error | +0.623 |
STE | +0.619 |
ally | +0.618 |
brand | +0.610 |
Neg logit contributions | |
arag | -0.616 |
entary | -0.583 |
hran | -0.556 |
chens | -0.533 |
ptic | -0.521 |
Token | Rh |
Token ID | 10323 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
own | +1.486 |
ally | +1.435 |
error | +1.432 |
STE | +1.420 |
brand | +1.405 |
Neg logit contributions | |
arag | -1.547 |
entary | -1.462 |
hran | -1.396 |
chens | -1.346 |
ptic | -1.319 |
Token | ulic |
Token ID | 28575 |
Feature activation | +8.96e-02 |
Pos logit contributions | |
own | +6.413 |
ally | +6.194 |
error | +6.128 |
brand | +5.965 |
STE | +5.743 |
Neg logit contributions | |
arag | -7.054 |
entary | -6.882 |
hran | -6.436 |
chens | -6.349 |
ptic | -6.138 |
Token | soldiers |
Token ID | 5795 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
own | +0.223 |
error | +0.216 |
STE | +0.214 |
ally | +0.213 |
brand | +0.210 |
Neg logit contributions | |
arag | -0.214 |
entary | -0.203 |
hran | -0.194 |
chens | -0.186 |
ptic | -0.181 |
Token | , |
Token ID | 11 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
own | +0.690 |
ally | +0.666 |
error | +0.665 |
STE | +0.661 |
brand | +0.655 |
Neg logit contributions | |
arag | -0.599 |
entary | -0.570 |
hran | -0.541 |
chens | -0.515 |
ptic | -0.505 |
Token | and |
Token ID | 290 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
own | +0.276 |
error | +0.268 |
ally | +0.266 |
STE | +0.266 |
brand | +0.263 |
Neg logit contributions | |
arag | -0.236 |
entary | -0.223 |
hran | -0.212 |
chens | -0.204 |
ptic | -0.197 |
Token | certainly |
Token ID | 3729 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
arag | +0.068 |
entary | +0.065 |
hran | +0.062 |
chens | +0.059 |
ptic | +0.058 |
Neg logit contributions | |
own | -0.061 |
error | -0.059 |
STE | -0.059 |
ally | -0.059 |
brand | -0.058 |
Token | building |
Token ID | 2615 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
arag | +0.853 |
entary | +0.808 |
hran | +0.769 |
chens | +0.738 |
ptic | +0.718 |
Neg logit contributions | |
own | -0.901 |
error | -0.872 |
STE | -0.869 |
ally | -0.867 |
brand | -0.849 |
Token | that |
Token ID | 326 |
Feature activation | +6.19e-02 |
Pos logit contributions | |
own | +1.399 |
ally | +1.356 |
error | +1.341 |
STE | +1.337 |
brand | +1.313 |
Neg logit contributions | |
arag | -1.327 |
entary | -1.255 |
hran | -1.194 |
chens | -1.135 |
ptic | -1.103 |
Token | contributes |
Token ID | 22625 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
own | +0.158 |
ally | +0.152 |
error | +0.152 |
STE | +0.152 |
brand | +0.149 |
Neg logit contributions | |
arag | -0.145 |
entary | -0.137 |
hran | -0.130 |
chens | -0.124 |
ptic | -0.121 |
Token | to |
Token ID | 284 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
own | +0.872 |
ally | +0.843 |
error | +0.842 |
STE | +0.841 |
brand | +0.819 |
Neg logit contributions | |
arag | -0.753 |
entary | -0.707 |
hran | -0.667 |
chens | -0.641 |
ptic | -0.619 |
Token | the |
Token ID | 262 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
own | +0.087 |
error | +0.084 |
ally | +0.084 |
STE | +0.084 |
brand | +0.082 |
Neg logit contributions | |
arag | -0.086 |
entary | -0.081 |
hran | -0.078 |
chens | -0.074 |
ptic | -0.072 |
Token | property |
Token ID | 3119 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
own | +0.709 |
error | +0.687 |
STE | +0.685 |
ally | +0.685 |
brand | +0.668 |
Neg logit contributions | |
arag | -0.619 |
entary | -0.583 |
hran | -0.555 |
chens | -0.531 |
ptic | -0.512 |
Token | tax |
Token ID | 1687 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
own | +5.795 |
ally | +5.631 |
error | +5.414 |
brand | +5.258 |
STE | +5.196 |
Neg logit contributions | |
arag | -7.992 |
entary | -7.532 |
hran | -7.373 |
chens | -6.904 |
ocular | -6.713 |
Token | base |
Token ID | 2779 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
own | +0.309 |
error | +0.300 |
STE | +0.298 |
ally | +0.298 |
brand | +0.292 |
Neg logit contributions | |
arag | -0.281 |
entary | -0.266 |
hran | -0.253 |
chens | -0.242 |
ptic | -0.235 |
Token | ? |
Token ID | 30 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
arag | +2.917 |
entary | +2.752 |
hran | +2.620 |
chens | +2.506 |
ptic | +2.448 |
Neg logit contributions | |
own | -3.550 |
error | -3.488 |
STE | -3.457 |
brand | -3.387 |
ally | -3.385 |
Token | We |
Token ID | 775 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
own | +1.877 |
STE | +1.797 |
error | +1.794 |
ally | +1.791 |
brand | +1.753 |
Neg logit contributions | |
arag | -2.222 |
entary | -2.124 |
hran | -2.039 |
chens | -1.945 |
ptic | -1.890 |
Token | have |
Token ID | 423 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
own | +0.897 |
ally | +0.868 |
error | +0.868 |
STE | +0.864 |
brand | +0.841 |
Neg logit contributions | |
arag | -0.812 |
entary | -0.773 |
hran | -0.728 |
chens | -0.693 |
ptic | -0.669 |
Token | s |
Token ID | 82 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
arag | +0.821 |
entary | +0.788 |
hran | +0.756 |
chens | +0.733 |
ptic | +0.717 |
Neg logit contributions | |
own | -0.561 |
error | -0.540 |
STE | -0.538 |
ally | -0.530 |
brand | -0.521 |
Token | somewhat |
Token ID | 6454 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
own | +1.897 |
ally | +1.830 |
STE | +1.825 |
error | +1.824 |
brand | +1.792 |
Neg logit contributions | |
arag | -1.750 |
entary | -1.670 |
hran | -1.574 |
chens | -1.514 |
ptic | -1.495 |
Token | based |
Token ID | 1912 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
own | +4.010 |
ally | +3.953 |
STE | +3.898 |
error | +3.841 |
brand | +3.771 |
Neg logit contributions | |
arag | -3.800 |
entary | -3.573 |
hran | -3.398 |
chens | -3.283 |
ptic | -3.191 |
Token | on |
Token ID | 319 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
own | +0.531 |
error | +0.516 |
STE | +0.514 |
ally | +0.512 |
brand | +0.502 |
Neg logit contributions | |
arag | -0.429 |
entary | -0.404 |
hran | -0.382 |
chens | -0.366 |
ptic | -0.355 |
Token | the |
Token ID | 262 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
own | +2.531 |
ally | +2.442 |
STE | +2.434 |
error | +2.425 |
brand | +2.371 |
Neg logit contributions | |
arag | -2.539 |
entary | -2.407 |
hran | -2.299 |
chens | -2.236 |
ptic | -2.185 |
Token | comic |
Token ID | 9048 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
own | +0.678 |
error | +0.655 |
STE | +0.655 |
ally | +0.653 |
brand | +0.638 |
Neg logit contributions | |
arag | -0.625 |
entary | -0.593 |
hran | -0.564 |
chens | -0.544 |
ptic | -0.527 |
Token | book |
Token ID | 1492 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
own | +6.169 |
ally | +6.039 |
STE | +5.960 |
error | +5.862 |
brand | +5.748 |
Neg logit contributions | |
arag | -7.221 |
entary | -6.807 |
hran | -6.614 |
chens | -6.363 |
ptic | -6.141 |
Token | , |
Token ID | 11 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
own | +2.493 |
STE | +2.421 |
ally | +2.414 |
error | +2.390 |
brand | +2.346 |
Neg logit contributions | |
arag | -2.386 |
entary | -2.251 |
hran | -2.151 |
chens | -2.076 |
ptic | -2.013 |
Token | � |
Token ID | 447 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
own | +0.806 |
error | +0.778 |
STE | +0.778 |
ally | +0.775 |
brand | +0.762 |
Neg logit contributions | |
arag | -0.759 |
entary | -0.722 |
hran | -0.686 |
chens | -0.660 |
ptic | -0.641 |
Token | � |
Token ID | 251 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
own | +0.700 |
error | +0.669 |
STE | +0.665 |
ally | +0.658 |
brand | +0.649 |
Neg logit contributions | |
arag | -1.013 |
entary | -0.977 |
hran | -0.928 |
chens | -0.903 |
ptic | -0.884 |
Token | Ar |
Token ID | 943 |
Feature activation | +8.37e-01 |
Pos logit contributions | |
own | +0.517 |
error | +0.498 |
STE | +0.497 |
ally | +0.495 |
brand | +0.486 |
Neg logit contributions | |
arag | -0.475 |
entary | -0.451 |
hran | -0.429 |
chens | -0.410 |
ptic | -0.401 |
Token | they |
Token ID | 484 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
own | +0.293 |
ally | +0.284 |
error | +0.284 |
STE | +0.282 |
brand | +0.274 |
Neg logit contributions | |
arag | -0.321 |
entary | -0.308 |
hran | -0.293 |
chens | -0.281 |
ptic | -0.272 |
Token | told |
Token ID | 1297 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
arag | +0.556 |
entary | +0.532 |
hran | +0.506 |
chens | +0.486 |
ptic | +0.473 |
Neg logit contributions | |
own | -0.517 |
error | -0.501 |
ally | -0.498 |
STE | -0.496 |
brand | -0.484 |
Token | us |
Token ID | 514 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
own | +0.868 |
error | +0.841 |
ally | +0.841 |
STE | +0.834 |
brand | +0.815 |
Neg logit contributions | |
arag | -0.733 |
entary | -0.688 |
hran | -0.658 |
chens | -0.630 |
ptic | -0.606 |
Token | that |
Token ID | 326 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
own | +1.559 |
ally | +1.505 |
error | +1.498 |
STE | +1.467 |
brand | +1.440 |
Neg logit contributions | |
arag | -1.977 |
entary | -1.892 |
hran | -1.816 |
chens | -1.740 |
ptic | -1.689 |
Token | Mer |
Token ID | 4638 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
own | +0.647 |
error | +0.624 |
ally | +0.620 |
STE | +0.614 |
brand | +0.603 |
Neg logit contributions | |
arag | -0.786 |
entary | -0.754 |
hran | -0.719 |
chens | -0.693 |
ptic | -0.670 |
Token | rick |
Token ID | 5557 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
arag | +1.211 |
entary | +1.162 |
hran | +1.125 |
chens | +1.095 |
ptic | +1.078 |
Neg logit contributions | |
own | -0.562 |
error | -0.538 |
STE | -0.534 |
ally | -0.527 |
brand | -0.509 |
Token | Cemetery |
Token ID | 35637 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
own | +5.709 |
ally | +5.354 |
STE | +5.139 |
OWN | +5.117 |
error | +5.101 |
Neg logit contributions | |
arag | -7.635 |
entary | -7.310 |
hran | -7.046 |
ptic | -6.560 |
ocular | -6.547 |
Token | is |
Token ID | 318 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
own | +0.698 |
ally | +0.671 |
error | +0.670 |
STE | +0.668 |
brand | +0.654 |
Neg logit contributions | |
arag | -0.675 |
entary | -0.640 |
hran | -0.608 |
chens | -0.577 |
ptic | -0.564 |
Token | not |
Token ID | 407 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
arag | +0.422 |
entary | +0.401 |
hran | +0.381 |
chens | +0.364 |
ptic | +0.355 |
Neg logit contributions | |
own | -0.447 |
error | -0.431 |
ally | -0.429 |
STE | -0.428 |
brand | -0.420 |
Token | in |
Token ID | 287 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
own | +0.044 |
ally | +0.042 |
error | +0.042 |
STE | +0.042 |
brand | +0.041 |
Neg logit contributions | |
arag | -0.043 |
entary | -0.041 |
hran | -0.039 |
chens | -0.037 |
ptic | -0.036 |
Token | their |
Token ID | 511 |
Feature activation | +9.19e-02 |
Pos logit contributions | |
arag | +0.169 |
entary | +0.160 |
hran | +0.152 |
chens | +0.146 |
ptic | +0.141 |
Neg logit contributions | |
own | -0.186 |
error | -0.180 |
STE | -0.179 |
ally | -0.178 |
brand | -0.174 |
Token | and |
Token ID | 290 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
own | +1.647 |
error | +1.586 |
STE | +1.583 |
ally | +1.581 |
brand | +1.551 |
Neg logit contributions | |
arag | -1.523 |
entary | -1.450 |
hran | -1.379 |
chens | -1.314 |
ptic | -1.276 |
Token | Cam |
Token ID | 7298 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
arag | +1.631 |
entary | +1.544 |
hran | +1.477 |
chens | +1.419 |
ptic | +1.386 |
Neg logit contributions | |
own | -1.654 |
error | -1.605 |
STE | -1.597 |
ally | -1.580 |
brand | -1.553 |
Token | Newton |
Token ID | 17321 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
arag | +4.441 |
entary | +4.276 |
hran | +3.947 |
chens | +3.882 |
ptic | +3.780 |
Neg logit contributions | |
own | -4.167 |
STE | -4.076 |
error | -4.074 |
Interstitial | -3.981 |
ally | -3.968 |
Token | . |
Token ID | 13 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
arag | +0.175 |
entary | +0.165 |
hran | +0.157 |
chens | +0.150 |
ptic | +0.146 |
Neg logit contributions | |
own | -0.202 |
error | -0.196 |
STE | -0.195 |
ally | -0.195 |
brand | -0.191 |
Token | B |
Token ID | 347 |
Feature activation | -9.94e-01 |
Pos logit contributions | |
arag | +0.843 |
entary | +0.803 |
hran | +0.766 |
chens | +0.740 |
ptic | +0.722 |
Neg logit contributions | |
own | -0.773 |
error | -0.748 |
STE | -0.742 |
ally | -0.741 |
brand | -0.724 |
Token | ort |
Token ID | 419 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
arag | +2.865 |
entary | +2.740 |
hran | +2.635 |
chens | +2.556 |
ptic | +2.512 |
Neg logit contributions | |
own | -1.922 |
error | -1.884 |
STE | -1.855 |
ally | -1.824 |
brand | -1.814 |
Token | les |
Token ID | 829 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
own | +4.695 |
ally | +4.443 |
brand | +4.289 |
error | +4.285 |
STE | +4.237 |
Neg logit contributions | |
arag | -8.528 |
hran | -8.238 |
entary | -8.054 |
arial | -7.650 |
ocular | -7.506 |
Token | is |
Token ID | 318 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
own | +3.286 |
ally | +3.132 |
STE | +3.122 |
error | +3.108 |
brand | +3.046 |
Neg logit contributions | |
arag | -3.296 |
entary | -3.138 |
hran | -3.010 |
chens | -2.846 |
ptic | -2.798 |
Token | clicking |
Token ID | 12264 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
own | +1.650 |
ally | +1.589 |
STE | +1.584 |
error | +1.575 |
brand | +1.550 |
Neg logit contributions | |
arag | -1.623 |
entary | -1.551 |
hran | -1.465 |
chens | -1.410 |
ptic | -1.375 |
Token | right |
Token ID | 826 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
arag | +1.384 |
entary | +1.309 |
hran | +1.246 |
chens | +1.193 |
ptic | +1.159 |
Neg logit contributions | |
own | -1.542 |
error | -1.491 |
STE | -1.486 |
ally | -1.483 |
brand | -1.450 |
Token | now |
Token ID | 783 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
arag | +0.305 |
entary | +0.288 |
hran | +0.273 |
chens | +0.257 |
ptic | +0.249 |
Neg logit contributions | |
own | -0.435 |
ally | -0.421 |
error | -0.419 |
STE | -0.418 |
brand | -0.410 |
Token | to |
Token ID | 284 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
own | +1.503 |
ally | +1.464 |
error | +1.458 |
STE | +1.448 |
brand | +1.423 |
Neg logit contributions | |
arag | -1.206 |
entary | -1.129 |
hran | -1.079 |
chens | -1.027 |
ptic | -0.997 |
Token | discover |
Token ID | 7073 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
arag | +1.247 |
entary | +1.175 |
hran | +1.111 |
chens | +1.059 |
ptic | +1.031 |
Neg logit contributions | |
own | -1.613 |
error | -1.568 |
STE | -1.562 |
ally | -1.554 |
brand | -1.527 |
Token | in |
Token ID | 287 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
own | +2.257 |
ally | +2.203 |
error | +2.161 |
STE | +2.141 |
brand | +2.110 |
Neg logit contributions | |
arag | -2.300 |
entary | -2.171 |
hran | -2.076 |
chens | -2.012 |
ptic | -1.944 |
Token | the |
Token ID | 262 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
arag | +0.851 |
entary | +0.806 |
hran | +0.765 |
chens | +0.733 |
ptic | +0.717 |
Neg logit contributions | |
own | -0.906 |
error | -0.880 |
STE | -0.873 |
ally | -0.867 |
brand | -0.852 |
Token | New |
Token ID | 968 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
arag | +0.232 |
entary | +0.221 |
hran | +0.211 |
chens | +0.203 |
ptic | +0.198 |
Neg logit contributions | |
own | -0.209 |
error | -0.202 |
STE | -0.201 |
ally | -0.200 |
brand | -0.195 |
Token | Xbox |
Token ID | 9445 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
arag | +0.684 |
entary | +0.654 |
hran | +0.622 |
chens | +0.601 |
ptic | +0.588 |
Neg logit contributions | |
own | -0.607 |
error | -0.593 |
STE | -0.587 |
ally | -0.583 |
brand | -0.571 |
Token | One |
Token ID | 1881 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
own | +6.132 |
ally | +5.650 |
STE | +5.633 |
brand | +5.615 |
error | +5.607 |
Neg logit contributions | |
arag | -7.207 |
entary | -6.857 |
hran | -6.587 |
chens | -6.287 |
arial | -6.209 |
Token | Experience |
Token ID | 16386 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
own | +0.537 |
error | +0.507 |
STE | +0.506 |
ally | +0.503 |
brand | +0.486 |
Neg logit contributions | |
arag | -1.096 |
entary | -1.054 |
hran | -1.017 |
chens | -0.988 |
ptic | -0.968 |
Token | , |
Token ID | 11 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
arag | +1.275 |
entary | +1.206 |
hran | +1.143 |
chens | +1.092 |
ptic | +1.069 |
Neg logit contributions | |
own | -1.498 |
error | -1.458 |
STE | -1.450 |
ally | -1.435 |
brand | -1.415 |
Token | and |
Token ID | 290 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
arag | +1.125 |
entary | +1.064 |
hran | +1.009 |
chens | +0.966 |
ptic | +0.940 |
Neg logit contributions | |
own | -1.302 |
error | -1.264 |
STE | -1.258 |
ally | -1.253 |
brand | -1.230 |
Token | all |
Token ID | 477 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
arag | +0.063 |
entary | +0.060 |
hran | +0.057 |
chens | +0.056 |
ptic | +0.054 |
Neg logit contributions | |
own | -0.054 |
error | -0.052 |
STE | -0.052 |
ally | -0.051 |
brand | -0.050 |
Token | setting |
Token ID | 4634 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
arag | +0.691 |
entary | +0.654 |
hran | +0.621 |
chens | +0.598 |
ptic | +0.581 |
Neg logit contributions | |
own | -0.735 |
error | -0.708 |
STE | -0.707 |
ally | -0.707 |
brand | -0.691 |
Token | the |
Token ID | 262 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
arag | +0.434 |
entary | +0.409 |
hran | +0.388 |
chens | +0.373 |
ptic | +0.364 |
Neg logit contributions | |
own | -0.470 |
ally | -0.450 |
STE | -0.450 |
error | -0.449 |
brand | -0.438 |
Token | tone |
Token ID | 8216 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
own | +1.391 |
ally | +1.327 |
STE | +1.326 |
error | +1.324 |
brand | +1.286 |
Neg logit contributions | |
arag | -1.362 |
entary | -1.281 |
hran | -1.215 |
chens | -1.172 |
ptic | -1.145 |
Token | for |
Token ID | 329 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
own | +1.510 |
ally | +1.464 |
STE | +1.442 |
error | +1.439 |
brand | +1.407 |
Neg logit contributions | |
arag | -1.347 |
entary | -1.282 |
hran | -1.226 |
chens | -1.173 |
ptic | -1.135 |
Token | the |
Token ID | 262 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
arag | +0.479 |
entary | +0.454 |
hran | +0.432 |
chens | +0.416 |
ptic | +0.405 |
Neg logit contributions | |
own | -0.508 |
error | -0.491 |
ally | -0.489 |
STE | -0.489 |
brand | -0.476 |
Token | offense |
Token ID | 6907 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
own | +0.798 |
ally | +0.771 |
error | +0.767 |
STE | +0.767 |
brand | +0.749 |
Neg logit contributions | |
arag | -0.604 |
entary | -0.566 |
hran | -0.537 |
chens | -0.514 |
ptic | -0.495 |
Token | . |
Token ID | 13 |
Feature activation | +7.73e-02 |
Pos logit contributions | |
ally | +6.316 |
own | +6.311 |
error | +5.855 |
STE | +5.771 |
----- | +5.719 |
Neg logit contributions | |
arag | -6.579 |
entary | -6.316 |
hran | -6.021 |
chens | -5.844 |
ptic | -5.675 |
Token | I |
Token ID | 314 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
own | +0.168 |
STE | +0.161 |
error | +0.161 |
ally | +0.160 |
brand | +0.156 |
Neg logit contributions | |
arag | -0.210 |
entary | -0.200 |
hran | -0.192 |
chens | -0.185 |
ptic | -0.181 |
Token | � |
Token ID | 447 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
own | +1.760 |
ally | +1.701 |
STE | +1.695 |
error | +1.684 |
brand | +1.643 |
Neg logit contributions | |
arag | -1.716 |
entary | -1.645 |
hran | -1.547 |
chens | -1.476 |
ptic | -1.437 |
Token | � |
Token ID | 247 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
own | +0.819 |
error | +0.786 |
ally | +0.782 |
STE | +0.780 |
brand | +0.764 |
Neg logit contributions | |
arag | -0.919 |
entary | -0.877 |
hran | -0.832 |
chens | -0.806 |
ptic | -0.784 |
Token | m |
Token ID | 76 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
arag | +0.572 |
entary | +0.539 |
hran | +0.509 |
chens | +0.487 |
ptic | +0.474 |
Neg logit contributions | |
own | -0.671 |
error | -0.650 |
ally | -0.645 |
STE | -0.645 |
brand | -0.633 |
Token | post |
Token ID | 7353 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
arag | +1.207 |
entary | +1.133 |
hran | +1.065 |
chens | +1.014 |
ptic | +0.985 |
Neg logit contributions | |
own | -1.687 |
STE | -1.639 |
error | -1.638 |
ally | -1.625 |
brand | -1.596 |
Token | or |
Token ID | 273 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
arag | +2.028 |
entary | +1.949 |
hran | +1.870 |
chens | +1.803 |
ptic | +1.782 |
Neg logit contributions | |
own | -1.163 |
STE | -1.122 |
error | -1.114 |
ally | -1.093 |
brand | -1.066 |
Token |
|
Token ID | 198 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
own | +1.324 |
error | +1.277 |
ally | +1.269 |
STE | +1.265 |
brand | +1.242 |
Neg logit contributions | |
arag | -1.398 |
entary | -1.327 |
hran | -1.270 |
chens | -1.221 |
ptic | -1.187 |
Token |
|
Token ID | 198 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
arag | +1.297 |
entary | +1.225 |
hran | +1.165 |
chens | +1.131 |
ptic | +1.108 |
Neg logit contributions | |
own | -1.400 |
error | -1.362 |
STE | -1.359 |
ally | -1.344 |
ensical | -1.327 |
Token | H |
Token ID | 39 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
arag | +1.222 |
entary | +1.165 |
hran | +1.120 |
chens | +1.084 |
ptic | +1.068 |
Neg logit contributions | |
own | -0.802 |
error | -0.769 |
ally | -0.763 |
STE | -0.762 |
brand | -0.739 |
Token | orn |
Token ID | 1211 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
own | +0.555 |
error | +0.533 |
STE | +0.529 |
ally | +0.528 |
brand | +0.515 |
Neg logit contributions | |
arag | -0.763 |
entary | -0.730 |
hran | -0.700 |
chens | -0.678 |
ptic | -0.663 |
Token | of |
Token ID | 286 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
own | +6.892 |
brand | +6.626 |
ally | +6.621 |
error | +6.397 |
STE | +6.367 |
Neg logit contributions | |
arag | -6.125 |
entary | -5.875 |
hran | -5.593 |
chens | -5.412 |
ptic | -5.152 |
Token | Plenty |
Token ID | 43257 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
own | +2.739 |
error | +2.643 |
ally | +2.615 |
STE | +2.602 |
brand | +2.572 |
Neg logit contributions | |
arag | -2.682 |
entary | -2.575 |
hran | -2.425 |
chens | -2.330 |
ptic | -2.283 |
Token | vs |
Token ID | 3691 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
arag | +0.283 |
entary | +0.267 |
hran | +0.253 |
chens | +0.241 |
ptic | +0.235 |
Neg logit contributions | |
own | -0.347 |
error | -0.337 |
STE | -0.336 |
ally | -0.334 |
brand | -0.328 |
Token | Lore |
Token ID | 15639 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
own | +1.817 |
error | +1.755 |
ally | +1.741 |
STE | +1.736 |
brand | +1.714 |
Neg logit contributions | |
arag | -1.701 |
entary | -1.619 |
hran | -1.535 |
chens | -1.472 |
ptic | -1.430 |
Token | Se |
Token ID | 1001 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
own | +1.262 |
error | +1.216 |
ally | +1.207 |
STE | +1.196 |
brand | +1.194 |
Neg logit contributions | |
arag | -1.314 |
entary | -1.249 |
hran | -1.184 |
chens | -1.144 |
ptic | -1.106 |
Token | ov |
Token ID | 709 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
arag | +0.336 |
entary | +0.321 |
hran | +0.308 |
chens | +0.297 |
ptic | +0.292 |
Neg logit contributions | |
own | -0.235 |
error | -0.225 |
STE | -0.224 |
ally | -0.223 |
brand | -0.218 |
Token | itch |
Token ID | 2007 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
own | +0.834 |
ally | +0.805 |
error | +0.800 |
STE | +0.794 |
brand | +0.775 |
Neg logit contributions | |
arag | -1.033 |
entary | -1.002 |
hran | -0.941 |
chens | -0.907 |
ptic | -0.898 |
Token |
|
Token ID | 198 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
arag | +0.094 |
entary | +0.089 |
hran | +0.085 |
chens | +0.082 |
ptic | +0.080 |
Neg logit contributions | |
own | -0.080 |
error | -0.077 |
STE | -0.077 |
ally | -0.077 |
brand | -0.075 |
Token |
|
Token ID | 198 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
arag | +0.723 |
entary | +0.685 |
hran | +0.653 |
chens | +0.632 |
ptic | +0.617 |
Neg logit contributions | |
own | -0.744 |
error | -0.723 |
STE | -0.719 |
ally | -0.714 |
brand | -0.701 |
Token | More |
Token ID | 5167 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
arag | +0.422 |
entary | +0.404 |
hran | +0.388 |
chens | +0.375 |
ptic | +0.368 |
Neg logit contributions | |
own | -0.288 |
error | -0.277 |
STE | -0.275 |
ally | -0.274 |
brand | -0.267 |
Token | entertainment |
Token ID | 9739 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
arag | +0.552 |
entary | +0.522 |
hran | +0.496 |
chens | +0.475 |
ptic | +0.463 |
Neg logit contributions | |
own | -0.621 |
error | -0.603 |
STE | -0.600 |
ally | -0.597 |
brand | -0.586 |
Token | stories |
Token ID | 3923 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
own | +6.559 |
ally | +6.547 |
STE | +6.310 |
brand | +6.172 |
error | +6.155 |
Neg logit contributions | |
arag | -6.333 |
entary | -5.950 |
hran | -5.712 |
chens | -5.614 |
ptic | -5.388 |
Token | on |
Token ID | 319 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
arag | +1.085 |
entary | +1.022 |
hran | +0.967 |
chens | +0.926 |
ptic | +0.900 |
Neg logit contributions | |
own | -1.336 |
error | -1.301 |
STE | -1.292 |
ally | -1.283 |
brand | -1.263 |
Token | Yahoo |
Token ID | 16551 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
own | +0.804 |
error | +0.781 |
STE | +0.778 |
ally | +0.775 |
brand | +0.758 |
Neg logit contributions | |
arag | -0.692 |
entary | -0.648 |
hran | -0.622 |
chens | -0.596 |
ptic | -0.579 |
Token | ! |
Token ID | 0 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
own | +0.946 |
error | +0.916 |
STE | +0.916 |
ally | +0.908 |
brand | +0.892 |
Neg logit contributions | |
arag | -0.888 |
entary | -0.835 |
hran | -0.797 |
chens | -0.765 |
ptic | -0.739 |
Token |
|
Token ID | 198 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
own | +1.165 |
error | +1.118 |
STE | +1.114 |
ally | +1.106 |
brand | +1.083 |
Neg logit contributions | |
arag | -1.692 |
entary | -1.611 |
hran | -1.550 |
chens | -1.500 |
ptic | -1.468 |
Token | been |
Token ID | 587 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
own | +0.429 |
ally | +0.415 |
error | +0.413 |
STE | +0.412 |
brand | +0.402 |
Neg logit contributions | |
arag | -0.419 |
entary | -0.401 |
hran | -0.379 |
chens | -0.365 |
ptic | -0.355 |
Token | charged |
Token ID | 5047 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
arag | +0.869 |
entary | +0.823 |
hran | +0.784 |
chens | +0.748 |
ptic | +0.729 |
Neg logit contributions | |
own | -0.967 |
error | -0.935 |
ally | -0.934 |
STE | -0.930 |
brand | -0.910 |
Token | with |
Token ID | 351 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
own | +1.897 |
ally | +1.825 |
error | +1.812 |
STE | +1.794 |
brand | +1.761 |
Neg logit contributions | |
arag | -1.846 |
entary | -1.765 |
hran | -1.688 |
chens | -1.603 |
ptic | -1.572 |
Token | misdemeanor |
Token ID | 22403 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
own | +0.694 |
error | +0.668 |
ally | +0.667 |
STE | +0.661 |
brand | +0.652 |
Neg logit contributions | |
arag | -0.642 |
entary | -0.610 |
hran | -0.583 |
chens | -0.558 |
ptic | -0.541 |
Token | petty |
Token ID | 25229 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
own | +1.845 |
ally | +1.778 |
error | +1.762 |
STE | +1.742 |
brand | +1.724 |
Neg logit contributions | |
arag | -1.716 |
entary | -1.639 |
hran | -1.574 |
chens | -1.501 |
ptic | -1.448 |
Token | theft |
Token ID | 12402 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
arag | +0.727 |
entary | +0.688 |
hran | +0.653 |
chens | +0.626 |
ptic | +0.609 |
Neg logit contributions | |
own | -0.823 |
error | -0.798 |
STE | -0.794 |
ally | -0.791 |
brand | -0.776 |
Token | , |
Token ID | 11 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
own | +6.228 |
ally | +6.079 |
error | +5.950 |
brand | +5.795 |
STE | +5.792 |
Neg logit contributions | |
arag | -6.570 |
entary | -6.480 |
hran | -6.221 |
chens | -5.801 |
ptic | -5.710 |
Token | though |
Token ID | 996 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
arag | +1.311 |
entary | +1.239 |
hran | +1.175 |
chens | +1.128 |
ptic | +1.100 |
Neg logit contributions | |
own | -1.443 |
error | -1.399 |
STE | -1.395 |
ally | -1.387 |
brand | -1.361 |
Token | . |
Token ID | 13 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
own | +1.175 |
error | +1.132 |
ally | +1.131 |
STE | +1.112 |
brand | +1.099 |
Neg logit contributions | |
arag | -1.313 |
entary | -1.259 |
hran | -1.206 |
chens | -1.151 |
ptic | -1.118 |
Token |
|
Token ID | 198 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
arag | +0.335 |
entary | +0.319 |
hran | +0.305 |
chens | +0.293 |
ptic | +0.286 |
Neg logit contributions | |
own | -0.294 |
error | -0.284 |
STE | -0.283 |
ally | -0.281 |
brand | -0.276 |
Token |
|
Token ID | 198 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
arag | +0.489 |
entary | +0.464 |
hran | +0.441 |
chens | +0.426 |
ptic | +0.417 |
Neg logit contributions | |
own | -0.495 |
error | -0.480 |
STE | -0.477 |
ally | -0.474 |
brand | -0.466 |
Token | hart |
Token ID | 18647 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
own | +3.373 |
ally | +3.279 |
error | +3.254 |
STE | +3.231 |
brand | +3.196 |
Neg logit contributions | |
arag | -2.635 |
entary | -2.491 |
hran | -2.342 |
chens | -2.210 |
ptic | -2.169 |
Token |
|
Token ID | 198 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
own | +3.888 |
error | +3.691 |
STE | +3.680 |
ally | +3.667 |
brand | +3.607 |
Neg logit contributions | |
arag | -4.516 |
entary | -4.267 |
hran | -4.071 |
chens | -3.885 |
ptic | -3.865 |
Token |
|
Token ID | 198 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
arag | +0.286 |
entary | +0.271 |
hran | +0.258 |
chens | +0.249 |
ptic | +0.243 |
Neg logit contributions | |
own | -0.284 |
error | -0.275 |
STE | -0.274 |
ally | -0.272 |
brand | -0.267 |
Token | 1987 |
Token ID | 27301 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
arag | +0.667 |
entary | +0.638 |
hran | +0.616 |
chens | +0.597 |
ptic | +0.585 |
Neg logit contributions | |
own | -0.393 |
error | -0.376 |
STE | -0.374 |
ally | -0.373 |
brand | -0.362 |
Token | Br |
Token ID | 1709 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
own | +1.505 |
ally | +1.454 |
error | +1.453 |
STE | +1.453 |
brand | +1.416 |
Neg logit contributions | |
arag | -1.570 |
entary | -1.498 |
hran | -1.419 |
chens | -1.367 |
ptic | -1.332 |
Token | onson |
Token ID | 36742 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
own | +0.559 |
error | +0.534 |
STE | +0.531 |
ally | +0.530 |
brand | +0.515 |
Neg logit contributions | |
arag | -0.887 |
entary | -0.851 |
hran | -0.818 |
chens | -0.793 |
ptic | -0.777 |
Token | P |
Token ID | 350 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
own | +6.548 |
ally | +6.240 |
error | +6.136 |
brand | +6.098 |
STE | +6.068 |
Neg logit contributions | |
arag | -6.439 |
entary | -6.165 |
hran | -5.729 |
chens | -5.567 |
ptic | -5.389 |
Token | inch |
Token ID | 8589 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
own | +4.139 |
ally | +3.955 |
error | +3.904 |
STE | +3.846 |
brand | +3.772 |
Neg logit contributions | |
arag | -4.419 |
entary | -4.238 |
hran | -4.023 |
chens | -3.858 |
ptic | -3.750 |
Token | ot |
Token ID | 313 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
own | +1.083 |
error | +1.039 |
ally | +1.036 |
STE | +1.029 |
brand | +1.014 |
Neg logit contributions | |
arag | -1.139 |
entary | -1.085 |
hran | -1.043 |
chens | -0.989 |
ptic | -0.967 |
Token | 1988 |
Token ID | 12122 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
own | +0.032 |
error | +0.031 |
STE | +0.031 |
ally | +0.031 |
brand | +0.030 |
Neg logit contributions | |
arag | -0.033 |
entary | -0.031 |
hran | -0.030 |
chens | -0.029 |
ptic | -0.028 |
Token | Michael |
Token ID | 3899 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
arag | +1.319 |
entary | +1.249 |
hran | +1.193 |
chens | +1.146 |
ptic | +1.118 |
Neg logit contributions | |
own | -1.309 |
error | -1.268 |
STE | -1.259 |
ally | -1.251 |
brand | -1.228 |
Token | it |
Token ID | 340 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
arag | +3.224 |
entary | +3.038 |
hran | +2.916 |
chens | +2.788 |
ptic | +2.727 |
Neg logit contributions | |
own | -3.200 |
error | -3.131 |
STE | -3.115 |
ally | -3.062 |
brand | -3.029 |
Token | " |
Token ID | 366 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
arag | +0.265 |
entary | +0.250 |
hran | +0.237 |
chens | +0.226 |
ptic | +0.220 |
Neg logit contributions | |
own | -0.326 |
error | -0.316 |
STE | -0.315 |
ally | -0.314 |
brand | -0.308 |
Token | a |
Token ID | 64 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
own | +0.779 |
error | +0.750 |
STE | +0.745 |
ally | +0.743 |
brand | +0.727 |
Neg logit contributions | |
arag | -0.959 |
entary | -0.920 |
hran | -0.879 |
chens | -0.849 |
ptic | -0.828 |
Token | kind |
Token ID | 1611 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
arag | +1.143 |
entary | +1.079 |
hran | +1.021 |
chens | +0.977 |
ptic | +0.949 |
Neg logit contributions | |
own | -1.397 |
error | -1.356 |
STE | -1.351 |
ally | -1.346 |
brand | -1.321 |
Token | of |
Token ID | 286 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
own | +1.146 |
error | +1.110 |
STE | +1.106 |
ally | +1.106 |
brand | +1.085 |
Neg logit contributions | |
arag | -0.863 |
entary | -0.810 |
hran | -0.766 |
chens | -0.731 |
ptic | -0.706 |
Token | entertainment |
Token ID | 9739 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
own | +2.227 |
ally | +2.161 |
error | +2.153 |
STE | +2.147 |
brand | +2.104 |
Neg logit contributions | |
arag | -1.859 |
entary | -1.779 |
hran | -1.675 |
chens | -1.622 |
ptic | -1.557 |
Token | machine |
Token ID | 4572 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
own | +6.569 |
ally | +6.563 |
error | +6.241 |
brand | +6.151 |
STE | +6.130 |
Neg logit contributions | |
arag | -6.236 |
entary | -5.977 |
chens | -5.601 |
hran | -5.590 |
ptic | -5.205 |
Token | set |
Token ID | 900 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
arag | +1.055 |
entary | +1.000 |
hran | +0.953 |
chens | +0.916 |
ptic | +0.894 |
Neg logit contributions | |
own | -1.056 |
error | -1.024 |
STE | -1.019 |
ally | -1.013 |
brand | -0.994 |
Token | to |
Token ID | 284 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
arag | +1.250 |
entary | +1.185 |
hran | +1.121 |
chens | +1.075 |
ptic | +1.046 |
Neg logit contributions | |
own | -1.454 |
error | -1.418 |
STE | -1.412 |
ally | -1.401 |
brand | -1.374 |
Token | dazz |
Token ID | 32282 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
arag | +1.535 |
entary | +1.451 |
hran | +1.383 |
chens | +1.319 |
ptic | +1.293 |
Neg logit contributions | |
own | -1.710 |
error | -1.660 |
STE | -1.657 |
ally | -1.648 |
brand | -1.615 |
Token | le |
Token ID | 293 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
own | +2.322 |
error | +2.187 |
STE | +2.171 |
ally | +2.143 |
brand | +2.106 |
Neg logit contributions | |
arag | -3.467 |
entary | -3.345 |
hran | -3.176 |
chens | -3.108 |
ptic | -3.014 |
Token | and |
Token ID | 290 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
arag | +1.769 |
entary | +1.676 |
hran | +1.597 |
chens | +1.513 |
ptic | +1.469 |
Neg logit contributions | |
own | -2.486 |
error | -2.420 |
STE | -2.403 |
brand | -2.385 |
Interstitial | -2.382 |
Token | Vol |
Token ID | 4709 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
arag | +1.825 |
entary | +1.743 |
hran | +1.673 |
chens | +1.616 |
ptic | +1.596 |
Neg logit contributions | |
own | -1.663 |
error | -1.602 |
STE | -1.588 |
ally | -1.577 |
brand | -1.554 |
Token | atile |
Token ID | 12610 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
own | +0.635 |
STE | +0.571 |
error | +0.570 |
ally | +0.566 |
brand | +0.539 |
Neg logit contributions | |
arag | -2.546 |
entary | -2.456 |
hran | -2.386 |
chens | -2.325 |
ptic | -2.277 |
Token | Evolution |
Token ID | 15815 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
arag | +4.153 |
entary | +4.002 |
hran | +3.796 |
chens | +3.743 |
ptic | +3.680 |
Neg logit contributions | |
own | -3.821 |
error | -3.707 |
STE | -3.651 |
ally | -3.629 |
brand | -3.594 |
Token | ( |
Token ID | 357 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
ally | +3.225 |
own | +3.199 |
STE | +3.126 |
error | +3.111 |
brand | +3.010 |
Neg logit contributions | |
arag | -3.225 |
entary | -3.004 |
hran | -2.868 |
chens | -2.806 |
ptic | -2.703 |
Token | MA |
Token ID | 5673 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
arag | +0.771 |
entary | +0.723 |
hran | +0.688 |
chens | +0.658 |
ptic | +0.648 |
Neg logit contributions | |
own | -0.865 |
error | -0.838 |
STE | -0.829 |
ally | -0.828 |
brand | -0.814 |
Token | VEN |
Token ID | 28290 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
arag | +5.300 |
entary | +4.938 |
ptic | +4.582 |
hran | +4.569 |
chens | +4.368 |
Neg logit contributions | |
own | -10.710 |
error | -10.657 |
brand | -10.532 |
ensical | -10.453 |
ally | -10.425 |
Token | ) |
Token ID | 8 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
arag | +0.084 |
entary | +0.078 |
hran | +0.073 |
chens | +0.069 |
ptic | +0.067 |
Neg logit contributions | |
own | -0.139 |
error | -0.135 |
STE | -0.134 |
ally | -0.134 |
brand | -0.132 |
Token | mission |
Token ID | 4365 |
Feature activation | +5.58e-02 |
Pos logit contributions | |
own | +2.198 |
error | +2.151 |
STE | +2.150 |
ally | +2.148 |
brand | +2.092 |
Neg logit contributions | |
arag | -1.722 |
entary | -1.595 |
hran | -1.517 |
chens | -1.469 |
ptic | -1.389 |
Token | , |
Token ID | 11 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
own | +0.141 |
error | +0.137 |
ally | +0.136 |
STE | +0.136 |
brand | +0.133 |
Neg logit contributions | |
arag | -0.132 |
entary | -0.124 |
hran | -0.118 |
chens | -0.113 |
ptic | -0.110 |
Token | which |
Token ID | 543 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
arag | +0.595 |
entary | +0.566 |
hran | +0.538 |
chens | +0.518 |
ptic | +0.503 |
Neg logit contributions | |
own | -0.606 |
error | -0.586 |
ally | -0.585 |
STE | -0.583 |
brand | -0.572 |
Token | on |
Token ID | 319 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
arag | +2.258 |
entary | +2.125 |
hran | +2.042 |
chens | +1.928 |
ptic | +1.872 |
Neg logit contributions | |
own | -2.642 |
error | -2.556 |
STE | -2.531 |
ally | -2.512 |
brand | -2.474 |
Token | sidelines |
Token ID | 29394 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
own | +2.917 |
ally | +2.869 |
error | +2.859 |
STE | +2.852 |
brand | +2.813 |
Neg logit contributions | |
arag | -2.499 |
entary | -2.320 |
hran | -2.201 |
chens | -2.112 |
arial | -2.023 |
Token | of |
Token ID | 286 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
arag | +1.835 |
entary | +1.677 |
hran | +1.623 |
chens | +1.537 |
ptic | +1.495 |
Neg logit contributions | |
own | -2.837 |
error | -2.731 |
STE | -2.717 |
ally | -2.699 |
Interstitial | -2.661 |
Token | Trump |
Token ID | 1301 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
arag | +1.270 |
entary | +1.199 |
hran | +1.140 |
chens | +1.084 |
ptic | +1.061 |
Neg logit contributions | |
own | -1.510 |
error | -1.468 |
STE | -1.460 |
ally | -1.453 |
brand | -1.426 |
Token | - |
Token ID | 12 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
arag | +0.618 |
entary | +0.584 |
hran | +0.552 |
chens | +0.531 |
ptic | +0.515 |
Neg logit contributions | |
own | -0.719 |
error | -0.696 |
STE | -0.694 |
ally | -0.692 |
brand | -0.679 |
Token | Kim |
Token ID | 26374 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
arag | +1.003 |
entary | +0.950 |
hran | +0.905 |
chens | +0.866 |
ptic | +0.846 |
Neg logit contributions | |
own | -1.053 |
error | -1.025 |
STE | -1.018 |
ally | -1.013 |
brand | -0.991 |
Token | summit |
Token ID | 14237 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
arag | +4.443 |
entary | +3.897 |
hran | +3.613 |
ptic | +3.354 |
chens | +3.224 |
Neg logit contributions | |
own | -11.825 |
Interstitial | -11.816 |
STE | -11.739 |
error | -11.729 |
ally | -11.674 |
Token | Manafort |
Token ID | 26351 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
arag | +2.013 |
entary | +1.901 |
hran | +1.806 |
chens | +1.723 |
ptic | +1.672 |
Neg logit contributions | |
own | -2.344 |
error | -2.274 |
STE | -2.258 |
ally | -2.246 |
brand | -2.210 |
Token | 's |
Token ID | 338 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
arag | +4.616 |
entary | +4.332 |
hran | +4.040 |
chens | +3.837 |
arial | +3.678 |
Neg logit contributions | |
own | -6.242 |
error | -6.105 |
STE | -6.055 |
Interstitial | -5.906 |
ally | -5.898 |
Token | attorneys |
Token ID | 14449 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
arag | +0.544 |
entary | +0.515 |
hran | +0.498 |
chens | +0.485 |
ptic | +0.473 |
Neg logit contributions | |
own | -0.481 |
error | -0.464 |
STE | -0.462 |
ally | -0.461 |
brand | -0.449 |
Token | say |
Token ID | 910 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
arag | +4.123 |
entary | +3.867 |
hran | +3.648 |
chens | +3.481 |
ptic | +3.377 |
Neg logit contributions | |
own | -5.212 |
error | -5.054 |
STE | -5.035 |
ally | -5.015 |
brand | -4.913 |
Token |
|
Token ID | 198 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
own | +0.309 |
error | +0.298 |
STE | +0.297 |
ally | +0.296 |
brand | +0.290 |
Neg logit contributions | |
arag | -0.338 |
entary | -0.322 |
hran | -0.307 |
chens | -0.295 |
ptic | -0.288 |
Token |
|
Token ID | 198 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
own | +1.203 |
error | +1.161 |
STE | +1.154 |
ally | +1.152 |
brand | +1.128 |
Neg logit contributions | |
arag | -1.343 |
entary | -1.282 |
hran | -1.223 |
chens | -1.167 |
ptic | -1.138 |
Token | S |
Token ID | 50 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
own | +0.844 |
STE | +0.810 |
error | +0.807 |
ally | +0.798 |
brand | +0.779 |
Neg logit contributions | |
arag | -1.371 |
entary | -1.323 |
hran | -1.277 |
chens | -1.232 |
ptic | -1.202 |
Token | aying |
Token ID | 8369 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
own | +0.729 |
error | +0.701 |
ally | +0.698 |
STE | +0.696 |
brand | +0.677 |
Neg logit contributions | |
arag | -0.966 |
entary | -0.926 |
hran | -0.890 |
chens | -0.856 |
ptic | -0.838 |
Token | that |
Token ID | 326 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
arag | +1.155 |
entary | +1.103 |
hran | +1.055 |
chens | +1.017 |
ptic | +0.993 |
Neg logit contributions | |
own | -0.956 |
error | -0.921 |
STE | -0.915 |
ally | -0.915 |
brand | -0.892 |
Token | Theresa |
Token ID | 20251 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
own | +0.663 |
ally | +0.641 |
error | +0.639 |
STE | +0.631 |
brand | +0.619 |
Neg logit contributions | |
arag | -0.699 |
entary | -0.670 |
hran | -0.638 |
chens | -0.611 |
ptic | -0.593 |
Token | May |
Token ID | 1737 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
arag | +5.640 |
entary | +5.061 |
chens | +4.702 |
hran | +4.699 |
ptic | +4.592 |
Neg logit contributions | |
Interstitial | -10.505 |
ensical | -10.285 |
error | -10.233 |
STE | -10.132 |
own | -10.118 |
Token | has |
Token ID | 468 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
arag | +3.819 |
entary | +3.532 |
hran | +3.354 |
chens | +3.267 |
ptic | +3.178 |
Neg logit contributions | |
own | -4.697 |
error | -4.602 |
STE | -4.584 |
Interstitial | -4.503 |
ally | -4.496 |
Token | a |
Token ID | 257 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
arag | +0.845 |
entary | +0.804 |
hran | +0.765 |
chens | +0.736 |
ptic | +0.717 |
Neg logit contributions | |
own | -0.824 |
error | -0.796 |
STE | -0.792 |
ally | -0.790 |
brand | -0.773 |
Token | � |
Token ID | 564 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
arag | +1.623 |
entary | +1.536 |
hran | +1.459 |
chens | +1.399 |
ptic | +1.363 |
Neg logit contributions | |
own | -1.780 |
error | -1.726 |
STE | -1.718 |
ally | -1.711 |
brand | -1.679 |
Token | � |
Token ID | 250 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
arag | +1.509 |
entary | +1.440 |
hran | +1.382 |
chens | +1.333 |
ptic | +1.307 |
Neg logit contributions | |
own | -1.155 |
error | -1.113 |
STE | -1.110 |
ally | -1.103 |
brand | -1.076 |
Token | on |
Token ID | 319 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
arag | +2.108 |
entary | +1.994 |
hran | +1.917 |
chens | +1.809 |
ptic | +1.762 |
Neg logit contributions | |
own | -2.296 |
error | -2.232 |
STE | -2.207 |
ally | -2.193 |
brand | -2.154 |
Token | sidelines |
Token ID | 29394 |
Feature activation | -9.38e-01 |
Pos logit contributions | |
own | +2.982 |
ally | +2.926 |
error | +2.919 |
STE | +2.914 |
brand | +2.872 |
Neg logit contributions | |
arag | -2.626 |
entary | -2.435 |
hran | -2.316 |
chens | -2.220 |
arial | -2.133 |
Token | of |
Token ID | 286 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
arag | +1.782 |
entary | +1.631 |
hran | +1.580 |
chens | +1.489 |
ptic | +1.448 |
Neg logit contributions | |
own | -2.759 |
error | -2.660 |
STE | -2.647 |
ally | -2.631 |
brand | -2.595 |
Token | Trump |
Token ID | 1301 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
arag | +1.017 |
entary | +0.962 |
hran | +0.909 |
chens | +0.874 |
ptic | +0.847 |
Neg logit contributions | |
own | -1.187 |
error | -1.150 |
STE | -1.146 |
ally | -1.142 |
brand | -1.121 |
Token | - |
Token ID | 12 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
arag | +0.409 |
entary | +0.386 |
hran | +0.364 |
chens | +0.351 |
ptic | +0.339 |
Neg logit contributions | |
own | -0.489 |
error | -0.474 |
STE | -0.472 |
ally | -0.472 |
brand | -0.462 |
Token | Kim |
Token ID | 26374 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
arag | +0.807 |
entary | +0.764 |
hran | +0.729 |
chens | +0.697 |
ptic | +0.681 |
Neg logit contributions | |
own | -0.845 |
error | -0.822 |
STE | -0.817 |
ally | -0.813 |
brand | -0.796 |
Token | summit |
Token ID | 14237 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
arag | +4.487 |
entary | +3.954 |
hran | +3.660 |
ptic | +3.431 |
chens | +3.316 |
Neg logit contributions | |
own | -11.541 |
Interstitial | -11.530 |
STE | -11.454 |
error | -11.440 |
ally | -11.381 |
Token | Manafort |
Token ID | 26351 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
arag | +1.942 |
entary | +1.841 |
hran | +1.755 |
chens | +1.677 |
ptic | +1.632 |
Neg logit contributions | |
own | -2.049 |
error | -1.985 |
STE | -1.971 |
ally | -1.959 |
brand | -1.927 |
Token | 's |
Token ID | 338 |
Feature activation | -7.87e-02 |
Pos logit contributions | |
arag | +4.368 |
entary | +4.108 |
hran | +3.844 |
chens | +3.664 |
ptic | +3.522 |
Neg logit contributions | |
own | -5.734 |
error | -5.593 |
STE | -5.550 |
ally | -5.435 |
brand | -5.408 |
Token | attorneys |
Token ID | 14449 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
arag | +0.202 |
entary | +0.191 |
hran | +0.185 |
chens | +0.180 |
ptic | +0.176 |
Neg logit contributions | |
own | -0.182 |
error | -0.176 |
STE | -0.175 |
ally | -0.175 |
brand | -0.170 |
Token | say |
Token ID | 910 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
arag | +3.763 |
entary | +3.535 |
hran | +3.337 |
chens | +3.183 |
ptic | +3.090 |
Neg logit contributions | |
own | -4.888 |
error | -4.745 |
STE | -4.726 |
ally | -4.709 |
brand | -4.621 |
Token | successful |
Token ID | 4388 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
own | +3.089 |
ally | +3.084 |
STE | +2.993 |
error | +2.976 |
brand | +2.947 |
Neg logit contributions | |
arag | -3.222 |
entary | -3.108 |
hran | -2.873 |
chens | -2.792 |
ocular | -2.666 |
Token | ( |
Token ID | 357 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
arag | +0.367 |
entary | +0.348 |
hran | +0.330 |
chens | +0.317 |
ptic | +0.308 |
Neg logit contributions | |
own | -0.400 |
error | -0.387 |
STE | -0.385 |
ally | -0.385 |
brand | -0.377 |
Token | as |
Token ID | 292 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
arag | +0.826 |
entary | +0.790 |
hran | +0.757 |
chens | +0.732 |
ptic | +0.717 |
Neg logit contributions | |
own | -0.607 |
error | -0.584 |
STE | -0.581 |
ally | -0.578 |
brand | -0.564 |
Token | compared |
Token ID | 3688 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
arag | +2.521 |
entary | +2.380 |
hran | +2.270 |
chens | +2.182 |
ptic | +2.143 |
Neg logit contributions | |
own | -2.415 |
error | -2.350 |
STE | -2.338 |
ally | -2.311 |
brand | -2.279 |
Token | to |
Token ID | 284 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
arag | +1.058 |
entary | +0.997 |
hran | +0.941 |
chens | +0.900 |
ptic | +0.873 |
Neg logit contributions | |
own | -1.399 |
error | -1.365 |
STE | -1.362 |
ally | -1.347 |
brand | -1.331 |
Token | Mitt |
Token ID | 16627 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
arag | +2.742 |
entary | +2.581 |
hran | +2.409 |
chens | +2.308 |
ptic | +2.258 |
Neg logit contributions | |
own | -3.816 |
error | -3.721 |
STE | -3.712 |
ally | -3.663 |
brand | -3.623 |
Token | Romney |
Token ID | 8431 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
arag | +4.455 |
entary | +3.910 |
hran | +3.471 |
chens | +3.332 |
ptic | +3.122 |
Neg logit contributions | |
STE | -11.558 |
error | -11.421 |
Interstitial | -11.371 |
own | -11.344 |
ensical | -11.322 |
Token | ) |
Token ID | 8 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
arag | +5.187 |
entary | +4.792 |
hran | +4.538 |
chens | +4.317 |
ptic | +4.197 |
Neg logit contributions | |
own | -7.099 |
error | -6.965 |
STE | -6.942 |
Interstitial | -6.819 |
licensed | -6.716 |
Token | in |
Token ID | 287 |
Feature activation | -4.94e-02 |
Pos logit contributions | |
own | +0.214 |
error | +0.206 |
ally | +0.206 |
STE | +0.205 |
brand | +0.202 |
Neg logit contributions | |
arag | -0.213 |
entary | -0.203 |
hran | -0.193 |
chens | -0.185 |
ptic | -0.180 |
Token | counties |
Token ID | 14683 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
arag | +0.120 |
entary | +0.114 |
hran | +0.108 |
chens | +0.104 |
ptic | +0.101 |
Neg logit contributions | |
own | -0.121 |
error | -0.117 |
STE | -0.117 |
ally | -0.117 |
brand | -0.114 |
Token | heavily |
Token ID | 7272 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
arag | +0.829 |
entary | +0.785 |
hran | +0.747 |
chens | +0.717 |
ptic | +0.700 |
Neg logit contributions | |
own | -0.881 |
error | -0.854 |
STE | -0.851 |
ally | -0.845 |
brand | -0.830 |
Token | on |
Token ID | 319 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
arag | +2.277 |
entary | +2.139 |
hran | +2.052 |
chens | +1.934 |
ptic | +1.887 |
Neg logit contributions | |
own | -2.648 |
error | -2.561 |
STE | -2.533 |
ally | -2.508 |
brand | -2.478 |
Token | sidelines |
Token ID | 29394 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
own | +2.827 |
ally | +2.777 |
error | +2.771 |
STE | +2.764 |
brand | +2.731 |
Neg logit contributions | |
arag | -2.417 |
entary | -2.238 |
hran | -2.127 |
chens | -2.034 |
arial | -1.952 |
Token | of |
Token ID | 286 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
arag | +1.729 |
entary | +1.586 |
hran | +1.529 |
chens | +1.447 |
ptic | +1.406 |
Neg logit contributions | |
own | -2.666 |
error | -2.571 |
STE | -2.560 |
ally | -2.539 |
brand | -2.504 |
Token | Trump |
Token ID | 1301 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
arag | +1.208 |
entary | +1.142 |
hran | +1.085 |
chens | +1.034 |
ptic | +1.011 |
Neg logit contributions | |
own | -1.411 |
error | -1.371 |
STE | -1.364 |
ally | -1.357 |
brand | -1.332 |
Token | - |
Token ID | 12 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
arag | +0.127 |
entary | +0.121 |
hran | +0.113 |
chens | +0.111 |
ptic | +0.106 |
Neg logit contributions | |
own | -0.141 |
ally | -0.136 |
error | -0.136 |
STE | -0.135 |
brand | -0.133 |
Token | Kim |
Token ID | 26374 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
arag | +0.881 |
entary | +0.838 |
hran | +0.796 |
chens | +0.766 |
ptic | +0.745 |
Neg logit contributions | |
own | -0.900 |
error | -0.865 |
STE | -0.863 |
ally | -0.860 |
brand | -0.846 |
Token | summit |
Token ID | 14237 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
arag | +4.074 |
entary | +3.565 |
hran | +3.223 |
ptic | +2.984 |
chens | +2.859 |
Neg logit contributions | |
own | -11.649 |
Interstitial | -11.647 |
error | -11.562 |
STE | -11.558 |
ally | -11.513 |
Token | Manafort |
Token ID | 26351 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
arag | +2.002 |
entary | +1.895 |
hran | +1.799 |
chens | +1.724 |
ptic | +1.677 |
Neg logit contributions | |
own | -2.220 |
error | -2.153 |
STE | -2.141 |
ally | -2.131 |
brand | -2.093 |
Token | 's |
Token ID | 338 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
arag | +4.270 |
entary | +4.016 |
hran | +3.752 |
chens | +3.575 |
ptic | +3.438 |
Neg logit contributions | |
own | -5.635 |
error | -5.496 |
STE | -5.465 |
ally | -5.343 |
Interstitial | -5.318 |
Token | attorneys |
Token ID | 14449 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
arag | +0.410 |
entary | +0.388 |
hran | +0.376 |
chens | +0.367 |
ptic | +0.358 |
Neg logit contributions | |
own | -0.374 |
error | -0.361 |
STE | -0.359 |
ally | -0.359 |
brand | -0.349 |
Token | say |
Token ID | 910 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
arag | +4.186 |
entary | +3.948 |
hran | +3.734 |
chens | +3.580 |
ptic | +3.482 |
Neg logit contributions | |
own | -4.737 |
error | -4.587 |
STE | -4.568 |
ally | -4.549 |
brand | -4.455 |
Token | considers |
Token ID | 14358 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
own | +1.525 |
ally | +1.463 |
error | +1.432 |
STE | +1.421 |
brand | +1.413 |
Neg logit contributions | |
arag | -1.490 |
entary | -1.432 |
hran | -1.345 |
chens | -1.274 |
ptic | -1.242 |
Token | intellectually |
Token ID | 39186 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
arag | +1.745 |
entary | +1.647 |
hran | +1.560 |
chens | +1.495 |
ptic | +1.451 |
Neg logit contributions | |
own | -2.173 |
error | -2.113 |
STE | -2.107 |
ally | -2.088 |
brand | -2.058 |
Token | inferior |
Token ID | 18536 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
own | +2.313 |
ally | +2.269 |
error | +2.243 |
STE | +2.203 |
brand | +2.134 |
Neg logit contributions | |
arag | -2.583 |
entary | -2.446 |
hran | -2.344 |
chens | -2.227 |
ptic | -2.158 |
Token | ( |
Token ID | 357 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
arag | +0.097 |
entary | +0.091 |
hran | +0.086 |
chens | +0.083 |
ptic | +0.080 |
Neg logit contributions | |
own | -0.118 |
error | -0.114 |
STE | -0.114 |
ally | -0.113 |
brand | -0.111 |
Token | ex |
Token ID | 1069 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
arag | +0.705 |
entary | +0.675 |
hran | +0.648 |
chens | +0.627 |
ptic | +0.614 |
Neg logit contributions | |
own | -0.492 |
error | -0.473 |
STE | -0.470 |
ally | -0.467 |
brand | -0.456 |
Token | empl |
Token ID | 18856 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
arag | +3.079 |
entary | +2.897 |
hran | +2.730 |
chens | +2.654 |
ptic | +2.596 |
Neg logit contributions | |
own | -3.057 |
error | -2.965 |
STE | -2.947 |
ally | -2.926 |
brand | -2.874 |
Token | ified |
Token ID | 1431 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
arag | +8.268 |
entary | +8.065 |
hran | +7.449 |
arial | +7.335 |
chens | +7.121 |
Neg logit contributions | |
STE | -6.784 |
own | -6.586 |
Interstitial | -6.582 |
error | -6.509 |
OWN | -6.388 |
Token | in |
Token ID | 287 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
arag | +2.249 |
entary | +2.138 |
hran | +2.054 |
chens | +1.970 |
ptic | +1.923 |
Neg logit contributions | |
own | -2.028 |
error | -1.991 |
STE | -1.977 |
ally | -1.934 |
brand | -1.928 |
Token | the |
Token ID | 262 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
arag | +0.571 |
entary | +0.541 |
hran | +0.513 |
chens | +0.491 |
ptic | +0.478 |
Neg logit contributions | |
own | -0.647 |
error | -0.627 |
STE | -0.624 |
ally | -0.622 |
brand | -0.610 |
Token | prose |
Token ID | 27149 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
arag | +0.984 |
entary | +0.931 |
hran | +0.882 |
chens | +0.845 |
ptic | +0.823 |
Neg logit contributions | |
own | -1.122 |
error | -1.089 |
STE | -1.085 |
ally | -1.079 |
brand | -1.061 |
Token | passages |
Token ID | 22674 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
arag | +0.074 |
entary | +0.070 |
hran | +0.066 |
chens | +0.064 |
ptic | +0.062 |
Neg logit contributions | |
own | -0.090 |
error | -0.087 |
ally | -0.087 |
STE | -0.086 |
brand | -0.085 |
Token | ! |
Token ID | 0 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
arag | +0.331 |
entary | +0.313 |
hran | +0.298 |
chens | +0.285 |
ptic | +0.277 |
Neg logit contributions | |
own | -0.356 |
error | -0.343 |
STE | -0.343 |
ally | -0.343 |
brand | -0.335 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
own | +1.013 |
error | +0.978 |
STE | +0.972 |
ally | +0.968 |
brand | +0.947 |
Neg logit contributions | |
arag | -1.183 |
entary | -1.127 |
hran | -1.079 |
chens | -1.041 |
ptic | -1.014 |
Token | Democratic |
Token ID | 33939 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
own | +2.638 |
STE | +2.559 |
error | +2.543 |
ally | +2.486 |
brand | +2.453 |
Neg logit contributions | |
arag | -4.140 |
entary | -4.003 |
hran | -3.847 |
chens | -3.721 |
ptic | -3.610 |
Token | presidential |
Token ID | 4787 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
arag | +1.354 |
entary | +1.245 |
hran | +1.148 |
chens | +1.073 |
ptic | +1.030 |
Neg logit contributions | |
own | -2.902 |
error | -2.837 |
STE | -2.825 |
ally | -2.815 |
brand | -2.776 |
Token | nominee |
Token ID | 10429 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
arag | +0.517 |
entary | +0.484 |
hran | +0.455 |
chens | +0.429 |
ptic | +0.414 |
Neg logit contributions | |
own | -0.804 |
error | -0.779 |
ally | -0.779 |
STE | -0.777 |
brand | -0.762 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
arag | +1.827 |
entary | +1.683 |
hran | +1.543 |
chens | +1.443 |
ptic | +1.386 |
Neg logit contributions | |
own | -4.115 |
error | -4.035 |
STE | -4.019 |
ally | -3.985 |
brand | -3.946 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
arag | +3.770 |
entary | +3.332 |
chens | +2.951 |
hran | +2.866 |
ptic | +2.720 |
Neg logit contributions | |
error | -10.921 |
own | -10.890 |
Interstitial | -10.773 |
STE | -10.762 |
ensical | -10.714 |
Token | Hillary |
Token ID | 5073 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
arag | +4.112 |
entary | +3.840 |
hran | +3.649 |
chens | +3.533 |
ptic | +3.466 |
Neg logit contributions | |
own | -4.475 |
error | -4.370 |
STE | -4.319 |
ally | -4.249 |
licensed | -4.199 |
Token | Diane |
Token ID | 26542 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
arag | +2.634 |
entary | +2.501 |
hran | +1.953 |
arial | +1.880 |
ocular | +1.863 |
Neg logit contributions | |
own | -10.686 |
error | -10.583 |
ensical | -10.481 |
═ | -10.471 |
Interstitial | -10.398 |
Token | Rodham |
Token ID | 41848 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
arag | +3.397 |
entary | +3.150 |
hran | +3.015 |
ocular | +2.776 |
ptic | +2.694 |
Neg logit contributions | |
own | -6.174 |
error | -6.129 |
Interstitial | -5.936 |
═ | -5.932 |
STE | -5.918 |
Token | Clinton |
Token ID | 2605 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
arag | +0.266 |
entary | +0.243 |
hran | +0.225 |
chens | +0.209 |
ptic | +0.198 |
Neg logit contributions | |
own | -0.618 |
error | -0.603 |
STE | -0.602 |
ally | -0.597 |
brand | -0.590 |
Token | - |
Token ID | 12 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
own | +1.263 |
error | +1.213 |
ally | +1.209 |
STE | +1.202 |
brand | +1.186 |
Neg logit contributions | |
arag | -1.245 |
entary | -1.187 |
hran | -1.127 |
chens | -1.076 |
ptic | -1.058 |
Token | q |
Token ID | 80 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
own | +1.206 |
error | +1.162 |
ally | +1.153 |
STE | +1.150 |
brand | +1.131 |
Neg logit contributions | |
arag | -1.370 |
entary | -1.315 |
hran | -1.245 |
chens | -1.197 |
ptic | -1.178 |
Token | aim |
Token ID | 1385 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
arag | +0.301 |
entary | +0.288 |
hran | +0.275 |
chens | +0.265 |
ptic | +0.259 |
Neg logit contributions | |
own | -0.253 |
error | -0.244 |
STE | -0.243 |
ally | -0.242 |
brand | -0.237 |
Token | ish |
Token ID | 680 |
Feature activation | -5.31e-03 |
Pos logit contributions | |
arag | +2.289 |
entary | +2.165 |
hran | +2.063 |
chens | +1.983 |
ptic | +1.923 |
Neg logit contributions | |
own | -2.361 |
error | -2.295 |
STE | -2.293 |
ally | -2.266 |
brand | -2.223 |
Token | ( |
Token ID | 357 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
arag | +0.013 |
entary | +0.012 |
hran | +0.012 |
chens | +0.011 |
ptic | +0.011 |
Neg logit contributions | |
own | -0.013 |
error | -0.013 |
ally | -0.013 |
STE | -0.012 |
brand | -0.012 |
Token | Middle |
Token ID | 34621 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
arag | +0.731 |
entary | +0.700 |
hran | +0.671 |
chens | +0.647 |
ptic | +0.634 |
Neg logit contributions | |
own | -0.550 |
error | -0.529 |
STE | -0.525 |
ally | -0.523 |
brand | -0.511 |
Token | Turk |
Token ID | 8484 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
arag | +7.326 |
entary | +7.006 |
hran | +6.685 |
chens | +6.600 |
ptic | +6.238 |
Neg logit contributions | |
own | -7.300 |
STE | -7.206 |
error | -7.191 |
ally | -6.965 |
Interstitial | -6.937 |
Token | ic |
Token ID | 291 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
own | +0.631 |
error | +0.596 |
ally | +0.594 |
STE | +0.584 |
brand | +0.573 |
Neg logit contributions | |
arag | -1.334 |
entary | -1.282 |
hran | -1.240 |
chens | -1.199 |
ptic | -1.185 |
Token | " |
Token ID | 366 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
arag | +1.145 |
entary | +1.083 |
hran | +1.029 |
chens | +0.983 |
ptic | +0.957 |
Neg logit contributions | |
own | -1.334 |
error | -1.292 |
STE | -1.286 |
ally | -1.284 |
brand | -1.260 |
Token | next |
Token ID | 19545 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
own | +1.214 |
error | +1.169 |
ally | +1.154 |
STE | +1.151 |
brand | +1.135 |
Neg logit contributions | |
arag | -1.438 |
entary | -1.383 |
hran | -1.321 |
chens | -1.268 |
ptic | -1.241 |
Token | time |
Token ID | 640 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
arag | +3.261 |
entary | +3.073 |
hran | +2.902 |
chens | +2.797 |
ptic | +2.705 |
Neg logit contributions | |
own | -3.867 |
STE | -3.790 |
error | -3.769 |
ally | -3.713 |
Interstitial | -3.673 |
Token |
|
Token ID | 198 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
own | +0.004 |
error | +0.004 |
STE | +0.004 |
ally | +0.004 |
brand | +0.004 |
Neg logit contributions | |
arag | -0.004 |
entary | -0.004 |
hran | -0.004 |
chens | -0.004 |
ptic | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
arag | +1.812 |
entary | +1.705 |
hran | +1.624 |
chens | +1.585 |
ptic | +1.552 |
Neg logit contributions | |
own | -2.034 |
error | -1.978 |
STE | -1.971 |
ensical | -1.969 |
ally | -1.950 |
Token | See |
Token ID | 6214 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
arag | +2.377 |
entary | +2.266 |
hran | +2.178 |
chens | +2.109 |
ptic | +2.083 |
Neg logit contributions | |
own | -1.483 |
error | -1.426 |
STE | -1.412 |
ally | -1.406 |
brand | -1.367 |
Token | also |
Token ID | 635 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
arag | +4.771 |
entary | +4.384 |
hran | +4.170 |
chens | +3.967 |
ptic | +3.923 |
Neg logit contributions | |
own | -6.006 |
STE | -5.944 |
error | -5.909 |
ally | -5.774 |
brand | -5.730 |
Token | [ |
Token ID | 685 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
arag | +1.688 |
entary | +1.608 |
hran | +1.538 |
chens | +1.488 |
ptic | +1.461 |
Neg logit contributions | |
own | -1.338 |
error | -1.289 |
STE | -1.284 |
ally | -1.267 |
brand | -1.245 |
Token | edit |
Token ID | 4370 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
arag | +3.314 |
entary | +2.910 |
hran | +2.826 |
chens | +2.791 |
ptic | +2.726 |
Neg logit contributions | |
ensical | -6.969 |
own | -6.788 |
STE | -6.687 |
Interstitial | -6.680 |
ally | -6.555 |
Token | ] |
Token ID | 2361 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
arag | +5.544 |
chens | +5.087 |
entary | +4.951 |
hran | +4.905 |
ptic | +4.784 |
Neg logit contributions | |
ensical | -9.280 |
own | -8.536 |
Interstitial | -8.522 |
iosyncr | -8.463 |
STE | -8.424 |
Token |
|
Token ID | 198 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
arag | +5.062 |
entary | +4.774 |
hran | +4.516 |
chens | +4.380 |
ptic | +4.274 |
Neg logit contributions | |
own | -5.124 |
STE | -5.028 |
error | -5.010 |
brand | -4.871 |
ally | -4.869 |
Token |
|
Token ID | 198 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
arag | +3.333 |
entary | +3.078 |
hran | +2.923 |
chens | +2.923 |
ptic | +2.872 |
Neg logit contributions | |
ensical | -4.540 |
own | -4.361 |
error | -4.268 |
STE | -4.238 |
Interstitial | -4.214 |
Token | References |
Token ID | 19927 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
arag | +4.263 |
entary | +4.000 |
hran | +3.856 |
ptic | +3.737 |
chens | +3.736 |
Neg logit contributions | |
own | -2.640 |
error | -2.542 |
STE | -2.519 |
ally | -2.503 |
brand | -2.433 |
Token | [ |
Token ID | 685 |
Feature activation | -9.81e-01 |
Pos logit contributions | |
arag | +2.775 |
entary | +2.638 |
hran | +2.523 |
chens | +2.438 |
ptic | +2.377 |
Neg logit contributions | |
own | -2.260 |
STE | -2.184 |
error | -2.183 |
ally | -2.140 |
brand | -2.114 |
Token | answers |
Token ID | 7429 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
arag | +1.138 |
entary | +1.078 |
hran | +1.025 |
chens | +0.985 |
ptic | +0.963 |
Neg logit contributions | |
own | -1.194 |
error | -1.160 |
STE | -1.154 |
ally | -1.142 |
brand | -1.129 |
Token | on |
Token ID | 319 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
arag | +1.214 |
entary | +1.146 |
hran | +1.086 |
chens | +1.039 |
ptic | +1.012 |
Neg logit contributions | |
own | -1.439 |
error | -1.399 |
STE | -1.394 |
ally | -1.383 |
brand | -1.361 |
Token | the |
Token ID | 262 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
own | +1.852 |
ally | +1.788 |
error | +1.784 |
STE | +1.765 |
brand | +1.721 |
Neg logit contributions | |
arag | -2.024 |
entary | -1.934 |
hran | -1.847 |
chens | -1.782 |
ptic | -1.729 |
Token | impact |
Token ID | 2928 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
own | +0.310 |
error | +0.300 |
STE | +0.299 |
ally | +0.298 |
brand | +0.292 |
Neg logit contributions | |
arag | -0.267 |
entary | -0.253 |
hran | -0.240 |
chens | -0.230 |
ptic | -0.223 |
Token | of |
Token ID | 286 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
arag | +0.367 |
entary | +0.346 |
hran | +0.327 |
chens | +0.312 |
ptic | +0.303 |
Neg logit contributions | |
own | -0.471 |
error | -0.457 |
ally | -0.455 |
STE | -0.455 |
brand | -0.445 |
Token | Brexit |
Token ID | 11435 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
arag | +1.077 |
entary | +1.019 |
hran | +0.967 |
chens | +0.926 |
ptic | +0.902 |
Neg logit contributions | |
own | -1.211 |
error | -1.174 |
STE | -1.169 |
ally | -1.164 |
brand | -1.142 |
Token | , |
Token ID | 11 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
arag | +5.962 |
entary | +5.411 |
hran | +5.067 |
chens | +4.868 |
ptic | +4.793 |
Neg logit contributions | |
own | -8.678 |
error | -8.604 |
STE | -8.546 |
licensed | -8.470 |
OWN | -8.328 |
Token | leaving |
Token ID | 4305 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
arag | +1.836 |
entary | +1.732 |
hran | +1.650 |
chens | +1.589 |
ptic | +1.550 |
Neg logit contributions | |
own | -1.850 |
error | -1.797 |
STE | -1.792 |
ally | -1.777 |
brand | -1.744 |
Token | that |
Token ID | 326 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
arag | +3.756 |
entary | +3.550 |
hran | +3.370 |
chens | +3.233 |
ptic | +3.183 |
Neg logit contributions | |
own | -3.984 |
STE | -3.913 |
error | -3.891 |
ally | -3.803 |
brand | -3.796 |
Token | to |
Token ID | 284 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
arag | +1.476 |
entary | +1.393 |
hran | +1.318 |
chens | +1.260 |
ptic | +1.225 |
Neg logit contributions | |
own | -1.807 |
error | -1.754 |
STE | -1.747 |
ally | -1.740 |
brand | -1.709 |
Token | surveys |
Token ID | 16255 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
arag | +1.290 |
entary | +1.221 |
hran | +1.158 |
chens | +1.113 |
ptic | +1.081 |
Neg logit contributions | |
own | -1.425 |
error | -1.380 |
STE | -1.372 |
ally | -1.370 |
brand | -1.342 |
Token | employees |
Token ID | 4409 |
Feature activation | -8.98e-02 |
Pos logit contributions | |
own | +0.622 |
ally | +0.601 |
STE | +0.599 |
error | +0.597 |
brand | +0.583 |
Neg logit contributions | |
arag | -0.492 |
entary | -0.458 |
hran | -0.438 |
chens | -0.416 |
ptic | -0.404 |
Token | to |
Token ID | 284 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
arag | +0.206 |
entary | +0.195 |
hran | +0.185 |
chens | +0.177 |
ptic | +0.173 |
Neg logit contributions | |
own | -0.232 |
error | -0.225 |
STE | -0.224 |
ally | -0.223 |
brand | -0.218 |
Token | employers |
Token ID | 11390 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
arag | +0.078 |
entary | +0.073 |
hran | +0.070 |
chens | +0.066 |
ptic | +0.065 |
Neg logit contributions | |
own | -0.091 |
STE | -0.087 |
ally | -0.087 |
error | -0.087 |
brand | -0.085 |
Token | ." |
Token ID | 526 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
own | +2.142 |
ally | +2.082 |
error | +2.062 |
STE | +2.050 |
brand | +2.004 |
Neg logit contributions | |
arag | -2.094 |
entary | -1.987 |
hran | -1.897 |
chens | -1.805 |
ptic | -1.769 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
own | +2.600 |
error | +2.513 |
STE | +2.498 |
ally | +2.490 |
brand | +2.437 |
Neg logit contributions | |
arag | -2.893 |
entary | -2.744 |
hran | -2.622 |
chens | -2.528 |
ptic | -2.467 |
Token | MA |
Token ID | 5673 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
own | +2.820 |
STE | +2.738 |
error | +2.716 |
ally | +2.655 |
brand | +2.621 |
Neg logit contributions | |
arag | -4.439 |
entary | -4.293 |
hran | -4.126 |
chens | -3.990 |
ptic | -3.870 |
Token | J |
Token ID | 41 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
arag | +7.714 |
entary | +7.345 |
hran | +7.174 |
chens | +6.772 |
ptic | +6.629 |
Neg logit contributions | |
own | -6.629 |
error | -6.457 |
ally | -6.320 |
brand | -6.271 |
licensed | -6.202 |
Token | UR |
Token ID | 4261 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
own | +1.628 |
error | +1.561 |
STE | +1.559 |
ally | +1.552 |
brand | +1.488 |
Neg logit contributions | |
arag | -2.900 |
entary | -2.785 |
hran | -2.669 |
chens | -2.604 |
ptic | -2.568 |
Token | O |
Token ID | 46 |
Feature activation | +9.19e-02 |
Pos logit contributions | |
own | +1.468 |
STE | +1.421 |
error | +1.415 |
ally | +1.404 |
brand | +1.351 |
Neg logit contributions | |
arag | -2.204 |
entary | -2.105 |
hran | -2.017 |
chens | -1.958 |
ptic | -1.918 |
Token | , |
Token ID | 11 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
own | +0.228 |
STE | +0.221 |
error | +0.220 |
ally | +0.219 |
brand | +0.214 |
Neg logit contributions | |
arag | -0.221 |
entary | -0.209 |
hran | -0.199 |
chens | -0.191 |
ptic | -0.186 |
Token | Marshall |
Token ID | 13606 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
own | +0.459 |
error | +0.446 |
STE | +0.445 |
ally | +0.441 |
brand | +0.433 |
Neg logit contributions | |
arag | -0.436 |
entary | -0.415 |
hran | -0.396 |
chens | -0.379 |
ptic | -0.367 |
Token | shown |
Token ID | 3402 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
own | +1.338 |
ally | +1.312 |
error | +1.287 |
STE | +1.281 |
brand | +1.244 |
Neg logit contributions | |
arag | -1.395 |
entary | -1.351 |
hran | -1.257 |
chens | -1.226 |
ptic | -1.184 |
Token | no |
Token ID | 645 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
own | +1.648 |
ally | +1.596 |
error | +1.572 |
STE | +1.567 |
brand | +1.533 |
Neg logit contributions | |
arag | -1.408 |
entary | -1.351 |
hran | -1.265 |
chens | -1.220 |
ptic | -1.180 |
Token | interest |
Token ID | 1393 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
own | +0.121 |
error | +0.116 |
ally | +0.115 |
STE | +0.115 |
brand | +0.113 |
Neg logit contributions | |
arag | -0.127 |
entary | -0.121 |
hran | -0.115 |
chens | -0.111 |
ptic | -0.108 |
Token | whatsoever |
Token ID | 16014 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
arag | +0.080 |
entary | +0.076 |
hran | +0.072 |
chens | +0.069 |
ptic | +0.067 |
Neg logit contributions | |
own | -0.085 |
error | -0.083 |
STE | -0.082 |
ally | -0.082 |
brand | -0.080 |
Token | in |
Token ID | 287 |
Feature activation | -8.90e-02 |
Pos logit contributions | |
arag | +0.285 |
entary | +0.271 |
hran | +0.257 |
chens | +0.247 |
ptic | +0.241 |
Neg logit contributions | |
own | -0.297 |
error | -0.286 |
ally | -0.285 |
STE | -0.285 |
brand | -0.279 |
Token | medi |
Token ID | 16957 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
arag | +0.216 |
entary | +0.206 |
hran | +0.196 |
chens | +0.188 |
ptic | +0.183 |
Neg logit contributions | |
own | -0.218 |
error | -0.211 |
ally | -0.210 |
STE | -0.209 |
brand | -0.205 |
Token | ating |
Token ID | 803 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
arag | +3.172 |
entary | +2.862 |
hran | +2.372 |
arial | +2.134 |
ptic | +2.096 |
Neg logit contributions | |
STE | -11.118 |
own | -11.106 |
OWN | -11.038 |
Interstitial | -11.028 |
error | -10.908 |
Token | in |
Token ID | 287 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
arag | +2.323 |
entary | +2.203 |
hran | +2.079 |
chens | +1.996 |
ptic | +1.947 |
Neg logit contributions | |
own | -2.666 |
error | -2.594 |
STE | -2.586 |
ally | -2.538 |
brand | -2.528 |
Token | a |
Token ID | 257 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
own | +0.722 |
ally | +0.704 |
error | +0.701 |
STE | +0.699 |
brand | +0.675 |
Neg logit contributions | |
arag | -0.760 |
entary | -0.725 |
hran | -0.695 |
chens | -0.663 |
ptic | -0.647 |
Token | highly |
Token ID | 4047 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
own | +0.544 |
ally | +0.528 |
STE | +0.527 |
error | +0.524 |
brand | +0.514 |
Neg logit contributions | |
arag | -0.438 |
entary | -0.411 |
hran | -0.391 |
chens | -0.373 |
ptic | -0.362 |
Token | heated |
Token ID | 16968 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
own | +1.215 |
ally | +1.184 |
error | +1.180 |
STE | +1.174 |
brand | +1.147 |
Neg logit contributions | |
arag | -1.115 |
entary | -1.055 |
hran | -1.002 |
chens | -0.973 |
ptic | -0.934 |
Token | some |
Token ID | 617 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
arag | +0.532 |
entary | +0.505 |
hran | +0.476 |
chens | +0.459 |
ptic | +0.445 |
Neg logit contributions | |
own | -0.565 |
ally | -0.546 |
error | -0.545 |
STE | -0.543 |
brand | -0.530 |
Token | fear |
Token ID | 3252 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
own | +0.564 |
ally | +0.552 |
error | +0.546 |
STE | +0.546 |
brand | +0.537 |
Neg logit contributions | |
arag | -0.476 |
entary | -0.463 |
hran | -0.426 |
chens | -0.410 |
arial | -0.393 |
Token | is |
Token ID | 318 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
own | +1.689 |
ally | +1.651 |
error | +1.618 |
STE | +1.613 |
brand | +1.580 |
Neg logit contributions | |
arag | -1.564 |
entary | -1.499 |
hran | -1.375 |
chens | -1.337 |
ptic | -1.308 |
Token | threatened |
Token ID | 8556 |
Feature activation | +2.18e-03 |
Pos logit contributions | |
arag | +0.815 |
entary | +0.775 |
hran | +0.734 |
chens | +0.709 |
ptic | +0.691 |
Neg logit contributions | |
own | -0.789 |
error | -0.761 |
ally | -0.760 |
STE | -0.757 |
brand | -0.739 |
Token | by |
Token ID | 416 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
own | +0.005 |
error | +0.004 |
ally | +0.004 |
STE | +0.004 |
brand | +0.004 |
Neg logit contributions | |
arag | -0.006 |
entary | -0.006 |
hran | -0.006 |
chens | -0.005 |
ptic | -0.005 |
Token | Brexit |
Token ID | 11435 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
own | +0.326 |
ally | +0.317 |
error | +0.315 |
STE | +0.314 |
brand | +0.306 |
Neg logit contributions | |
arag | -0.283 |
entary | -0.270 |
hran | -0.251 |
chens | -0.244 |
ptic | -0.235 |
Token | . |
Token ID | 13 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
arag | +5.525 |
entary | +4.982 |
hran | +4.742 |
chens | +4.557 |
ptic | +4.457 |
Neg logit contributions | |
own | -8.520 |
STE | -8.470 |
error | -8.468 |
licensed | -8.414 |
Interstitial | -8.336 |
Token |
|
Token ID | 198 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
arag | +0.994 |
entary | +0.943 |
hran | +0.903 |
chens | +0.864 |
ptic | +0.845 |
Neg logit contributions | |
own | -0.962 |
error | -0.933 |
STE | -0.926 |
ally | -0.923 |
brand | -0.903 |
Token |
|
Token ID | 198 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
own | +0.302 |
error | +0.293 |
STE | +0.291 |
ally | +0.290 |
brand | +0.284 |
Neg logit contributions | |
arag | -0.312 |
entary | -0.296 |
hran | -0.282 |
chens | -0.272 |
ptic | -0.265 |
Token | Trump |
Token ID | 6170 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
own | +0.338 |
STE | +0.325 |
error | +0.324 |
ally | +0.320 |
brand | +0.312 |
Neg logit contributions | |
arag | -0.528 |
entary | -0.509 |
hran | -0.489 |
chens | -0.474 |
ptic | -0.461 |
Token | 's |
Token ID | 338 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
arag | +1.617 |
entary | +1.534 |
hran | +1.459 |
chens | +1.401 |
ptic | +1.367 |
Neg logit contributions | |
own | -1.662 |
error | -1.610 |
STE | -1.602 |
ally | -1.595 |
brand | -1.564 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
arag | +0.884 |
entary | +0.844 |
hran | +0.807 |
chens | +0.779 |
ptic | +0.763 |
Neg logit contributions | |
own | -0.708 |
error | -0.683 |
STE | -0.679 |
ally | -0.676 |
brand | -0.660 |
Token | Why |
Token ID | 5195 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
own | +3.089 |
STE | +3.009 |
error | +2.982 |
ally | +2.907 |
brand | +2.877 |
Neg logit contributions | |
arag | -4.839 |
entary | -4.686 |
hran | -4.503 |
chens | -4.352 |
ptic | -4.214 |
Token | automation |
Token ID | 22771 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
arag | +1.910 |
entary | +1.807 |
hran | +1.720 |
chens | +1.654 |
ptic | +1.609 |
Neg logit contributions | |
own | -2.041 |
error | -1.977 |
STE | -1.969 |
ally | -1.959 |
brand | -1.921 |
Token | rather |
Token ID | 2138 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
own | +0.506 |
error | +0.489 |
ally | +0.488 |
STE | +0.485 |
brand | +0.477 |
Neg logit contributions | |
arag | -0.431 |
entary | -0.405 |
hran | -0.383 |
chens | -0.366 |
ptic | -0.356 |
Token | than |
Token ID | 621 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
own | +0.646 |
error | +0.621 |
ally | +0.619 |
STE | +0.618 |
brand | +0.602 |
Neg logit contributions | |
arag | -0.741 |
entary | -0.703 |
hran | -0.672 |
chens | -0.647 |
ptic | -0.631 |
Token | Brexit |
Token ID | 11435 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
own | +0.597 |
error | +0.577 |
STE | +0.575 |
ally | +0.573 |
brand | +0.562 |
Neg logit contributions | |
arag | -0.514 |
entary | -0.483 |
hran | -0.459 |
chens | -0.440 |
ptic | -0.427 |
Token | is |
Token ID | 318 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
arag | +6.042 |
entary | +5.727 |
hran | +5.386 |
chens | +5.244 |
ptic | +5.121 |
Neg logit contributions | |
own | -7.982 |
error | -7.872 |
STE | -7.846 |
Interstitial | -7.749 |
licensed | -7.664 |
Token | the |
Token ID | 262 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
own | +1.207 |
ally | +1.178 |
error | +1.170 |
STE | +1.166 |
brand | +1.141 |
Neg logit contributions | |
arag | -1.197 |
entary | -1.138 |
hran | -1.072 |
chens | -1.033 |
ptic | -0.996 |
Token | prime |
Token ID | 6994 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
arag | +0.630 |
entary | +0.596 |
hran | +0.566 |
chens | +0.542 |
ptic | +0.527 |
Neg logit contributions | |
own | -0.703 |
error | -0.682 |
STE | -0.679 |
ally | -0.676 |
brand | -0.663 |
Token | challenge |
Token ID | 4427 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
arag | +4.529 |
entary | +4.352 |
hran | +4.068 |
ptic | +3.892 |
chens | +3.884 |
Neg logit contributions | |
own | -5.220 |
error | -5.084 |
STE | -5.039 |
licensed | -4.993 |
Interstitial | -4.971 |
Token | Belfast |
Token ID | 29713 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
arag | +0.389 |
entary | +0.369 |
hran | +0.351 |
chens | +0.336 |
ptic | +0.327 |
Neg logit contributions | |
own | -0.417 |
error | -0.404 |
STE | -0.402 |
ally | -0.401 |
brand | -0.393 |
Token | also |
Token ID | 635 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
arag | +0.744 |
entary | +0.698 |
hran | +0.657 |
chens | +0.624 |
ptic | +0.605 |
Neg logit contributions | |
own | -1.058 |
error | -1.028 |
STE | -1.025 |
ally | -1.022 |
brand | -1.004 |
Token | discuss |
Token ID | 2112 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
own | +0.035 |
error | +0.034 |
ally | +0.034 |
STE | +0.034 |
brand | +0.033 |
Neg logit contributions | |
arag | -0.024 |
entary | -0.022 |
hran | -0.021 |
chens | -0.020 |
ptic | -0.019 |
Token | possible |
Token ID | 1744 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
arag | +1.153 |
entary | +1.090 |
hran | +1.035 |
chens | +0.991 |
ptic | +0.965 |
Neg logit contributions | |
own | -1.308 |
error | -1.269 |
STE | -1.264 |
ally | -1.255 |
brand | -1.235 |
Token | post |
Token ID | 1281 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
arag | +1.776 |
entary | +1.666 |
hran | +1.572 |
chens | +1.494 |
ptic | +1.451 |
Neg logit contributions | |
own | -2.469 |
error | -2.405 |
STE | -2.391 |
ally | -2.378 |
brand | -2.346 |
Token | - |
Token ID | 12 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
arag | +2.657 |
entary | +2.458 |
hran | +2.373 |
chens | +2.226 |
ptic | +2.182 |
Neg logit contributions | |
own | -3.345 |
STE | -3.298 |
error | -3.293 |
ally | -3.211 |
Interstitial | -3.206 |
Token | Brexit |
Token ID | 40730 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
arag | +2.968 |
entary | +2.787 |
hran | +2.709 |
chens | +2.590 |
ptic | +2.558 |
Neg logit contributions | |
own | -2.077 |
STE | -2.015 |
ally | -1.994 |
error | -1.993 |
Interstitial | -1.954 |
Token | trade |
Token ID | 3292 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
arag | +5.402 |
entary | +5.025 |
hran | +4.690 |
chens | +4.394 |
arial | +4.372 |
Neg logit contributions | |
error | -8.665 |
own | -8.642 |
Interstitial | -8.619 |
licensed | -8.556 |
STE | -8.491 |
Token | ties |
Token ID | 8470 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
arag | +1.017 |
entary | +0.957 |
hran | +0.901 |
chens | +0.861 |
ptic | +0.835 |
Neg logit contributions | |
own | -1.368 |
error | -1.329 |
STE | -1.324 |
ally | -1.321 |
brand | -1.297 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
arag | +2.668 |
entary | +2.492 |
hran | +2.405 |
chens | +2.271 |
ptic | +2.175 |
Neg logit contributions | |
own | -3.757 |
error | -3.702 |
STE | -3.667 |
Interstitial | -3.618 |
ally | -3.592 |
Token |
|
Token ID | 198 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
arag | +0.269 |
entary | +0.256 |
hran | +0.243 |
chens | +0.234 |
ptic | +0.228 |
Neg logit contributions | |
own | -0.268 |
error | -0.259 |
STE | -0.258 |
ally | -0.257 |
brand | -0.251 |
Token |
|
Token ID | 198 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
own | +0.868 |
error | +0.839 |
STE | +0.835 |
ally | +0.832 |
brand | +0.814 |
Neg logit contributions | |
arag | -0.925 |
entary | -0.880 |
hran | -0.839 |
chens | -0.804 |
ptic | -0.785 |
Token |
|
Token ID | 198 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
arag | +0.059 |
entary | +0.056 |
hran | +0.054 |
chens | +0.052 |
ptic | +0.050 |
Neg logit contributions | |
own | -0.052 |
error | -0.051 |
STE | -0.050 |
ally | -0.050 |
brand | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
arag | +0.562 |
entary | +0.533 |
hran | +0.507 |
chens | +0.491 |
ptic | +0.479 |
Neg logit contributions | |
own | -0.575 |
error | -0.557 |
STE | -0.555 |
ally | -0.551 |
brand | -0.542 |
Token | See |
Token ID | 6214 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
arag | +0.843 |
entary | +0.801 |
hran | +0.769 |
chens | +0.744 |
ptic | +0.730 |
Neg logit contributions | |
own | -0.616 |
error | -0.593 |
STE | -0.589 |
ally | -0.586 |
brand | -0.571 |
Token | also |
Token ID | 635 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
arag | +4.357 |
entary | +4.000 |
hran | +3.849 |
chens | +3.624 |
ptic | +3.507 |
Neg logit contributions | |
own | -5.646 |
STE | -5.539 |
error | -5.524 |
ally | -5.390 |
licensed | -5.332 |
Token | [ |
Token ID | 685 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
arag | +1.232 |
entary | +1.172 |
hran | +1.123 |
chens | +1.085 |
ptic | +1.060 |
Neg logit contributions | |
own | -0.992 |
error | -0.957 |
STE | -0.950 |
ally | -0.940 |
brand | -0.918 |
Token | edit |
Token ID | 4370 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
arag | +3.286 |
entary | +2.882 |
hran | +2.770 |
chens | +2.700 |
ptic | +2.660 |
Neg logit contributions | |
ensical | -6.552 |
own | -6.496 |
STE | -6.433 |
Interstitial | -6.378 |
ally | -6.262 |
Token | ] |
Token ID | 2361 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
arag | +5.584 |
entary | +5.073 |
chens | +5.049 |
hran | +4.961 |
ptic | +4.736 |
Neg logit contributions | |
ensical | -8.453 |
own | -8.115 |
Interstitial | -8.050 |
STE | -7.974 |
ally | -7.904 |
Token |
|
Token ID | 198 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
arag | +4.826 |
entary | +4.520 |
hran | +4.345 |
chens | +4.173 |
ptic | +4.008 |
Neg logit contributions | |
own | -4.967 |
error | -4.834 |
STE | -4.829 |
ally | -4.707 |
brand | -4.688 |
Token |
|
Token ID | 198 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
arag | +3.167 |
entary | +2.933 |
hran | +2.791 |
chens | +2.777 |
ptic | +2.722 |
Neg logit contributions | |
ensical | -4.170 |
own | -4.051 |
error | -3.957 |
STE | -3.926 |
Interstitial | -3.891 |
Token | References |
Token ID | 19927 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
arag | +4.460 |
entary | +4.188 |
hran | +4.063 |
chens | +3.941 |
ptic | +3.910 |
Neg logit contributions | |
own | -2.305 |
error | -2.196 |
STE | -2.179 |
ally | -2.159 |
ensical | -2.088 |
Token | [ |
Token ID | 685 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
arag | +3.105 |
entary | +2.949 |
hran | +2.828 |
chens | +2.729 |
ptic | +2.632 |
Neg logit contributions | |
own | -2.670 |
STE | -2.578 |
error | -2.577 |
ally | -2.520 |
Interstitial | -2.518 |
Token |
|
Token ID | 198 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
own | +0.050 |
error | +0.048 |
STE | +0.048 |
ally | +0.048 |
brand | +0.047 |
Neg logit contributions | |
arag | -0.054 |
entary | -0.051 |
hran | -0.049 |
chens | -0.047 |
ptic | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
arag | +1.567 |
entary | +1.474 |
hran | +1.403 |
chens | +1.369 |
ptic | +1.343 |
Neg logit contributions | |
own | -1.749 |
error | -1.699 |
STE | -1.695 |
ensical | -1.687 |
ally | -1.678 |
Token | See |
Token ID | 6214 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
arag | +2.269 |
entary | +2.161 |
hran | +2.068 |
chens | +2.009 |
ptic | +1.995 |
Neg logit contributions | |
own | -1.400 |
error | -1.333 |
ally | -1.324 |
STE | -1.315 |
brand | -1.281 |
Token | also |
Token ID | 635 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
arag | +4.760 |
entary | +4.461 |
hran | +4.152 |
chens | +3.959 |
ptic | +3.943 |
Neg logit contributions | |
own | -6.276 |
STE | -6.167 |
error | -6.134 |
ally | -6.011 |
Interstitial | -5.994 |
Token | [ |
Token ID | 685 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
arag | +1.985 |
entary | +1.895 |
hran | +1.802 |
chens | +1.751 |
ptic | +1.718 |
Neg logit contributions | |
own | -1.606 |
error | -1.546 |
STE | -1.535 |
ally | -1.517 |
brand | -1.493 |
Token | edit |
Token ID | 4370 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
arag | +3.213 |
entary | +2.830 |
chens | +2.695 |
hran | +2.682 |
ptic | +2.612 |
Neg logit contributions | |
ensical | -6.905 |
own | -6.688 |
Interstitial | -6.566 |
STE | -6.561 |
ally | -6.461 |
Token | ] |
Token ID | 2361 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
arag | +5.469 |
chens | +4.996 |
entary | +4.973 |
hran | +4.867 |
ptic | +4.692 |
Neg logit contributions | |
ensical | -8.603 |
own | -8.151 |
Interstitial | -8.081 |
STE | -8.002 |
ally | -7.931 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
arag | +4.837 |
entary | +4.622 |
hran | +4.317 |
chens | +4.186 |
ptic | +4.077 |
Neg logit contributions | |
own | -4.956 |
STE | -4.824 |
error | -4.816 |
brand | -4.732 |
Interstitial | -4.725 |
Token | I |
Token ID | 40 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
own | +2.409 |
STE | +2.333 |
error | +2.322 |
ally | +2.270 |
brand | +2.237 |
Neg logit contributions | |
arag | -3.814 |
entary | -3.685 |
hran | -3.543 |
chens | -3.427 |
ptic | -3.327 |
Token | ke |
Token ID | 365 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
own | +0.889 |
STE | +0.857 |
error | +0.856 |
ally | +0.854 |
brand | +0.832 |
Neg logit contributions | |
arag | -0.932 |
entary | -0.889 |
hran | -0.846 |
chens | -0.809 |
ptic | -0.787 |
Token | a |
Token ID | 64 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
arag | +1.996 |
entary | +1.897 |
hran | +1.812 |
chens | +1.738 |
ptic | +1.704 |
Neg logit contributions | |
own | -1.953 |
error | -1.896 |
STE | -1.887 |
ally | -1.872 |
brand | -1.835 |
Token | , |
Token ID | 11 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
arag | +0.186 |
entary | +0.176 |
hran | +0.167 |
chens | +0.159 |
ptic | +0.156 |
Neg logit contributions | |
own | -0.209 |
error | -0.201 |
ally | -0.201 |
STE | -0.200 |
brand | -0.196 |
Token | and |
Token ID | 290 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
arag | +0.258 |
entary | +0.245 |
hran | +0.233 |
chens | +0.222 |
ptic | +0.216 |
Neg logit contributions | |
own | -0.283 |
error | -0.273 |
ally | -0.272 |
STE | -0.271 |
brand | -0.266 |
Token | from |
Token ID | 422 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
own | +0.638 |
ally | +0.618 |
error | +0.614 |
STE | +0.611 |
brand | +0.596 |
Neg logit contributions | |
arag | -0.663 |
entary | -0.632 |
hran | -0.600 |
chens | -0.574 |
ptic | -0.559 |
Token | this |
Token ID | 428 |
Feature activation | +5.56e-02 |
Pos logit contributions | |
own | +2.091 |
ally | +2.047 |
STE | +2.005 |
error | +2.004 |
brand | +1.962 |
Neg logit contributions | |
arag | -2.216 |
entary | -2.099 |
hran | -2.005 |
chens | -1.924 |
ptic | -1.877 |
Token | perspective |
Token ID | 6650 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
own | +0.133 |
ally | +0.129 |
error | +0.128 |
STE | +0.128 |
brand | +0.124 |
Neg logit contributions | |
arag | -0.139 |
entary | -0.131 |
hran | -0.126 |
chens | -0.121 |
ptic | -0.117 |
Token | Brexit |
Token ID | 11435 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
arag | +0.417 |
entary | +0.396 |
hran | +0.377 |
chens | +0.363 |
ptic | +0.353 |
Neg logit contributions | |
own | -0.395 |
error | -0.381 |
ally | -0.381 |
STE | -0.379 |
brand | -0.369 |
Token | could |
Token ID | 714 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
arag | +5.714 |
entary | +5.359 |
hran | +5.131 |
chens | +4.956 |
ptic | +4.848 |
Neg logit contributions | |
own | -8.184 |
error | -8.118 |
STE | -8.056 |
Interstitial | -7.885 |
licensed | -7.866 |
Token | deliver |
Token ID | 5203 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
arag | +0.174 |
entary | +0.164 |
hran | +0.155 |
chens | +0.148 |
ptic | +0.142 |
Neg logit contributions | |
own | -0.208 |
error | -0.201 |
ally | -0.201 |
STE | -0.201 |
brand | -0.196 |
Token | benefits |
Token ID | 4034 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
arag | +0.073 |
entary | +0.069 |
hran | +0.066 |
chens | +0.063 |
ptic | +0.061 |
Neg logit contributions | |
own | -0.080 |
ally | -0.078 |
error | -0.077 |
STE | -0.077 |
brand | -0.075 |
Token | for |
Token ID | 329 |
Feature activation | +9.57e-02 |
Pos logit contributions | |
arag | +0.052 |
entary | +0.049 |
hran | +0.046 |
chens | +0.044 |
ptic | +0.043 |
Neg logit contributions | |
own | -0.062 |
error | -0.060 |
ally | -0.060 |
STE | -0.060 |
brand | -0.059 |
Token | some |
Token ID | 617 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
own | +0.241 |
ally | +0.233 |
STE | +0.231 |
error | +0.231 |
brand | +0.225 |
Neg logit contributions | |
arag | -0.228 |
entary | -0.216 |
hran | -0.206 |
chens | -0.196 |
ptic | -0.192 |
Token | and |
Token ID | 290 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
own | +0.341 |
error | +0.332 |
STE | +0.331 |
ally | +0.328 |
brand | +0.323 |
Neg logit contributions | |
arag | -0.270 |
entary | -0.255 |
hran | -0.242 |
chens | -0.232 |
ptic | -0.225 |
Token | frequency |
Token ID | 8373 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
arag | +0.513 |
entary | +0.486 |
hran | +0.464 |
chens | +0.445 |
ptic | +0.435 |
Neg logit contributions | |
own | -0.522 |
error | -0.506 |
STE | -0.504 |
ally | -0.500 |
brand | -0.492 |
Token | with |
Token ID | 351 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
own | +1.891 |
error | +1.836 |
STE | +1.828 |
ally | +1.821 |
brand | +1.788 |
Neg logit contributions | |
arag | -1.559 |
entary | -1.471 |
hran | -1.393 |
chens | -1.332 |
ptic | -1.295 |
Token | which |
Token ID | 543 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
own | +1.413 |
error | +1.357 |
ally | +1.354 |
STE | +1.345 |
brand | +1.321 |
Neg logit contributions | |
arag | -1.433 |
entary | -1.364 |
hran | -1.300 |
chens | -1.251 |
ptic | -1.207 |
Token | the |
Token ID | 262 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
arag | +0.817 |
entary | +0.774 |
hran | +0.736 |
chens | +0.706 |
ptic | +0.688 |
Neg logit contributions | |
own | -0.874 |
error | -0.847 |
STE | -0.843 |
ally | -0.839 |
brand | -0.823 |
Token | Mitt |
Token ID | 16627 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
own | +0.289 |
error | +0.280 |
STE | +0.279 |
ally | +0.278 |
brand | +0.273 |
Neg logit contributions | |
arag | -0.242 |
entary | -0.228 |
hran | -0.216 |
chens | -0.207 |
ptic | -0.201 |
Token | Romney |
Token ID | 8431 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
arag | +5.719 |
entary | +5.315 |
hran | +4.972 |
chens | +4.733 |
ptic | +4.541 |
Neg logit contributions | |
own | -8.343 |
STE | -8.267 |
error | -8.263 |
Interstitial | -8.127 |
licensed | -7.984 |
Token | / |
Token ID | 14 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
arag | +4.642 |
entary | +4.307 |
hran | +4.002 |
chens | +3.865 |
ptic | +3.816 |
Neg logit contributions | |
own | -6.945 |
STE | -6.780 |
error | -6.769 |
licensed | -6.595 |
Interstitial | -6.573 |
Token | Paul |
Token ID | 12041 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
arag | +4.404 |
entary | +4.136 |
hran | +4.005 |
chens | +3.891 |
ptic | +3.820 |
Neg logit contributions | |
own | -3.137 |
error | -3.035 |
STE | -2.997 |
ally | -2.945 |
Interstitial | -2.910 |
Token | Ryan |
Token ID | 6047 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
arag | +2.840 |
entary | +2.654 |
hran | +2.498 |
chens | +2.416 |
ptic | +2.347 |
Neg logit contributions | |
own | -3.527 |
STE | -3.450 |
error | -3.441 |
ally | -3.392 |
Interstitial | -3.345 |
Token | ticket |
Token ID | 7846 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
arag | +1.240 |
entary | +1.173 |
hran | +1.108 |
chens | +1.056 |
ptic | +1.021 |
Neg logit contributions | |
own | -1.577 |
error | -1.531 |
ally | -1.523 |
STE | -1.523 |
brand | -1.495 |
Token | frequency |
Token ID | 8373 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
own | +1.131 |
error | +1.094 |
ally | +1.088 |
STE | +1.085 |
brand | +1.060 |
Neg logit contributions | |
arag | -1.059 |
entary | -1.003 |
hran | -0.950 |
chens | -0.911 |
ptic | -0.883 |
Token | , |
Token ID | 11 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
own | +1.008 |
error | +0.984 |
ally | +0.980 |
STE | +0.975 |
brand | +0.953 |
Neg logit contributions | |
arag | -0.878 |
entary | -0.830 |
hran | -0.791 |
chens | -0.753 |
ptic | -0.727 |
Token | and |
Token ID | 290 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
arag | +0.480 |
entary | +0.455 |
hran | +0.433 |
chens | +0.416 |
ptic | +0.404 |
Neg logit contributions | |
own | -0.503 |
error | -0.487 |
STE | -0.485 |
ally | -0.484 |
brand | -0.474 |
Token | asked |
Token ID | 1965 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
own | +0.286 |
error | +0.275 |
STE | +0.274 |
ally | +0.274 |
brand | +0.266 |
Neg logit contributions | |
arag | -0.346 |
entary | -0.330 |
hran | -0.316 |
chens | -0.305 |
ptic | -0.297 |
Token | , |
Token ID | 11 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
own | +1.906 |
ally | +1.841 |
error | +1.814 |
STE | +1.798 |
brand | +1.751 |
Neg logit contributions | |
arag | -2.022 |
entary | -1.914 |
hran | -1.834 |
chens | -1.772 |
ptic | -1.706 |
Token | " |
Token ID | 366 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
own | +1.834 |
error | +1.777 |
STE | +1.767 |
ally | +1.766 |
brand | +1.729 |
Neg logit contributions | |
arag | -1.328 |
entary | -1.250 |
hran | -1.184 |
chens | -1.128 |
ptic | -1.086 |
Token | Ron |
Token ID | 23672 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
own | +3.242 |
STE | +3.056 |
error | +3.055 |
ally | +3.008 |
brand | +2.937 |
Neg logit contributions | |
arag | -5.944 |
entary | -5.790 |
hran | -5.590 |
chens | -5.378 |
ptic | -5.224 |
Token | . |
Token ID | 13 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
own | +3.097 |
ally | +3.010 |
error | +2.960 |
STE | +2.940 |
brand | +2.922 |
Neg logit contributions | |
arag | -3.253 |
entary | -3.097 |
hran | -2.961 |
chens | -2.815 |
ptic | -2.768 |
Token | This |
Token ID | 770 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
own | +1.234 |
error | +1.189 |
STE | +1.185 |
ally | +1.182 |
brand | +1.153 |
Neg logit contributions | |
arag | -1.386 |
entary | -1.320 |
hran | -1.264 |
chens | -1.205 |
ptic | -1.178 |
Token | is |
Token ID | 318 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
arag | +1.883 |
entary | +1.772 |
hran | +1.675 |
chens | +1.597 |
ptic | +1.552 |
Neg logit contributions | |
own | -2.468 |
error | -2.399 |
STE | -2.391 |
ally | -2.378 |
brand | -2.339 |
Token | George |
Token ID | 4502 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
arag | +1.058 |
entary | +1.004 |
hran | +0.956 |
chens | +0.917 |
ptic | +0.896 |
Neg logit contributions | |
own | -1.065 |
error | -1.031 |
STE | -1.026 |
ally | -1.021 |
brand | -1.002 |
Token | a |
Token ID | 257 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
own | +0.753 |
ally | +0.725 |
error | +0.725 |
STE | +0.725 |
brand | +0.708 |
Neg logit contributions | |
arag | -0.733 |
entary | -0.698 |
hran | -0.663 |
chens | -0.637 |
ptic | -0.619 |
Token | player |
Token ID | 2137 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
own | +1.051 |
STE | +1.009 |
ally | +1.008 |
error | +1.006 |
brand | +0.991 |
Neg logit contributions | |
arag | -1.030 |
entary | -0.977 |
hran | -0.930 |
chens | -0.890 |
ptic | -0.860 |
Token | to |
Token ID | 284 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
own | +1.740 |
ally | +1.679 |
error | +1.671 |
STE | +1.661 |
brand | +1.631 |
Neg logit contributions | |
arag | -1.735 |
entary | -1.652 |
hran | -1.565 |
chens | -1.514 |
ptic | -1.459 |
Token | their |
Token ID | 511 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
arag | +0.720 |
entary | +0.683 |
hran | +0.648 |
chens | +0.622 |
ptic | +0.604 |
Neg logit contributions | |
own | -0.779 |
error | -0.753 |
STE | -0.752 |
ally | -0.749 |
brand | -0.734 |
Token | particular |
Token ID | 1948 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
own | +1.252 |
ally | +1.203 |
STE | +1.199 |
error | +1.194 |
brand | +1.173 |
Neg logit contributions | |
arag | -1.172 |
entary | -1.121 |
hran | -1.064 |
chens | -1.021 |
ptic | -0.982 |
Token | franchise |
Token ID | 8663 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
own | +3.116 |
ally | +3.011 |
brand | +2.949 |
STE | +2.945 |
error | +2.923 |
Neg logit contributions | |
arag | -3.011 |
entary | -2.888 |
hran | -2.757 |
chens | -2.643 |
ptic | -2.542 |
Token | , |
Token ID | 11 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
own | +4.332 |
ally | +4.239 |
STE | +4.128 |
error | +4.104 |
brand | +4.097 |
Neg logit contributions | |
arag | -4.523 |
entary | -4.291 |
hran | -4.138 |
chens | -3.975 |
ptic | -3.783 |
Token | it |
Token ID | 340 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
own | +0.946 |
STE | +0.902 |
ally | +0.901 |
error | +0.901 |
brand | +0.878 |
Neg logit contributions | |
arag | -1.412 |
entary | -1.361 |
hran | -1.303 |
chens | -1.260 |
ptic | -1.226 |
Token | 's |
Token ID | 338 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
own | +0.090 |
ally | +0.087 |
error | +0.086 |
STE | +0.086 |
brand | +0.084 |
Neg logit contributions | |
arag | -0.077 |
entary | -0.073 |
hran | -0.069 |
chens | -0.065 |
ptic | -0.063 |
Token | a |
Token ID | 257 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
arag | +0.354 |
entary | +0.335 |
hran | +0.317 |
chens | +0.304 |
ptic | +0.295 |
Neg logit contributions | |
own | -0.390 |
error | -0.377 |
ally | -0.376 |
STE | -0.376 |
brand | -0.367 |
Token | multif |
Token ID | 43543 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
arag | +0.233 |
entary | +0.219 |
hran | +0.206 |
chens | +0.198 |
ptic | +0.190 |
Neg logit contributions | |
own | -0.302 |
STE | -0.292 |
error | -0.291 |
ally | -0.291 |
brand | -0.285 |
Token | secretary |
Token ID | 7705 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
arag | +2.228 |
entary | +2.088 |
hran | +1.961 |
chens | +1.840 |
ptic | +1.776 |
Neg logit contributions | |
own | -3.647 |
STE | -3.563 |
error | -3.539 |
ally | -3.496 |
licensed | -3.458 |
Token | . |
Token ID | 13 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
arag | +2.761 |
entary | +2.594 |
hran | +2.460 |
chens | +2.338 |
ptic | +2.266 |
Neg logit contributions | |
own | -3.472 |
error | -3.376 |
STE | -3.366 |
ally | -3.329 |
licensed | -3.280 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
arag | +0.606 |
entary | +0.575 |
hran | +0.547 |
chens | +0.526 |
ptic | +0.513 |
Neg logit contributions | |
own | -0.623 |
error | -0.603 |
STE | -0.600 |
ally | -0.599 |
brand | -0.586 |
Token | AL |
Token ID | 1847 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
own | +3.332 |
STE | +3.250 |
error | +3.215 |
ally | +3.134 |
brand | +3.103 |
Neg logit contributions | |
arag | -5.194 |
entary | -5.037 |
hran | -4.834 |
chens | -4.669 |
ptic | -4.521 |
Token | B |
Token ID | 33 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
arag | +5.294 |
entary | +5.012 |
hran | +4.821 |
chens | +4.636 |
ptic | +4.626 |
Neg logit contributions | |
own | -3.890 |
ally | -3.734 |
error | -3.713 |
STE | -3.562 |
Interstitial | -3.551 |
Token | ION |
Token ID | 2849 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
arag | +0.724 |
entary | +0.699 |
hran | +0.677 |
chens | +0.659 |
ptic | +0.648 |
Neg logit contributions | |
own | -0.261 |
error | -0.245 |
STE | -0.244 |
ally | -0.241 |
brand | -0.232 |
Token | are |
Token ID | 389 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
own | +5.177 |
STE | +5.112 |
ally | +4.926 |
error | +4.887 |
OWN | +4.887 |
Neg logit contributions | |
arag | -5.643 |
entary | -5.212 |
hran | -5.160 |
chens | -4.779 |
ptic | -4.738 |
Token | delighted |
Token ID | 20707 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
own | +1.033 |
ally | +1.001 |
error | +0.993 |
STE | +0.990 |
brand | +0.977 |
Neg logit contributions | |
arag | -0.975 |
entary | -0.934 |
hran | -0.876 |
chens | -0.842 |
ptic | -0.812 |
Token | to |
Token ID | 284 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
own | +2.414 |
ally | +2.343 |
error | +2.332 |
STE | +2.326 |
brand | +2.291 |
Neg logit contributions | |
arag | -2.034 |
entary | -1.910 |
hran | -1.801 |
chens | -1.724 |
ptic | -1.678 |
Token | announce |
Token ID | 5453 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
arag | +0.101 |
entary | +0.097 |
hran | +0.092 |
chens | +0.089 |
ptic | +0.087 |
Neg logit contributions | |
own | -0.090 |
error | -0.087 |
STE | -0.086 |
ally | -0.086 |
brand | -0.084 |
Token | the |
Token ID | 262 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
own | +2.197 |
ally | +2.122 |
STE | +2.106 |
error | +2.103 |
brand | +2.071 |
Neg logit contributions | |
arag | -2.402 |
entary | -2.279 |
hran | -2.183 |
chens | -2.104 |
ptic | -2.050 |
Token | their |
Token ID | 511 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
own | +0.941 |
error | +0.910 |
STE | +0.906 |
ally | +0.904 |
brand | +0.885 |
Neg logit contributions | |
arag | -0.930 |
entary | -0.883 |
hran | -0.841 |
chens | -0.807 |
ptic | -0.786 |
Token | own |
Token ID | 898 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
arag | +0.511 |
entary | +0.486 |
hran | +0.464 |
chens | +0.448 |
ptic | +0.438 |
Neg logit contributions | |
own | -0.445 |
error | -0.432 |
STE | -0.429 |
ally | -0.426 |
brand | -0.417 |
Token | index |
Token ID | 6376 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
own | +1.391 |
error | +1.340 |
STE | +1.336 |
ally | +1.335 |
brand | +1.307 |
Neg logit contributions | |
arag | -1.453 |
entary | -1.387 |
hran | -1.321 |
chens | -1.265 |
ptic | -1.234 |
Token | - |
Token ID | 12 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
own | +2.002 |
ally | +1.935 |
STE | +1.909 |
error | +1.904 |
brand | +1.871 |
Neg logit contributions | |
arag | -2.399 |
entary | -2.284 |
hran | -2.199 |
chens | -2.092 |
ptic | -2.050 |
Token | based |
Token ID | 3106 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
arag | +0.104 |
entary | +0.100 |
hran | +0.096 |
chens | +0.094 |
ptic | +0.092 |
Neg logit contributions | |
own | -0.054 |
error | -0.052 |
STE | -0.052 |
ally | -0.051 |
brand | -0.049 |
Token | discovery |
Token ID | 9412 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
arag | +1.697 |
entary | +1.607 |
hran | +1.530 |
chens | +1.481 |
ptic | +1.449 |
Neg logit contributions | |
own | -1.734 |
error | -1.685 |
STE | -1.678 |
ally | -1.658 |
brand | -1.637 |
Token | capability |
Token ID | 12971 |
Feature activation | -8.15e-02 |
Pos logit contributions | |
own | +4.119 |
ally | +4.057 |
STE | +3.928 |
error | +3.925 |
brand | +3.847 |
Neg logit contributions | |
arag | -4.641 |
entary | -4.457 |
hran | -4.193 |
chens | -4.000 |
ptic | -3.907 |
Token | to |
Token ID | 284 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
arag | +0.179 |
entary | +0.169 |
hran | +0.160 |
chens | +0.153 |
ptic | +0.148 |
Neg logit contributions | |
own | -0.219 |
error | -0.212 |
STE | -0.211 |
ally | -0.211 |
brand | -0.207 |
Token | integrate |
Token ID | 19386 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
arag | +1.590 |
entary | +1.500 |
hran | +1.420 |
chens | +1.364 |
ptic | +1.328 |
Neg logit contributions | |
own | -1.976 |
error | -1.921 |
STE | -1.911 |
ally | -1.897 |
brand | -1.866 |
Token | E |
Token ID | 412 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
own | +0.062 |
error | +0.060 |
STE | +0.060 |
ally | +0.060 |
brand | +0.058 |
Neg logit contributions | |
arag | -0.064 |
entary | -0.061 |
hran | -0.058 |
chens | -0.056 |
ptic | -0.054 |
Token | DS |
Token ID | 5258 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
own | +0.369 |
error | +0.356 |
STE | +0.354 |
ally | +0.353 |
brand | +0.346 |
Neg logit contributions | |
arag | -0.393 |
entary | -0.374 |
hran | -0.357 |
chens | -0.345 |
ptic | -0.337 |
Token | ep |
Token ID | 538 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
own | +0.241 |
ally | +0.233 |
error | +0.233 |
STE | +0.231 |
brand | +0.229 |
Neg logit contributions | |
arag | -0.198 |
entary | -0.189 |
hran | -0.179 |
chens | -0.169 |
ptic | -0.163 |
Token | shows |
Token ID | 2523 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
arag | +0.621 |
entary | +0.591 |
hran | +0.561 |
chens | +0.537 |
ptic | +0.522 |
Neg logit contributions | |
own | -0.668 |
error | -0.644 |
STE | -0.641 |
ally | -0.640 |
brand | -0.628 |
Token | . |
Token ID | 13 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
arag | +0.364 |
entary | +0.344 |
hran | +0.326 |
chens | +0.312 |
ptic | +0.304 |
Neg logit contributions | |
own | -0.425 |
error | -0.412 |
STE | -0.410 |
ally | -0.409 |
brand | -0.401 |
Token |
|
Token ID | 198 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
own | +0.385 |
error | +0.373 |
STE | +0.371 |
ally | +0.369 |
brand | +0.362 |
Neg logit contributions | |
arag | -0.402 |
entary | -0.382 |
hran | -0.365 |
chens | -0.351 |
ptic | -0.342 |
Token |
|
Token ID | 198 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
own | +1.737 |
error | +1.672 |
STE | +1.669 |
ally | +1.660 |
brand | +1.623 |
Neg logit contributions | |
arag | -2.008 |
entary | -1.918 |
hran | -1.832 |
chens | -1.743 |
ptic | -1.698 |
Token | Social |
Token ID | 20636 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
own | +1.329 |
STE | +1.277 |
error | +1.268 |
ally | +1.252 |
brand | +1.222 |
Neg logit contributions | |
arag | -2.379 |
entary | -2.288 |
hran | -2.215 |
chens | -2.140 |
ptic | -2.086 |
Token | - |
Token ID | 12 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
own | +4.810 |
ally | +4.696 |
error | +4.630 |
STE | +4.530 |
brand | +4.527 |
Neg logit contributions | |
arag | -4.483 |
entary | -4.247 |
hran | -4.033 |
chens | -3.995 |
ptic | -3.752 |
Token | net |
Token ID | 3262 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
own | +3.354 |
error | +3.233 |
ally | +3.183 |
STE | +3.155 |
brand | +3.147 |
Neg logit contributions | |
arag | -5.141 |
entary | -4.931 |
hran | -4.777 |
chens | -4.650 |
ptic | -4.446 |
Token | working |
Token ID | 16090 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
own | +2.350 |
error | +2.243 |
brand | +2.196 |
STE | +2.193 |
ally | +2.188 |
Neg logit contributions | |
arag | -3.921 |
entary | -3.775 |
hran | -3.599 |
chens | -3.482 |
ptic | -3.425 |
Token | and |
Token ID | 290 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
arag | +0.543 |
entary | +0.510 |
hran | +0.480 |
chens | +0.457 |
ptic | +0.442 |
Neg logit contributions | |
own | -0.766 |
error | -0.744 |
STE | -0.741 |
ally | -0.740 |
brand | -0.727 |
Token | news |
Token ID | 1705 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
own | +0.416 |
error | +0.404 |
STE | +0.402 |
ally | +0.401 |
brand | +0.394 |
Neg logit contributions | |
arag | -0.349 |
entary | -0.329 |
hran | -0.313 |
chens | -0.298 |
ptic | -0.289 |
Token | of |
Token ID | 286 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
arag | +0.744 |
entary | +0.703 |
hran | +0.664 |
chens | +0.636 |
ptic | +0.620 |
Neg logit contributions | |
own | -0.884 |
error | -0.859 |
STE | -0.856 |
ally | -0.846 |
brand | -0.836 |
Token | this |
Token ID | 428 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
own | +2.181 |
ally | +2.088 |
error | +2.084 |
STE | +2.080 |
brand | +2.035 |
Neg logit contributions | |
arag | -2.204 |
entary | -2.091 |
hran | -1.994 |
chens | -1.938 |
ptic | -1.877 |
Token | drama |
Token ID | 10512 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
arag | +0.068 |
entary | +0.064 |
hran | +0.061 |
chens | +0.059 |
ptic | +0.057 |
Neg logit contributions | |
own | -0.082 |
error | -0.080 |
STE | -0.080 |
ally | -0.080 |
brand | -0.078 |
Token | of |
Token ID | 286 |
Feature activation | -9.61e-02 |
Pos logit contributions | |
arag | +0.280 |
entary | +0.264 |
hran | +0.251 |
chens | +0.240 |
ptic | +0.234 |
Neg logit contributions | |
own | -0.323 |
error | -0.314 |
STE | -0.312 |
ally | -0.311 |
brand | -0.305 |
Token | commerce |
Token ID | 19497 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
arag | +0.222 |
entary | +0.210 |
hran | +0.200 |
chens | +0.192 |
ptic | +0.186 |
Neg logit contributions | |
own | -0.247 |
error | -0.239 |
STE | -0.238 |
ally | -0.237 |
brand | -0.233 |
Token | . |
Token ID | 13 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
own | +2.266 |
ally | +2.197 |
error | +2.181 |
STE | +2.162 |
brand | +2.127 |
Neg logit contributions | |
arag | -2.117 |
entary | -2.006 |
hran | -1.905 |
chens | -1.848 |
ptic | -1.792 |
Token | Act |
Token ID | 2191 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
own | +0.576 |
error | +0.555 |
STE | +0.554 |
ally | +0.549 |
brand | +0.539 |
Neg logit contributions | |
arag | -0.676 |
entary | -0.642 |
hran | -0.615 |
chens | -0.592 |
ptic | -0.578 |
Token | III |
Token ID | 6711 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
arag | +1.934 |
entary | +1.816 |
hran | +1.706 |
chens | +1.637 |
ptic | +1.585 |
Neg logit contributions | |
own | -2.662 |
error | -2.604 |
STE | -2.599 |
ally | -2.552 |
brand | -2.537 |
Token | remains |
Token ID | 3793 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
own | +1.073 |
error | +1.036 |
ally | +1.035 |
STE | +1.034 |
brand | +1.007 |
Neg logit contributions | |
arag | -1.032 |
entary | -0.977 |
hran | -0.932 |
chens | -0.891 |
ptic | -0.870 |
Token | to |
Token ID | 284 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
arag | +0.105 |
entary | +0.099 |
hran | +0.094 |
chens | +0.090 |
ptic | +0.088 |
Neg logit contributions | |
own | -0.115 |
error | -0.111 |
ally | -0.110 |
STE | -0.110 |
brand | -0.108 |
Token | be |
Token ID | 307 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
arag | +1.560 |
entary | +1.462 |
hran | +1.368 |
chens | +1.302 |
ptic | +1.268 |
Neg logit contributions | |
own | -2.296 |
STE | -2.244 |
error | -2.243 |
ally | -2.219 |
brand | -2.192 |
Token | country |
Token ID | 1499 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
own | +0.177 |
error | +0.171 |
STE | +0.171 |
ally | +0.171 |
brand | +0.167 |
Neg logit contributions | |
arag | -0.145 |
entary | -0.137 |
hran | -0.131 |
chens | -0.125 |
ptic | -0.120 |
Token | 's |
Token ID | 338 |
Feature activation | -8.25e-02 |
Pos logit contributions | |
own | +0.838 |
ally | +0.813 |
error | +0.811 |
STE | +0.804 |
brand | +0.790 |
Neg logit contributions | |
arag | -0.704 |
entary | -0.665 |
hran | -0.630 |
chens | -0.600 |
ptic | -0.584 |
Token | central |
Token ID | 4318 |
Feature activation | -5.98e-02 |
Pos logit contributions | |
arag | +0.181 |
entary | +0.170 |
hran | +0.162 |
chens | +0.155 |
ptic | +0.149 |
Neg logit contributions | |
own | -0.223 |
error | -0.216 |
ally | -0.215 |
STE | -0.215 |
brand | -0.211 |
Token | and |
Token ID | 290 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
arag | +0.129 |
entary | +0.121 |
hran | +0.115 |
chens | +0.110 |
ptic | +0.106 |
Neg logit contributions | |
own | -0.163 |
error | -0.158 |
ally | -0.158 |
STE | -0.158 |
brand | -0.154 |
Token | southern |
Token ID | 8372 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
arag | +0.336 |
entary | +0.314 |
hran | +0.294 |
chens | +0.279 |
ptic | +0.270 |
Neg logit contributions | |
own | -0.528 |
error | -0.515 |
STE | -0.513 |
ally | -0.510 |
brand | -0.503 |
Token | areas |
Token ID | 3006 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
arag | +0.389 |
entary | +0.368 |
hran | +0.350 |
chens | +0.335 |
ptic | +0.326 |
Neg logit contributions | |
own | -0.433 |
error | -0.419 |
STE | -0.417 |
ally | -0.417 |
brand | -0.408 |
Token | . |
Token ID | 13 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
own | +1.235 |
ally | +1.196 |
error | +1.195 |
STE | +1.187 |
brand | +1.161 |
Neg logit contributions | |
arag | -1.054 |
entary | -1.003 |
hran | -0.948 |
chens | -0.899 |
ptic | -0.877 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
arag | +0.567 |
entary | +0.539 |
hran | +0.513 |
chens | +0.493 |
ptic | +0.483 |
Neg logit contributions | |
own | -0.549 |
error | -0.531 |
STE | -0.531 |
ally | -0.527 |
brand | -0.516 |
Token | The |
Token ID | 464 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
own | +2.687 |
STE | +2.607 |
error | +2.591 |
ally | +2.531 |
brand | +2.499 |
Neg logit contributions | |
arag | -4.233 |
entary | -4.094 |
hran | -3.934 |
chens | -3.804 |
ptic | -3.691 |
Token | Globe |
Token ID | 18260 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
arag | +1.074 |
entary | +1.016 |
hran | +0.963 |
chens | +0.923 |
ptic | +0.900 |
Neg logit contributions | |
own | -1.209 |
error | -1.173 |
STE | -1.168 |
ally | -1.163 |
brand | -1.141 |
Token | 's |
Token ID | 338 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
arag | +1.049 |
entary | +0.989 |
hran | +0.935 |
chens | +0.890 |
ptic | +0.867 |
Neg logit contributions | |
own | -1.341 |
error | -1.304 |
STE | -1.299 |
ally | -1.292 |
brand | -1.270 |
Token |
|
Token ID | 198 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
own | +1.494 |
error | +1.443 |
STE | +1.429 |
ally | +1.427 |
brand | +1.401 |
Neg logit contributions | |
arag | -1.690 |
entary | -1.615 |
hran | -1.538 |
chens | -1.470 |
ptic | -1.434 |
Token |
|
Token ID | 198 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
own | +0.343 |
error | +0.332 |
STE | +0.330 |
ally | +0.329 |
brand | +0.322 |
Neg logit contributions | |
arag | -0.361 |
entary | -0.343 |
hran | -0.327 |
chens | -0.314 |
ptic | -0.306 |
Token | At |
Token ID | 2953 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
own | +0.371 |
error | +0.357 |
STE | +0.355 |
ally | +0.353 |
brand | +0.345 |
Neg logit contributions | |
arag | -0.494 |
entary | -0.472 |
hran | -0.453 |
chens | -0.437 |
ptic | -0.428 |
Token | this |
Token ID | 428 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
own | +0.633 |
error | +0.609 |
ally | +0.603 |
STE | +0.602 |
brand | +0.590 |
Neg logit contributions | |
arag | -0.813 |
entary | -0.780 |
hran | -0.748 |
chens | -0.719 |
ptic | -0.707 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
arag | +0.413 |
entary | +0.390 |
hran | +0.369 |
chens | +0.353 |
ptic | +0.343 |
Neg logit contributions | |
own | -0.505 |
error | -0.490 |
STE | -0.488 |
ally | -0.487 |
brand | -0.478 |
Token | � |
Token ID | 447 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
arag | +0.332 |
entary | +0.314 |
hran | +0.298 |
chens | +0.286 |
ptic | +0.279 |
Neg logit contributions | |
own | -0.369 |
error | -0.357 |
STE | -0.356 |
ally | -0.354 |
brand | -0.348 |
Token | � |
Token ID | 247 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
own | +0.249 |
error | +0.239 |
STE | +0.237 |
ally | +0.236 |
brand | +0.233 |
Neg logit contributions | |
arag | -0.263 |
entary | -0.252 |
hran | -0.239 |
chens | -0.231 |
ptic | -0.225 |
Token | s |
Token ID | 82 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
arag | +0.282 |
entary | +0.269 |
hran | +0.258 |
chens | +0.249 |
ptic | +0.243 |
Neg logit contributions | |
own | -0.225 |
error | -0.216 |
STE | -0.215 |
ally | -0.214 |
brand | -0.210 |
Token | goal |
Token ID | 3061 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
own | +1.859 |
error | +1.782 |
ally | +1.775 |
STE | +1.754 |
brand | +1.727 |
Neg logit contributions | |
arag | -1.817 |
entary | -1.722 |
hran | -1.631 |
chens | -1.581 |
ptic | -1.546 |
Token | … |
Token ID | 1399 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
own | +0.698 |
error | +0.673 |
ally | +0.672 |
STE | +0.669 |
brand | +0.655 |
Neg logit contributions | |
arag | -0.696 |
entary | -0.659 |
hran | -0.625 |
chens | -0.601 |
ptic | -0.588 |
Token | I |
Token ID | 314 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
arag | +1.690 |
entary | +1.611 |
hran | +1.542 |
chens | +1.488 |
ptic | +1.454 |
Neg logit contributions | |
own | -1.396 |
error | -1.348 |
STE | -1.346 |
ally | -1.333 |
brand | -1.306 |
Token | A |
Token ID | 317 |
Feature activation | -7.26e-02 |
Pos logit contributions | |
arag | +0.226 |
entary | +0.215 |
hran | +0.205 |
chens | +0.197 |
ptic | +0.193 |
Neg logit contributions | |
own | -0.204 |
STE | -0.197 |
error | -0.197 |
ally | -0.196 |
brand | -0.192 |
Token | 2013 |
Token ID | 2211 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
arag | +0.177 |
entary | +0.167 |
hran | +0.161 |
chens | +0.153 |
ptic | +0.150 |
Neg logit contributions | |
own | -0.177 |
error | -0.171 |
ally | -0.171 |
STE | -0.170 |
brand | -0.167 |
Token | survey |
Token ID | 5526 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
own | +3.806 |
ally | +3.740 |
error | +3.691 |
STE | +3.666 |
brand | +3.596 |
Neg logit contributions | |
arag | -3.041 |
entary | -2.847 |
hran | -2.735 |
chens | -2.588 |
ptic | -2.515 |
Token | in |
Token ID | 287 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
arag | +1.450 |
entary | +1.382 |
hran | +1.320 |
chens | +1.274 |
ptic | +1.244 |
Neg logit contributions | |
own | -1.289 |
error | -1.252 |
STE | -1.243 |
ally | -1.227 |
brand | -1.211 |
Token | Boston |
Token ID | 6182 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
arag | +0.994 |
entary | +0.939 |
hran | +0.894 |
chens | +0.861 |
ptic | +0.840 |
Neg logit contributions | |
own | -1.039 |
error | -1.012 |
STE | -1.003 |
ally | -0.996 |
brand | -0.984 |
Token | by |
Token ID | 416 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
arag | +2.290 |
entary | +2.201 |
hran | +2.105 |
chens | +2.046 |
ptic | +1.986 |
Neg logit contributions | |
own | -1.712 |
error | -1.660 |
STE | -1.650 |
ally | -1.612 |
brand | -1.594 |
Token | anti |
Token ID | 3098 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
own | +0.081 |
error | +0.078 |
STE | +0.078 |
ally | +0.078 |
brand | +0.076 |
Neg logit contributions | |
arag | -0.079 |
entary | -0.075 |
hran | -0.071 |
chens | -0.069 |
ptic | -0.067 |
Token | - |
Token ID | 12 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
arag | +3.112 |
entary | +2.880 |
hran | +2.721 |
chens | +2.582 |
ptic | +2.553 |
Neg logit contributions | |
own | -4.086 |
error | -4.030 |
STE | -4.013 |
ally | -3.971 |
Interstitial | -3.957 |
Token | street |
Token ID | 25662 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
arag | +3.479 |
entary | +3.270 |
hran | +3.079 |
chens | +2.981 |
ptic | +2.955 |
Neg logit contributions | |
own | -3.419 |
error | -3.337 |
STE | -3.322 |
ally | -3.302 |
Interstitial | -3.236 |
Token | harassment |
Token ID | 10556 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
own | +0.033 |
error | +0.032 |
STE | +0.031 |
ally | +0.031 |
brand | +0.030 |
Neg logit contributions | |
arag | -0.049 |
entary | -0.047 |
hran | -0.045 |
chens | -0.043 |
ptic | -0.042 |
Token | organization |
Token ID | 4009 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
own | +1.208 |
ally | +1.184 |
error | +1.176 |
STE | +1.171 |
brand | +1.154 |
Neg logit contributions | |
arag | -0.885 |
entary | -0.839 |
hran | -0.791 |
chens | -0.752 |
ptic | -0.728 |
Token | seemed |
Token ID | 3947 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
own | +0.650 |
ally | +0.630 |
STE | +0.622 |
error | +0.622 |
brand | +0.608 |
Neg logit contributions | |
arag | -0.681 |
entary | -0.656 |
hran | -0.617 |
chens | -0.599 |
ptic | -0.581 |
Token | relatively |
Token ID | 5365 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
own | +0.469 |
ally | +0.456 |
error | +0.451 |
STE | +0.451 |
brand | +0.441 |
Neg logit contributions | |
arag | -0.397 |
entary | -0.375 |
hran | -0.350 |
chens | -0.339 |
ptic | -0.326 |
Token | quiet |
Token ID | 5897 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
own | +3.362 |
ally | +3.298 |
error | +3.181 |
STE | +3.174 |
brand | +3.133 |
Neg logit contributions | |
arag | -2.867 |
entary | -2.651 |
hran | -2.488 |
chens | -2.407 |
ocular | -2.280 |
Token | of |
Token ID | 286 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
own | +0.403 |
ally | +0.389 |
error | +0.385 |
STE | +0.382 |
brand | +0.377 |
Neg logit contributions | |
arag | -0.386 |
entary | -0.368 |
hran | -0.350 |
chens | -0.335 |
ptic | -0.325 |
Token | late |
Token ID | 2739 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
own | +1.658 |
error | +1.608 |
STE | +1.605 |
ally | +1.604 |
brand | +1.575 |
Neg logit contributions | |
arag | -0.934 |
entary | -0.884 |
hran | -0.817 |
chens | -0.776 |
ptic | -0.743 |
Token | despite |
Token ID | 3805 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
own | +2.810 |
ally | +2.749 |
error | +2.678 |
brand | +2.638 |
STE | +2.636 |
Neg logit contributions | |
arag | -2.862 |
entary | -2.755 |
hran | -2.609 |
chens | -2.496 |
ptic | -2.426 |
Token | the |
Token ID | 262 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
own | +0.703 |
error | +0.679 |
STE | +0.677 |
ally | +0.677 |
brand | +0.662 |
Neg logit contributions | |
arag | -0.686 |
entary | -0.652 |
hran | -0.621 |
chens | -0.598 |
ptic | -0.581 |
Token | fact |
Token ID | 1109 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
arag | +0.996 |
entary | +0.944 |
hran | +0.897 |
chens | +0.859 |
ptic | +0.838 |
Neg logit contributions | |
own | -1.068 |
error | -1.036 |
STE | -1.031 |
ally | -1.023 |
brand | -1.006 |
Token | that |
Token ID | 326 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
arag | +2.416 |
entary | +2.298 |
hran | +2.170 |
chens | +2.085 |
ptic | +2.026 |
Neg logit contributions | |
own | -2.680 |
error | -2.643 |
STE | -2.624 |
Interstitial | -2.560 |
ally | -2.550 |
Token | TCU |
Token ID | 44914 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
arag | +0.640 |
entary | +0.606 |
hran | +0.578 |
chens | +0.554 |
ptic | +0.541 |
Neg logit contributions | |
own | -0.647 |
error | -0.627 |
STE | -0.623 |
ally | -0.620 |
brand | -0.608 |
Token | can |
Token ID | 460 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
own | +3.875 |
ally | +3.759 |
STE | +3.695 |
error | +3.650 |
brand | +3.633 |
Neg logit contributions | |
arag | -3.841 |
entary | -3.697 |
hran | -3.530 |
chens | -3.349 |
ptic | -3.288 |
Token | company |
Token ID | 1664 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
arag | +0.120 |
entary | +0.114 |
hran | +0.107 |
chens | +0.102 |
ptic | +0.100 |
Neg logit contributions | |
own | -0.144 |
error | -0.139 |
STE | -0.139 |
ally | -0.138 |
brand | -0.136 |
Token | public |
Token ID | 1171 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
own | +2.033 |
ally | +1.963 |
error | +1.940 |
STE | +1.927 |
brand | +1.918 |
Neg logit contributions | |
arag | -1.767 |
entary | -1.679 |
hran | -1.575 |
chens | -1.501 |
ptic | -1.468 |
Token | in |
Token ID | 287 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
own | +2.296 |
ally | +2.241 |
error | +2.177 |
STE | +2.169 |
brand | +2.156 |
Neg logit contributions | |
arag | -2.075 |
entary | -1.968 |
hran | -1.864 |
chens | -1.802 |
ptic | -1.755 |
Token | April |
Token ID | 3035 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
own | +0.234 |
error | +0.226 |
STE | +0.225 |
ally | +0.224 |
brand | +0.219 |
Neg logit contributions | |
arag | -0.242 |
entary | -0.231 |
hran | -0.219 |
chens | -0.211 |
ptic | -0.205 |
Token | 2013 |
Token ID | 2211 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
own | +0.820 |
ally | +0.792 |
STE | +0.792 |
error | +0.789 |
brand | +0.772 |
Neg logit contributions | |
arag | -0.835 |
entary | -0.799 |
hran | -0.756 |
chens | -0.719 |
ptic | -0.706 |
Token | . |
Token ID | 13 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
own | +2.157 |
ally | +2.090 |
error | +2.078 |
STE | +2.066 |
brand | +2.038 |
Neg logit contributions | |
arag | -1.958 |
entary | -1.875 |
hran | -1.763 |
chens | -1.673 |
ptic | -1.651 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
arag | +0.517 |
entary | +0.491 |
hran | +0.469 |
chens | +0.451 |
ptic | +0.440 |
Neg logit contributions | |
own | -0.496 |
error | -0.480 |
STE | -0.477 |
ally | -0.475 |
brand | -0.465 |
Token |
|
Token ID | 198 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
arag | +0.258 |
entary | +0.245 |
hran | +0.233 |
chens | +0.225 |
ptic | +0.220 |
Neg logit contributions | |
own | -0.257 |
error | -0.248 |
STE | -0.247 |
ally | -0.246 |
brand | -0.241 |
Token | In |
Token ID | 818 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
arag | +0.089 |
entary | +0.085 |
hran | +0.081 |
chens | +0.079 |
ptic | +0.077 |
Neg logit contributions | |
own | -0.058 |
error | -0.056 |
STE | -0.055 |
ally | -0.055 |
brand | -0.054 |
Token | the |
Token ID | 262 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
own | +0.597 |
error | +0.577 |
STE | +0.577 |
ally | +0.574 |
brand | +0.561 |
Neg logit contributions | |
arag | -0.612 |
entary | -0.586 |
hran | -0.559 |
chens | -0.533 |
ptic | -0.521 |
Token | months |
Token ID | 1933 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
own | +1.109 |
error | +1.070 |
STE | +1.068 |
ally | +1.063 |
brand | +1.042 |
Neg logit contributions | |
arag | -0.911 |
entary | -0.862 |
hran | -0.817 |
chens | -0.778 |
ptic | -0.751 |
Token | Pan |
Token ID | 5961 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
arag | +2.481 |
entary | +2.356 |
hran | +2.241 |
chens | +2.149 |
ptic | +2.107 |
Neg logit contributions | |
own | -2.492 |
error | -2.418 |
STE | -2.400 |
ally | -2.386 |
brand | -2.336 |
Token | or |
Token ID | 273 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
arag | +3.532 |
entary | +3.342 |
hran | +3.200 |
chens | +3.091 |
ptic | +3.038 |
Neg logit contributions | |
own | -2.799 |
STE | -2.725 |
error | -2.721 |
ally | -2.690 |
brand | -2.620 |
Token | am |
Token ID | 321 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
own | +0.555 |
error | +0.533 |
ally | +0.528 |
STE | +0.527 |
brand | +0.519 |
Neg logit contributions | |
arag | -0.690 |
entary | -0.661 |
hran | -0.634 |
chens | -0.610 |
ptic | -0.594 |
Token | io |
Token ID | 952 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
arag | +3.241 |
entary | +3.064 |
hran | +2.910 |
chens | +2.807 |
ptic | +2.769 |
Neg logit contributions | |
own | -3.095 |
error | -3.006 |
STE | -2.989 |
ally | -2.948 |
brand | -2.902 |
Token | . |
Token ID | 13 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
own | +1.508 |
error | +1.458 |
STE | +1.455 |
ally | +1.451 |
brand | +1.418 |
Neg logit contributions | |
arag | -1.573 |
entary | -1.501 |
hran | -1.426 |
chens | -1.369 |
ptic | -1.325 |
Token | ( |
Token ID | 357 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
arag | +1.528 |
entary | +1.448 |
hran | +1.388 |
chens | +1.340 |
ptic | +1.323 |
Neg logit contributions | |
own | -1.319 |
error | -1.273 |
STE | -1.270 |
ally | -1.261 |
brand | -1.225 |
Token | Free |
Token ID | 11146 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
arag | +0.629 |
entary | +0.604 |
hran | +0.583 |
chens | +0.566 |
ptic | +0.557 |
Neg logit contributions | |
own | -0.318 |
error | -0.303 |
STE | -0.301 |
ally | -0.300 |
brand | -0.290 |
Token | ) |
Token ID | 8 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
arag | +2.244 |
entary | +2.128 |
hran | +2.003 |
chens | +1.910 |
ptic | +1.872 |
Neg logit contributions | |
own | -2.789 |
STE | -2.727 |
error | -2.727 |
ally | -2.686 |
brand | -2.638 |
Token | [ |
Token ID | 685 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
own | +0.645 |
error | +0.621 |
STE | +0.618 |
ally | +0.614 |
brand | +0.600 |
Neg logit contributions | |
arag | -0.846 |
entary | -0.808 |
hran | -0.774 |
chens | -0.748 |
ptic | -0.732 |
Token | Home |
Token ID | 16060 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
arag | +1.723 |
entary | +1.658 |
hran | +1.608 |
chens | +1.569 |
ptic | +1.546 |
Neg logit contributions | |
own | -0.558 |
error | -0.525 |
ally | -0.522 |
STE | -0.518 |
brand | -0.490 |
Token | page |
Token ID | 7700 |
Feature activation | -9.12e-01 |
Pos logit contributions | |
arag | +1.451 |
entary | +1.402 |
hran | +1.358 |
chens | +1.326 |
ptic | +1.308 |
Neg logit contributions | |
own | -0.427 |
STE | -0.397 |
error | -0.397 |
ally | -0.388 |
brand | -0.367 |
Token | close |
Token ID | 1969 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
own | +0.305 |
ally | +0.298 |
STE | +0.294 |
error | +0.294 |
brand | +0.288 |
Neg logit contributions | |
arag | -0.231 |
entary | -0.215 |
hran | -0.203 |
chens | -0.194 |
ptic | -0.186 |
Token | attention |
Token ID | 3241 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
arag | +1.095 |
entary | +1.038 |
hran | +0.988 |
chens | +0.947 |
ptic | +0.923 |
Neg logit contributions | |
own | -1.116 |
ally | -1.081 |
error | -1.072 |
STE | -1.069 |
brand | -1.045 |
Token | to |
Token ID | 284 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
own | +0.802 |
ally | +0.775 |
error | +0.774 |
STE | +0.770 |
brand | +0.755 |
Neg logit contributions | |
arag | -0.670 |
entary | -0.633 |
hran | -0.600 |
chens | -0.574 |
ptic | -0.556 |
Token | my |
Token ID | 616 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
arag | +1.734 |
entary | +1.647 |
hran | +1.569 |
chens | +1.508 |
ptic | +1.469 |
Neg logit contributions | |
own | -1.727 |
error | -1.670 |
STE | -1.663 |
ally | -1.658 |
brand | -1.624 |
Token | body |
Token ID | 1767 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
own | +0.604 |
ally | +0.582 |
error | +0.580 |
STE | +0.579 |
brand | +0.567 |
Neg logit contributions | |
arag | -0.496 |
entary | -0.468 |
hran | -0.443 |
chens | -0.426 |
ptic | -0.407 |
Token | language |
Token ID | 3303 |
Feature activation | -8.10e-02 |
Pos logit contributions | |
arag | +0.782 |
entary | +0.739 |
hran | +0.700 |
chens | +0.670 |
ptic | +0.650 |
Neg logit contributions | |
own | -0.929 |
error | -0.900 |
ally | -0.896 |
STE | -0.895 |
brand | -0.878 |
Token | when |
Token ID | 618 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
arag | +0.184 |
entary | +0.174 |
hran | +0.165 |
chens | +0.158 |
ptic | +0.154 |
Neg logit contributions | |
own | -0.211 |
error | -0.205 |
STE | -0.204 |
ally | -0.204 |
brand | -0.199 |
Token | they |
Token ID | 484 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
own | +1.223 |
ally | +1.176 |
error | +1.162 |
STE | +1.161 |
brand | +1.130 |
Neg logit contributions | |
arag | -1.704 |
entary | -1.645 |
hran | -1.570 |
chens | -1.526 |
ptic | -1.463 |
Token | touch |
Token ID | 3638 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
arag | +0.250 |
entary | +0.238 |
hran | +0.224 |
chens | +0.214 |
ptic | +0.204 |
Neg logit contributions | |
own | -0.311 |
ally | -0.301 |
error | -0.300 |
STE | -0.299 |
brand | -0.293 |
Token | me |
Token ID | 502 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
own | +1.959 |
ally | +1.889 |
STE | +1.862 |
error | +1.859 |
brand | +1.818 |
Neg logit contributions | |
arag | -1.973 |
entary | -1.884 |
hran | -1.797 |
chens | -1.730 |
ptic | -1.657 |
Token | . |
Token ID | 13 |
Feature activation | -6.65e-02 |
Pos logit contributions | |
arag | +0.690 |
entary | +0.652 |
hran | +0.618 |
chens | +0.591 |
ptic | +0.575 |
Neg logit contributions | |
own | -0.815 |
error | -0.790 |
STE | -0.786 |
ally | -0.785 |
brand | -0.770 |
Token | ruining |
Token ID | 39842 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
arag | +0.300 |
entary | +0.285 |
hran | +0.270 |
chens | +0.259 |
ptic | +0.252 |
Neg logit contributions | |
own | -0.330 |
error | -0.318 |
ally | -0.317 |
STE | -0.317 |
brand | -0.311 |
Token | the |
Token ID | 262 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
arag | +0.615 |
entary | +0.583 |
hran | +0.554 |
chens | +0.532 |
ptic | +0.519 |
Neg logit contributions | |
own | -0.641 |
error | -0.621 |
STE | -0.618 |
ally | -0.615 |
brand | -0.603 |
Token | town |
Token ID | 3240 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
arag | +0.411 |
entary | +0.389 |
hran | +0.369 |
chens | +0.354 |
ptic | +0.344 |
Neg logit contributions | |
own | -0.461 |
error | -0.447 |
STE | -0.445 |
ally | -0.443 |
brand | -0.435 |
Token |
|
Token ID | 198 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
own | +2.961 |
ally | +2.872 |
error | +2.840 |
STE | +2.814 |
brand | +2.782 |
Neg logit contributions | |
arag | -2.691 |
entary | -2.546 |
hran | -2.406 |
chens | -2.296 |
ptic | -2.242 |
Token |
|
Token ID | 198 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
arag | +0.753 |
entary | +0.710 |
hran | +0.676 |
chens | +0.654 |
ptic | +0.639 |
Neg logit contributions | |
own | -0.768 |
error | -0.744 |
ally | -0.739 |
STE | -0.739 |
brand | -0.722 |
Token | Buy |
Token ID | 14518 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
arag | +0.684 |
entary | +0.654 |
hran | +0.628 |
chens | +0.609 |
ptic | +0.599 |
Neg logit contributions | |
own | -0.437 |
error | -0.420 |
STE | -0.417 |
ally | -0.415 |
brand | -0.404 |
Token | Photo |
Token ID | 5555 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
arag | +2.657 |
entary | +2.481 |
hran | +2.313 |
chens | +2.224 |
ptic | +2.146 |
Neg logit contributions | |
own | -4.039 |
error | -3.943 |
STE | -3.924 |
ally | -3.905 |
brand | -3.816 |
Token | Pokemon |
Token ID | 14878 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
arag | +1.107 |
entary | +1.050 |
hran | +1.000 |
chens | +0.963 |
ptic | +0.939 |
Neg logit contributions | |
own | -1.126 |
error | -1.090 |
STE | -1.082 |
ally | -1.081 |
brand | -1.057 |
Token | Go |
Token ID | 1514 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
arag | +1.371 |
entary | +1.308 |
hran | +1.249 |
chens | +1.205 |
ptic | +1.178 |
Neg logit contributions | |
own | -1.178 |
error | -1.138 |
STE | -1.133 |
ally | -1.125 |
brand | -1.102 |
Token | players |
Token ID | 1938 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
arag | +3.388 |
entary | +3.224 |
hran | +3.049 |
chens | +2.943 |
ptic | +2.880 |
Neg logit contributions | |
own | -3.781 |
error | -3.692 |
STE | -3.680 |
ally | -3.641 |
brand | -3.592 |
Token | make |
Token ID | 787 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
own | +0.452 |
ally | +0.439 |
error | +0.438 |
STE | +0.437 |
brand | +0.427 |
Neg logit contributions | |
arag | -0.381 |
entary | -0.359 |
hran | -0.340 |
chens | -0.325 |
ptic | -0.313 |
Token | A |
Token ID | 317 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
own | +0.508 |
ally | +0.492 |
error | +0.491 |
STE | +0.489 |
brand | +0.477 |
Neg logit contributions | |
arag | -0.535 |
entary | -0.500 |
hran | -0.482 |
chens | -0.460 |
ptic | -0.445 |
Token | veterinarian |
Token ID | 41404 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
own | +0.145 |
error | +0.141 |
STE | +0.140 |
ally | +0.140 |
brand | +0.137 |
Neg logit contributions | |
arag | -0.111 |
entary | -0.103 |
hran | -0.098 |
chens | -0.093 |
ptic | -0.089 |
Token | skilled |
Token ID | 14297 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
own | +0.735 |
ally | +0.715 |
error | +0.707 |
STE | +0.702 |
brand | +0.690 |
Neg logit contributions | |
arag | -0.697 |
entary | -0.653 |
hran | -0.629 |
chens | -0.601 |
ptic | -0.578 |
Token | in |
Token ID | 287 |
Feature activation | -5.57e-04 |
Pos logit contributions | |
arag | +0.853 |
entary | +0.817 |
hran | +0.774 |
chens | +0.736 |
ptic | +0.730 |
Neg logit contributions | |
own | -0.979 |
STE | -0.960 |
error | -0.954 |
brand | -0.935 |
ally | -0.934 |
Token | the |
Token ID | 262 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
arag | +0.001 |
entary | +0.001 |
hran | +0.001 |
chens | +0.001 |
ptic | +0.001 |
Neg logit contributions | |
own | -0.001 |
error | -0.001 |
ally | -0.001 |
STE | -0.001 |
brand | -0.001 |
Token | healthcare |
Token ID | 11409 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
own | +0.559 |
error | +0.542 |
ally | +0.541 |
STE | +0.540 |
brand | +0.526 |
Neg logit contributions | |
arag | -0.445 |
entary | -0.420 |
hran | -0.395 |
chens | -0.380 |
ptic | -0.365 |
Token | and |
Token ID | 290 |
Feature activation | -8.93e-02 |
Pos logit contributions | |
arag | +1.089 |
entary | +1.026 |
hran | +0.974 |
chens | +0.930 |
ptic | +0.909 |
Neg logit contributions | |
own | -1.354 |
error | -1.315 |
STE | -1.315 |
ally | -1.294 |
brand | -1.281 |
Token | maintenance |
Token ID | 9262 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
arag | +0.199 |
entary | +0.188 |
hran | +0.178 |
chens | +0.171 |
ptic | +0.165 |
Neg logit contributions | |
own | -0.236 |
error | -0.230 |
ally | -0.228 |
STE | -0.228 |
brand | -0.223 |
Token | of |
Token ID | 286 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
own | +0.946 |
error | +0.921 |
STE | +0.917 |
ally | +0.912 |
brand | +0.898 |
Neg logit contributions | |
arag | -0.691 |
entary | -0.650 |
hran | -0.612 |
chens | -0.583 |
ptic | -0.567 |
Token | non |
Token ID | 1729 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
own | +0.754 |
ally | +0.740 |
error | +0.734 |
STE | +0.729 |
brand | +0.712 |
Neg logit contributions | |
arag | -0.663 |
entary | -0.626 |
hran | -0.599 |
chens | -0.575 |
ptic | -0.549 |
Token | - |
Token ID | 12 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
arag | +1.218 |
entary | +1.154 |
hran | +1.094 |
chens | +1.048 |
ptic | +1.025 |
Neg logit contributions | |
own | -1.347 |
error | -1.306 |
STE | -1.302 |
ally | -1.294 |
brand | -1.270 |
Token | at |
Token ID | 379 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
arag | +3.583 |
entary | +3.406 |
hran | +3.230 |
chens | +3.114 |
ptic | +3.024 |
Neg logit contributions | |
own | -3.784 |
error | -3.706 |
STE | -3.696 |
ally | -3.656 |
brand | -3.586 |
Token | Hart |
Token ID | 11345 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
arag | +1.025 |
entary | +0.972 |
hran | +0.924 |
chens | +0.888 |
ptic | +0.865 |
Neg logit contributions | |
own | -1.067 |
error | -1.034 |
STE | -1.029 |
ally | -1.024 |
brand | -1.005 |
Token | z |
Token ID | 89 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
own | +3.695 |
error | +3.482 |
ally | +3.465 |
STE | +3.456 |
brand | +3.441 |
Neg logit contributions | |
arag | -4.373 |
entary | -4.116 |
hran | -3.974 |
chens | -3.785 |
ptic | -3.760 |
Token | ell |
Token ID | 695 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
own | +4.136 |
error | +3.925 |
ally | +3.919 |
STE | +3.879 |
brand | +3.871 |
Neg logit contributions | |
arag | -4.555 |
entary | -4.358 |
hran | -4.151 |
chens | -3.976 |
ptic | -3.906 |
Token | House |
Token ID | 2097 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
own | +0.493 |
error | +0.473 |
STE | +0.471 |
ally | +0.470 |
brand | +0.461 |
Neg logit contributions | |
arag | -0.487 |
entary | -0.461 |
hran | -0.441 |
chens | -0.421 |
ptic | -0.411 |
Token | Bed |
Token ID | 15585 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
own | +0.615 |
STE | +0.586 |
ally | +0.585 |
error | +0.584 |
brand | +0.575 |
Neg logit contributions | |
arag | -0.577 |
entary | -0.548 |
hran | -0.519 |
chens | -0.492 |
ptic | -0.485 |
Token | & |
Token ID | 1222 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
arag | +4.792 |
entary | +4.511 |
hran | +4.351 |
chens | +4.236 |
ptic | +4.081 |
Neg logit contributions | |
own | -5.059 |
STE | -5.028 |
error | -5.019 |
ally | -4.963 |
Interstitial | -4.943 |
Token | Breakfast |
Token ID | 32175 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
own | +0.809 |
error | +0.787 |
STE | +0.782 |
ally | +0.781 |
brand | +0.765 |
Neg logit contributions | |
arag | -0.708 |
entary | -0.668 |
hran | -0.633 |
chens | -0.607 |
ptic | -0.590 |
Token | in |
Token ID | 287 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
own | +0.252 |
error | +0.241 |
STE | +0.241 |
ally | +0.241 |
brand | +0.236 |
Neg logit contributions | |
arag | -0.239 |
entary | -0.227 |
hran | -0.216 |
chens | -0.206 |
ptic | -0.202 |
Token | Add |
Token ID | 3060 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
own | +0.600 |
error | +0.574 |
ally | +0.573 |
STE | +0.572 |
brand | +0.558 |
Neg logit contributions | |
arag | -0.585 |
entary | -0.556 |
hran | -0.529 |
chens | -0.506 |
ptic | -0.494 |
Token | ision |
Token ID | 1166 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
own | +1.142 |
error | +1.102 |
STE | +1.096 |
ally | +1.095 |
brand | +1.075 |
Neg logit contributions | |
arag | -1.094 |
entary | -1.038 |
hran | -0.984 |
chens | -0.945 |
ptic | -0.922 |
Token | , |
Token ID | 11 |
Feature activation | -7.97e-02 |
Pos logit contributions | |
arag | +0.357 |
entary | +0.339 |
hran | +0.322 |
chens | +0.310 |
ptic | +0.302 |
Neg logit contributions | |
own | -0.356 |
error | -0.344 |
STE | -0.343 |
ally | -0.342 |
brand | -0.335 |
Token | ne |
Token ID | 497 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
arag | +0.199 |
entary | +0.190 |
hran | +0.180 |
chens | +0.174 |
ptic | +0.169 |
Neg logit contributions | |
own | -0.190 |
error | -0.184 |
STE | -0.183 |
ally | -0.182 |
brand | -0.179 |
Token | pot |
Token ID | 13059 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
arag | +3.886 |
entary | +3.732 |
hran | +3.544 |
chens | +3.441 |
ptic | +3.389 |
Neg logit contributions | |
own | -3.161 |
error | -3.038 |
STE | -3.033 |
ally | -2.997 |
brand | -2.945 |
Token | ism |
Token ID | 1042 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
arag | +0.784 |
entary | +0.750 |
hran | +0.714 |
chens | +0.693 |
ptic | +0.683 |
Neg logit contributions | |
own | -0.551 |
STE | -0.534 |
error | -0.532 |
ally | -0.522 |
brand | -0.515 |
Token | ran |
Token ID | 4966 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
arag | +0.647 |
entary | +0.615 |
hran | +0.584 |
chens | +0.560 |
ptic | +0.546 |
Neg logit contributions | |
own | -0.672 |
error | -0.650 |
STE | -0.647 |
ally | -0.646 |
brand | -0.632 |
Token | am |
Token ID | 716 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
own | +0.247 |
ally | +0.238 |
error | +0.236 |
STE | +0.235 |
brand | +0.230 |
Neg logit contributions | |
arag | -0.184 |
entary | -0.176 |
hran | -0.166 |
chens | -0.156 |
ptic | -0.152 |
Token | ok |
Token ID | 482 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
arag | +5.532 |
entary | +5.086 |
hran | +4.977 |
ptic | +4.853 |
chens | +4.828 |
Neg logit contributions | |
STE | -3.287 |
own | -3.242 |
error | -3.197 |
Interstitial | -3.144 |
ally | -3.084 |
Token | . |
Token ID | 13 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
arag | +1.397 |
entary | +1.311 |
hran | +1.240 |
chens | +1.184 |
ptic | +1.154 |
Neg logit contributions | |
own | -1.810 |
error | -1.764 |
STE | -1.759 |
ally | -1.743 |
brand | -1.719 |
Token | CNN |
Token ID | 8100 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
arag | +0.569 |
entary | +0.542 |
hran | +0.517 |
chens | +0.497 |
ptic | +0.485 |
Neg logit contributions | |
own | -0.526 |
error | -0.508 |
STE | -0.506 |
ally | -0.503 |
brand | -0.494 |
Token | president |
Token ID | 1893 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
arag | +1.335 |
entary | +1.266 |
hran | +1.209 |
chens | +1.162 |
ptic | +1.134 |
Neg logit contributions | |
own | -1.264 |
error | -1.224 |
STE | -1.216 |
ally | -1.209 |
brand | -1.186 |
Token | Jeff |
Token ID | 5502 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
own | +0.061 |
error | +0.059 |
STE | +0.059 |
ally | +0.059 |
brand | +0.058 |
Neg logit contributions | |
arag | -0.058 |
entary | -0.055 |
hran | -0.053 |
chens | -0.051 |
ptic | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
own | +1.581 |
ally | +1.531 |
error | +1.523 |
STE | +1.512 |
brand | +1.481 |
Neg logit contributions | |
arag | -1.402 |
entary | -1.326 |
hran | -1.258 |
chens | -1.203 |
ptic | -1.165 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
arag | +0.364 |
entary | +0.345 |
hran | +0.329 |
chens | +0.316 |
ptic | +0.309 |
Neg logit contributions | |
own | -0.356 |
error | -0.345 |
STE | -0.343 |
ally | -0.342 |
brand | -0.335 |
Token | Federal |
Token ID | 24099 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
own | +2.533 |
STE | +2.454 |
error | +2.439 |
ally | +2.384 |
brand | +2.351 |
Neg logit contributions | |
arag | -4.003 |
entary | -3.869 |
hran | -3.717 |
chens | -3.595 |
ptic | -3.490 |
Token | police |
Token ID | 1644 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
own | +0.346 |
error | +0.333 |
ally | +0.333 |
STE | +0.332 |
brand | +0.324 |
Neg logit contributions | |
arag | -0.348 |
entary | -0.330 |
hran | -0.315 |
chens | -0.302 |
ptic | -0.294 |
Token | have |
Token ID | 423 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
arag | +0.332 |
entary | +0.316 |
hran | +0.298 |
chens | +0.286 |
ptic | +0.278 |
Neg logit contributions | |
own | -0.373 |
error | -0.362 |
STE | -0.361 |
ally | -0.360 |
brand | -0.353 |
Token | laid |
Token ID | 8104 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
arag | +0.734 |
entary | +0.695 |
hran | +0.661 |
chens | +0.634 |
ptic | +0.618 |
Neg logit contributions | |
own | -0.773 |
error | -0.749 |
STE | -0.745 |
ally | -0.742 |
brand | -0.728 |
Token | fresh |
Token ID | 4713 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
arag | +4.495 |
entary | +4.228 |
hran | +4.051 |
chens | +3.880 |
ptic | +3.788 |
Neg logit contributions | |
own | -4.206 |
STE | -4.118 |
error | -4.096 |
ally | -4.014 |
brand | -3.988 |
Token | charges |
Token ID | 4530 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
arag | +0.404 |
entary | +0.389 |
hran | +0.372 |
chens | +0.362 |
ptic | +0.352 |
Neg logit contributions | |
own | -0.291 |
ally | -0.280 |
error | -0.279 |
STE | -0.276 |
brand | -0.269 |
Token | against |
Token ID | 1028 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
arag | +0.968 |
entary | +0.919 |
hran | +0.873 |
chens | +0.837 |
ptic | +0.816 |
Neg logit contributions | |
own | -1.028 |
error | -0.996 |
STE | -0.992 |
ally | -0.988 |
brand | -0.969 |
Token | former |
Token ID | 1966 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
arag | +0.498 |
entary | +0.469 |
hran | +0.443 |
chens | +0.423 |
ptic | +0.411 |
Neg logit contributions | |
own | -0.635 |
error | -0.617 |
STE | -0.615 |
ally | -0.612 |
brand | -0.601 |
Token | Reserve |
Token ID | 12224 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
arag | +0.436 |
entary | +0.413 |
hran | +0.393 |
chens | +0.377 |
ptic | +0.367 |
Neg logit contributions | |
own | -0.455 |
error | -0.441 |
STE | -0.439 |
ally | -0.437 |
brand | -0.428 |
Token | 's |
Token ID | 338 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
arag | +1.130 |
entary | +1.066 |
hran | +1.016 |
chens | +0.972 |
ptic | +0.945 |
Neg logit contributions | |
own | -1.250 |
error | -1.210 |
STE | -1.206 |
ally | -1.205 |
brand | -1.176 |
Token | physical |
Token ID | 3518 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
own | +1.845 |
STE | +1.797 |
ally | +1.793 |
error | +1.780 |
brand | +1.736 |
Neg logit contributions | |
arag | -1.438 |
entary | -1.349 |
hran | -1.290 |
chens | -1.247 |
ptic | -1.188 |
Token | fitness |
Token ID | 13547 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
own | +1.525 |
ally | +1.489 |
error | +1.484 |
STE | +1.469 |
brand | +1.435 |
Neg logit contributions | |
arag | -1.339 |
entary | -1.266 |
hran | -1.214 |
chens | -1.172 |
ptic | -1.128 |
Token | test |
Token ID | 1332 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
arag | +0.294 |
entary | +0.275 |
hran | +0.259 |
chens | +0.248 |
ptic | +0.240 |
Neg logit contributions | |
own | -0.405 |
ally | -0.394 |
error | -0.393 |
STE | -0.392 |
brand | -0.384 |
Token | , |
Token ID | 11 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
arag | +2.422 |
entary | +2.292 |
hran | +2.170 |
chens | +2.086 |
ptic | +2.033 |
Neg logit contributions | |
own | -2.849 |
error | -2.771 |
STE | -2.760 |
ally | -2.722 |
brand | -2.699 |
Token | mand |
Token ID | 6855 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
arag | +1.455 |
entary | +1.378 |
hran | +1.308 |
chens | +1.253 |
ptic | +1.222 |
Neg logit contributions | |
own | -1.599 |
error | -1.550 |
STE | -1.544 |
ally | -1.535 |
brand | -1.507 |
Token | ating |
Token ID | 803 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
arag | +5.061 |
entary | +4.839 |
hran | +4.605 |
chens | +4.335 |
ptic | +4.320 |
Neg logit contributions | |
STE | -4.621 |
own | -4.562 |
error | -4.556 |
Interstitial | -4.475 |
OWN | -4.422 |
Token | that |
Token ID | 326 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
arag | +1.297 |
entary | +1.224 |
hran | +1.167 |
chens | +1.120 |
ptic | +1.089 |
Neg logit contributions | |
own | -1.391 |
error | -1.345 |
STE | -1.340 |
ally | -1.340 |
brand | -1.309 |
Token | the |
Token ID | 262 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
own | +0.094 |
error | +0.091 |
ally | +0.091 |
STE | +0.090 |
brand | +0.088 |
Neg logit contributions | |
arag | -0.108 |
entary | -0.102 |
hran | -0.098 |
chens | -0.095 |
ptic | -0.092 |
Token | rest |
Token ID | 1334 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
own | +0.120 |
STE | +0.116 |
ally | +0.116 |
error | +0.116 |
brand | +0.113 |
Neg logit contributions | |
arag | -0.100 |
entary | -0.094 |
hran | -0.090 |
chens | -0.086 |
ptic | -0.082 |
Token | of |
Token ID | 286 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
arag | +2.226 |
entary | +2.126 |
hran | +1.970 |
chens | +1.876 |
ptic | +1.832 |
Neg logit contributions | |
own | -3.307 |
error | -3.255 |
STE | -3.234 |
ally | -3.187 |
brand | -3.163 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
arag | +2.481 |
entary | +2.339 |
hran | +2.207 |
chens | +2.113 |
ptic | +2.047 |
Neg logit contributions | |
own | -3.166 |
error | -3.096 |
STE | -3.078 |
ally | -3.046 |
brand | -3.009 |
Token |
|
Token ID | 198 |
Feature activation | -6.00e-02 |
Pos logit contributions | |
arag | +0.345 |
entary | +0.328 |
hran | +0.314 |
chens | +0.301 |
ptic | +0.294 |
Neg logit contributions | |
own | -0.311 |
error | -0.300 |
STE | -0.299 |
ally | -0.298 |
brand | -0.291 |
Token |
|
Token ID | 198 |
Feature activation | -9.79e-02 |
Pos logit contributions | |
arag | +0.147 |
entary | +0.140 |
hran | +0.133 |
chens | +0.128 |
ptic | +0.125 |
Neg logit contributions | |
own | -0.145 |
error | -0.140 |
STE | -0.140 |
ally | -0.139 |
brand | -0.136 |
Token | � |
Token ID | 447 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
arag | +0.225 |
entary | +0.213 |
hran | +0.201 |
chens | +0.194 |
ptic | +0.189 |
Neg logit contributions | |
own | -0.252 |
error | -0.245 |
STE | -0.243 |
ally | -0.242 |
brand | -0.238 |
Token | � |
Token ID | 246 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
arag | +1.405 |
entary | +1.343 |
hran | +1.286 |
chens | +1.244 |
ptic | +1.219 |
Neg logit contributions | |
own | -1.061 |
error | -1.023 |
STE | -1.016 |
ally | -1.011 |
brand | -0.987 |
Token | These |
Token ID | 4711 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
own | +0.022 |
error | +0.021 |
STE | +0.021 |
ally | +0.020 |
brand | +0.020 |
Neg logit contributions | |
arag | -0.039 |
entary | -0.037 |
hran | -0.036 |
chens | -0.035 |
ptic | -0.034 |
Token | facts |
Token ID | 6419 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
arag | +4.262 |
entary | +4.037 |
hran | +3.869 |
chens | +3.664 |
ptic | +3.597 |
Neg logit contributions | |
own | -5.565 |
error | -5.420 |
STE | -5.386 |
brand | -5.328 |
ally | -5.278 |
Token | alone |
Token ID | 3436 |
Feature activation | +5.56e-02 |
Pos logit contributions | |
arag | +1.557 |
entary | +1.465 |
hran | +1.382 |
chens | +1.316 |
ptic | +1.278 |
Neg logit contributions | |
own | -2.064 |
error | -2.005 |
STE | -1.996 |
ally | -1.994 |
brand | -1.955 |
Token | make |
Token ID | 787 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
own | +0.150 |
ally | +0.146 |
error | +0.144 |
STE | +0.142 |
brand | +0.141 |
Neg logit contributions | |
arag | -0.123 |
entary | -0.116 |
hran | -0.109 |
chens | -0.103 |
ptic | -0.100 |
Token | the |
Token ID | 262 |
Feature activation | -9.33e-02 |
Pos logit contributions | |
arag | +0.058 |
entary | +0.055 |
hran | +0.053 |
chens | +0.050 |
ptic | +0.049 |
Neg logit contributions | |
own | -0.062 |
ally | -0.060 |
error | -0.060 |
STE | -0.060 |
brand | -0.058 |
Token | ocean |
Token ID | 9151 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
arag | +0.188 |
entary | +0.176 |
hran | +0.166 |
chens | +0.157 |
ptic | +0.152 |
Neg logit contributions | |
own | -0.269 |
error | -0.261 |
ally | -0.260 |
STE | -0.260 |
brand | -0.254 |