Token | by |
Token ID | 416 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
gdala | +0.685 |
ICAN | +0.554 |
amination | +0.535 |
INE | +0.525 |
Magikarp | +0.522 |
Neg logit contributions | |
leys | -0.662 |
luaj | -0.648 |
bri | -0.628 |
nen | -0.621 |
ahime | -0.612 |
Token | 23 |
Token ID | 2242 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
leys | +1.388 |
luaj | +1.360 |
bri | +1.321 |
nen | +1.304 |
jin | +1.286 |
Neg logit contributions | |
gdala | -1.589 |
ICAN | -1.298 |
amination | -1.253 |
Magikarp | -1.230 |
INE | -1.229 |
Token | Muslim |
Token ID | 3765 |
Feature activation | -6.11e-02 |
Pos logit contributions | |
leys | +1.086 |
luaj | +1.066 |
bri | +1.039 |
nen | +1.024 |
jin | +1.012 |
Neg logit contributions | |
gdala | -1.083 |
ICAN | -0.871 |
amination | -0.837 |
INE | -0.822 |
Magikarp | -0.822 |
Token | organisations |
Token ID | 16435 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
gdala | +0.051 |
ICAN | +0.042 |
amination | +0.040 |
INE | +0.039 |
Magikarp | +0.039 |
Neg logit contributions | |
leys | -0.047 |
luaj | -0.046 |
bri | -0.045 |
nen | -0.044 |
jin | -0.044 |
Token | in |
Token ID | 287 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
leys | +0.512 |
luaj | +0.500 |
bri | +0.487 |
nen | +0.481 |
jin | +0.474 |
Neg logit contributions | |
gdala | -0.552 |
ICAN | -0.447 |
amination | -0.430 |
INE | -0.424 |
Magikarp | -0.423 |
Token | Tamil |
Token ID | 32519 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
gdala | +0.535 |
ICAN | +0.435 |
amination | +0.421 |
INE | +0.413 |
Magikarp | +0.412 |
Neg logit contributions | |
leys | -0.500 |
luaj | -0.491 |
bri | -0.473 |
nen | -0.472 |
igans | -0.465 |
Token | Nadu |
Token ID | 46917 |
Feature activation | +7.26e+00 |
Pos logit contributions | |
leys | +1.821 |
luaj | +1.695 |
jin | +1.521 |
bri | +1.356 |
nen | +1.209 |
Neg logit contributions | |
gdala | -17.000 |
ICAN | -15.028 |
Magikarp | -14.700 |
renheit | -14.693 |
INE | -14.664 |
Token | before |
Token ID | 878 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
leys | +4.961 |
luaj | +4.893 |
bri | +4.749 |
jin | +4.648 |
nen | +4.632 |
Neg logit contributions | |
gdala | -6.522 |
ICAN | -5.326 |
Magikarp | -5.183 |
amination | -5.159 |
renheit | -5.071 |
Token | its |
Token ID | 663 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
gdala | +2.684 |
ICAN | +2.216 |
amination | +2.151 |
coinc | +2.105 |
INE | +2.089 |
Neg logit contributions | |
leys | -2.644 |
luaj | -2.625 |
ahime | -2.520 |
nen | -2.486 |
bri | -2.475 |
Token | release |
Token ID | 2650 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
gdala | +1.290 |
ICAN | +1.074 |
amination | +1.043 |
coinc | +1.018 |
INE | +1.013 |
Neg logit contributions | |
leys | -1.058 |
luaj | -1.028 |
igans | -0.981 |
bri | -0.980 |
ahime | -0.979 |
Token | and |
Token ID | 290 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
gdala | +1.602 |
ICAN | +1.288 |
amination | +1.251 |
INE | +1.224 |
coinc | +1.217 |
Neg logit contributions | |
leys | -1.624 |
luaj | -1.599 |
bri | -1.542 |
nen | -1.525 |
ahime | -1.514 |
Token | of |
Token ID | 286 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
leys | +0.807 |
luaj | +0.791 |
bri | +0.772 |
nen | +0.760 |
jin | +0.750 |
Neg logit contributions | |
gdala | -0.851 |
ICAN | -0.686 |
amination | -0.662 |
Magikarp | -0.651 |
INE | -0.650 |
Token | the |
Token ID | 262 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
leys | +0.105 |
luaj | +0.103 |
bri | +0.100 |
nen | +0.099 |
ahime | +0.097 |
Neg logit contributions | |
gdala | -0.117 |
ICAN | -0.095 |
amination | -0.092 |
INE | -0.091 |
Magikarp | -0.090 |
Token | state |
Token ID | 1181 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
gdala | +0.446 |
ICAN | +0.369 |
amination | +0.358 |
INE | +0.351 |
Magikarp | +0.348 |
Neg logit contributions | |
leys | -0.369 |
luaj | -0.362 |
bri | -0.345 |
nen | -0.345 |
ahime | -0.343 |
Token | oil |
Token ID | 3056 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
leys | +0.637 |
luaj | +0.623 |
bri | +0.602 |
nen | +0.593 |
jin | +0.584 |
Neg logit contributions | |
gdala | -0.838 |
ICAN | -0.695 |
amination | -0.673 |
INE | -0.663 |
Magikarp | -0.660 |
Token | firm |
Token ID | 4081 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
leys | +2.006 |
luaj | +1.952 |
bri | +1.911 |
nen | +1.866 |
jin | +1.844 |
Neg logit contributions | |
gdala | -3.043 |
ICAN | -2.535 |
amination | -2.460 |
Magikarp | -2.434 |
INE | -2.423 |
Token | Uk |
Token ID | 5065 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
leys | +0.877 |
luaj | +0.859 |
bri | +0.833 |
nen | +0.821 |
jin | +0.811 |
Neg logit contributions | |
gdala | -0.964 |
ICAN | -0.782 |
amination | -0.755 |
INE | -0.744 |
Magikarp | -0.741 |
Token | r |
Token ID | 81 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
leys | +8.043 |
luaj | +7.765 |
jin | +7.737 |
nen | +7.725 |
bri | +7.488 |
Neg logit contributions | |
gdala | -10.141 |
ICAN | -8.361 |
Magikarp | -8.196 |
amination | -7.740 |
INE | -7.725 |
Token | na |
Token ID | 2616 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
leys | +0.933 |
luaj | +0.913 |
bri | +0.890 |
nen | +0.876 |
jin | +0.864 |
Neg logit contributions | |
gdala | -1.125 |
ICAN | -0.920 |
amination | -0.890 |
Magikarp | -0.877 |
INE | -0.874 |
Token | ft |
Token ID | 701 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
leys | +1.617 |
luaj | +1.582 |
bri | +1.543 |
nen | +1.519 |
jin | +1.500 |
Neg logit contributions | |
gdala | -1.888 |
ICAN | -1.539 |
amination | -1.487 |
Magikarp | -1.464 |
INE | -1.459 |
Token | a |
Token ID | 64 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
leys | +0.398 |
luaj | +0.390 |
bri | +0.377 |
nen | +0.370 |
jin | +0.364 |
Neg logit contributions | |
gdala | -0.473 |
ICAN | -0.389 |
amination | -0.378 |
INE | -0.371 |
Magikarp | -0.369 |
Token | in |
Token ID | 287 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
leys | +1.020 |
luaj | +0.999 |
bri | +0.968 |
nen | +0.953 |
jin | +0.937 |
Neg logit contributions | |
gdala | -1.211 |
ICAN | -0.992 |
amination | -0.959 |
INE | -0.945 |
Magikarp | -0.942 |
Token | Jo |
Token ID | 9908 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
leys | +0.098 |
luaj | +0.096 |
bri | +0.093 |
nen | +0.092 |
ahime | +0.090 |
Neg logit contributions | |
gdala | -0.110 |
ICAN | -0.090 |
amination | -0.087 |
INE | -0.086 |
Magikarp | -0.085 |
Token | ha |
Token ID | 387 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
gdala | +1.616 |
ICAN | +1.326 |
amination | +1.299 |
INE | +1.290 |
Magikarp | +1.244 |
Neg logit contributions | |
luaj | -1.460 |
leys | -1.458 |
bri | -1.382 |
nen | -1.374 |
ahime | -1.357 |
Token | i |
Token ID | 72 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
leys | +1.045 |
luaj | +1.032 |
bri | +1.002 |
nen | +0.987 |
ahime | +0.976 |
Neg logit contributions | |
gdala | -0.965 |
ICAN | -0.769 |
amination | -0.738 |
INE | -0.728 |
Magikarp | -0.721 |
Token | w |
Token ID | 266 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
leys | +2.211 |
luaj | +2.159 |
bri | +2.108 |
nen | +2.068 |
jin | +2.041 |
Neg logit contributions | |
gdala | -2.955 |
ICAN | -2.439 |
amination | -2.363 |
Magikarp | -2.333 |
INE | -2.322 |
Token | ahi |
Token ID | 32810 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
leys | +1.791 |
luaj | +1.745 |
bri | +1.694 |
nen | +1.664 |
jin | +1.637 |
Neg logit contributions | |
gdala | -2.773 |
ICAN | -2.320 |
amination | -2.251 |
Magikarp | -2.224 |
INE | -2.216 |
Token | kh |
Token ID | 44081 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
leys | +3.231 |
luaj | +3.143 |
bri | +3.092 |
nen | +3.031 |
jin | +2.989 |
Neg logit contributions | |
gdala | -4.515 |
ICAN | -3.736 |
amination | -3.619 |
Magikarp | -3.585 |
INE | -3.554 |
Token | il |
Token ID | 346 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
leys | +8.877 |
bri | +8.611 |
nen | +8.573 |
luaj | +8.480 |
jin | +8.373 |
Neg logit contributions | |
gdala | -8.825 |
ICAN | -6.966 |
Magikarp | -6.904 |
renheit | -6.707 |
amination | -6.663 |
Token | ai |
Token ID | 1872 |
Feature activation | +6.77e+00 |
Pos logit contributions | |
leys | +3.091 |
luaj | +3.005 |
bri | +2.953 |
nen | +2.902 |
jin | +2.853 |
Neg logit contributions | |
gdala | -4.267 |
ICAN | -3.531 |
amination | -3.420 |
Magikarp | -3.390 |
INE | -3.363 |
Token | ye |
Token ID | 5948 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
leys | +4.484 |
luaj | +4.363 |
bri | +4.358 |
nen | +4.248 |
jin | +4.207 |
Neg logit contributions | |
gdala | -6.287 |
ICAN | -5.189 |
amination | -5.026 |
Magikarp | -4.993 |
INE | -4.924 |
Token | ... |
Token ID | 986 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
leys | +3.511 |
luaj | +3.410 |
bri | +3.379 |
nen | +3.302 |
jin | +3.265 |
Neg logit contributions | |
gdala | -4.891 |
ICAN | -4.051 |
amination | -3.928 |
Magikarp | -3.892 |
INE | -3.852 |
Token | k |
Token ID | 74 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
leys | +0.504 |
luaj | +0.495 |
bri | +0.479 |
nen | +0.471 |
jin | +0.464 |
Neg logit contributions | |
gdala | -0.611 |
ICAN | -0.502 |
amination | -0.485 |
INE | -0.477 |
Magikarp | -0.476 |
Token | dolphins |
Token ID | 36798 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
leys | +1.140 |
luaj | +1.116 |
bri | +1.086 |
nen | +1.069 |
jin | +1.054 |
Neg logit contributions | |
gdala | -1.368 |
ICAN | -1.119 |
amination | -1.082 |
Magikarp | -1.066 |
INE | -1.063 |
Token | and |
Token ID | 290 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
gdala | +1.380 |
ICAN | +1.123 |
amination | +1.081 |
INE | +1.075 |
Magikarp | +1.063 |
Neg logit contributions | |
leys | -1.206 |
luaj | -1.191 |
bri | -1.155 |
nen | -1.135 |
jin | -1.115 |
Token | the |
Token ID | 262 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
leys | +0.551 |
luaj | +0.540 |
bri | +0.525 |
nen | +0.518 |
jin | +0.511 |
Neg logit contributions | |
gdala | -0.621 |
ICAN | -0.504 |
amination | -0.487 |
Magikarp | -0.480 |
INE | -0.478 |
Token | highly |
Token ID | 4047 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
leys | +0.275 |
luaj | +0.269 |
bri | +0.262 |
nen | +0.258 |
jin | +0.254 |
Neg logit contributions | |
gdala | -0.325 |
ICAN | -0.265 |
amination | -0.256 |
Magikarp | -0.253 |
INE | -0.252 |
Token | endangered |
Token ID | 22700 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
leys | +2.162 |
luaj | +2.122 |
bri | +2.069 |
nen | +2.033 |
jin | +2.001 |
Neg logit contributions | |
gdala | -2.919 |
ICAN | -2.422 |
amination | -2.338 |
INE | -2.305 |
Magikarp | -2.305 |
Token | Bengal |
Token ID | 28630 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
gdala | +0.593 |
ICAN | +0.483 |
amination | +0.466 |
Magikarp | +0.460 |
INE | +0.459 |
Neg logit contributions | |
leys | -0.510 |
luaj | -0.499 |
bri | -0.483 |
nen | -0.479 |
ahime | -0.472 |
Token | tiger |
Token ID | 26241 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
leys | +6.373 |
luaj | +6.315 |
bri | +6.240 |
jin | +6.118 |
nen | +6.061 |
Neg logit contributions | |
gdala | -9.396 |
ICAN | -7.769 |
amination | -7.560 |
Magikarp | -7.519 |
renheit | -7.430 |
Token | . |
Token ID | 13 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
leys | +2.916 |
luaj | +2.838 |
bri | +2.795 |
nen | +2.735 |
jin | +2.725 |
Neg logit contributions | |
gdala | -3.813 |
ICAN | -3.163 |
amination | -3.092 |
Magikarp | -3.044 |
renheit | -3.014 |
Token |
|
Token ID | 198 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
leys | +0.115 |
luaj | +0.112 |
bri | +0.109 |
nen | +0.107 |
jin | +0.105 |
Neg logit contributions | |
gdala | -0.154 |
ICAN | -0.128 |
amination | -0.123 |
INE | -0.122 |
Magikarp | -0.122 |
Token |
|
Token ID | 198 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
gdala | +0.112 |
ICAN | +0.093 |
amination | +0.091 |
Magikarp | +0.090 |
INE | +0.089 |
Neg logit contributions | |
leys | -0.077 |
luaj | -0.075 |
bri | -0.073 |
nen | -0.072 |
jin | -0.071 |
Token | " |
Token ID | 1 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
gdala | +0.146 |
ICAN | +0.121 |
INE | +0.115 |
Magikarp | +0.114 |
amination | +0.114 |
Neg logit contributions | |
leys | -0.135 |
luaj | -0.133 |
bri | -0.130 |
nen | -0.127 |
ahime | -0.126 |
Token |
|
Token ID | 198 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
leys | +0.206 |
luaj | +0.200 |
bri | +0.194 |
nen | +0.192 |
jin | +0.189 |
Neg logit contributions | |
gdala | -0.312 |
ICAN | -0.260 |
amination | -0.253 |
Magikarp | -0.250 |
INE | -0.247 |
Token | R |
Token ID | 49 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
leys | +0.104 |
luaj | +0.102 |
bri | +0.101 |
nen | +0.098 |
ahime | +0.097 |
Neg logit contributions | |
gdala | -0.113 |
ICAN | -0.093 |
amination | -0.088 |
INE | -0.088 |
Magikarp | -0.088 |
Token | S |
Token ID | 311 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
leys | +0.283 |
luaj | +0.281 |
bri | +0.272 |
nen | +0.267 |
jin | +0.262 |
Neg logit contributions | |
gdala | -0.342 |
ICAN | -0.281 |
amination | -0.272 |
INE | -0.268 |
Magikarp | -0.264 |
Token | enth |
Token ID | 7944 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
leys | +0.302 |
luaj | +0.297 |
bri | +0.288 |
nen | +0.282 |
jin | +0.277 |
Neg logit contributions | |
gdala | -0.395 |
ICAN | -0.326 |
amination | -0.317 |
INE | -0.312 |
Magikarp | -0.309 |
Token | il |
Token ID | 346 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
leys | +0.268 |
luaj | +0.267 |
bri | +0.257 |
nen | +0.252 |
ahime | +0.247 |
Neg logit contributions | |
gdala | -0.342 |
ICAN | -0.283 |
amination | -0.273 |
INE | -0.270 |
Magikarp | -0.265 |
Token | Kumar |
Token ID | 26105 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
leys | +1.497 |
luaj | +1.468 |
bri | +1.424 |
nen | +1.397 |
jin | +1.376 |
Neg logit contributions | |
gdala | -2.018 |
ICAN | -1.668 |
amination | -1.619 |
Magikarp | -1.593 |
INE | -1.592 |
Token | / |
Token ID | 14 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
leys | +6.833 |
nen | +6.485 |
bri | +6.474 |
jin | +6.450 |
luaj | +6.450 |
Neg logit contributions | |
gdala | -9.117 |
ICAN | -7.575 |
Magikarp | -7.303 |
amination | -7.206 |
renheit | -7.160 |
Token | Press |
Token ID | 13800 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
leys | +0.863 |
luaj | +0.848 |
bri | +0.828 |
nen | +0.816 |
jin | +0.805 |
Neg logit contributions | |
gdala | -0.766 |
ICAN | -0.608 |
amination | -0.581 |
INE | -0.571 |
Magikarp | -0.570 |
Token | Trust |
Token ID | 9870 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
leys | +1.389 |
luaj | +1.388 |
bri | +1.334 |
nen | +1.304 |
igans | +1.275 |
Neg logit contributions | |
gdala | -2.443 |
ICAN | -2.051 |
amination | -1.996 |
INE | -1.972 |
Magikarp | -1.959 |
Token | of |
Token ID | 286 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
leys | +0.605 |
luaj | +0.595 |
bri | +0.580 |
nen | +0.576 |
jin | +0.565 |
Neg logit contributions | |
gdala | -0.593 |
ICAN | -0.474 |
amination | -0.456 |
INE | -0.447 |
Magikarp | -0.444 |
Token | India |
Token ID | 3794 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
leys | +0.563 |
luaj | +0.552 |
bri | +0.538 |
nen | +0.530 |
jin | +0.524 |
Neg logit contributions | |
gdala | -0.595 |
ICAN | -0.480 |
amination | -0.463 |
Magikarp | -0.456 |
INE | -0.454 |
Token | don |
Token ID | 836 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
gdala | +2.381 |
ICAN | +1.902 |
coinc | +1.871 |
amination | +1.859 |
INE | +1.837 |
Neg logit contributions | |
leys | -1.960 |
luaj | -1.932 |
ahime | -1.849 |
nen | -1.824 |
bri | -1.812 |
Token | 't |
Token ID | 470 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
gdala | +1.945 |
ICAN | +1.604 |
amination | +1.548 |
INE | +1.537 |
Magikarp | +1.518 |
Neg logit contributions | |
leys | -1.517 |
luaj | -1.495 |
bri | -1.454 |
ahime | -1.422 |
nen | -1.397 |
Token | know |
Token ID | 760 |
Feature activation | +8.84e-02 |
Pos logit contributions | |
gdala | +0.519 |
ICAN | +0.428 |
amination | +0.412 |
coinc | +0.412 |
INE | +0.412 |
Neg logit contributions | |
leys | -0.395 |
luaj | -0.394 |
ahime | -0.373 |
nen | -0.369 |
bri | -0.368 |
Token | who |
Token ID | 508 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
leys | +0.067 |
luaj | +0.067 |
bri | +0.064 |
nen | +0.064 |
ahime | +0.063 |
Neg logit contributions | |
gdala | -0.074 |
ICAN | -0.060 |
amination | -0.058 |
INE | -0.058 |
Magikarp | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
leys | +1.429 |
luaj | +1.410 |
bri | +1.362 |
nen | +1.351 |
jin | +1.331 |
Neg logit contributions | |
gdala | -1.635 |
ICAN | -1.333 |
amination | -1.286 |
INE | -1.267 |
Magikarp | -1.259 |
Token | Koch |
Token ID | 17009 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
leys | +0.575 |
luaj | +0.564 |
nen | +0.542 |
bri | +0.541 |
ahime | +0.536 |
Neg logit contributions | |
gdala | -0.732 |
ICAN | -0.606 |
amination | -0.582 |
INE | -0.575 |
Magikarp | -0.574 |
Token | brothers |
Token ID | 9397 |
Feature activation | +5.90e+00 |
Pos logit contributions | |
leys | +4.928 |
bri | +4.534 |
luaj | +4.466 |
nen | +4.377 |
jin | +4.227 |
Neg logit contributions | |
gdala | -11.409 |
ICAN | -9.530 |
amination | -9.522 |
Magikarp | -9.397 |
renheit | -9.312 |
Token | are |
Token ID | 389 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
leys | +3.712 |
luaj | +3.580 |
bri | +3.518 |
nen | +3.436 |
jin | +3.370 |
Neg logit contributions | |
gdala | -5.758 |
ICAN | -4.811 |
amination | -4.689 |
Magikarp | -4.659 |
INE | -4.595 |
Token | ." |
Token ID | 526 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
leys | +0.233 |
luaj | +0.231 |
bri | +0.221 |
nen | +0.219 |
ahime | +0.217 |
Neg logit contributions | |
gdala | -0.290 |
ICAN | -0.238 |
amination | -0.229 |
INE | -0.228 |
Magikarp | -0.226 |
Token |
|
Token ID | 198 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
leys | +1.256 |
luaj | +1.226 |
bri | +1.191 |
nen | +1.170 |
jin | +1.153 |
Neg logit contributions | |
gdala | -1.790 |
ICAN | -1.487 |
amination | -1.442 |
Magikarp | -1.422 |
INE | -1.419 |
Token |
|
Token ID | 198 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
leys | +0.145 |
luaj | +0.141 |
bri | +0.137 |
nen | +0.135 |
jin | +0.133 |
Neg logit contributions | |
gdala | -0.214 |
ICAN | -0.178 |
amination | -0.173 |
Magikarp | -0.171 |
INE | -0.170 |
Token | iting |
Token ID | 1780 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
leys | +2.253 |
luaj | +2.222 |
bri | +2.183 |
nen | +2.164 |
jin | +2.147 |
Neg logit contributions | |
gdala | -1.219 |
ICAN | -0.867 |
amination | -0.808 |
Magikarp | -0.807 |
INE | -0.792 |
Token | campaign |
Token ID | 1923 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
leys | +1.582 |
luaj | +1.552 |
bri | +1.499 |
nen | +1.488 |
jin | +1.465 |
Neg logit contributions | |
gdala | -1.898 |
ICAN | -1.557 |
amination | -1.504 |
INE | -1.485 |
Magikarp | -1.481 |
Token | funds |
Token ID | 5153 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
leys | +1.330 |
luaj | +1.304 |
bri | +1.268 |
nen | +1.256 |
jin | +1.239 |
Neg logit contributions | |
gdala | -1.336 |
ICAN | -1.076 |
amination | -1.033 |
Magikarp | -1.017 |
INE | -1.016 |
Token | from |
Token ID | 422 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
leys | +3.818 |
luaj | +3.710 |
bri | +3.686 |
nen | +3.582 |
igans | +3.534 |
Neg logit contributions | |
gdala | -4.891 |
ICAN | -3.966 |
amination | -3.867 |
Magikarp | -3.820 |
INE | -3.763 |
Token | the |
Token ID | 262 |
Feature activation | +6.35e-02 |
Pos logit contributions | |
leys | +0.108 |
luaj | +0.105 |
nen | +0.102 |
bri | +0.102 |
ahime | +0.101 |
Neg logit contributions | |
gdala | -0.121 |
ICAN | -0.099 |
amination | -0.095 |
INE | -0.095 |
Magikarp | -0.093 |
Token | Koch |
Token ID | 17009 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
leys | +0.046 |
luaj | +0.045 |
nen | +0.044 |
bri | +0.043 |
ahime | +0.043 |
Neg logit contributions | |
gdala | -0.055 |
ICAN | -0.046 |
amination | -0.044 |
INE | -0.044 |
Magikarp | -0.043 |
Token | brothers |
Token ID | 9397 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
leys | +5.091 |
luaj | +4.757 |
bri | +4.753 |
nen | +4.623 |
jin | +4.493 |
Neg logit contributions | |
gdala | -10.924 |
amination | -9.000 |
ICAN | -8.947 |
Magikarp | -8.897 |
renheit | -8.864 |
Token | , |
Token ID | 11 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
leys | +4.204 |
luaj | +4.132 |
bri | +4.054 |
nen | +3.980 |
jin | +3.915 |
Neg logit contributions | |
gdala | -5.264 |
ICAN | -4.268 |
amination | -4.175 |
Magikarp | -4.092 |
INE | -4.056 |
Token | famous |
Token ID | 5863 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
leys | +0.404 |
luaj | +0.397 |
bri | +0.381 |
nen | +0.380 |
ahime | +0.376 |
Neg logit contributions | |
gdala | -0.443 |
ICAN | -0.363 |
amination | -0.348 |
INE | -0.346 |
coinc | -0.343 |
Token | ( |
Token ID | 357 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
gdala | +1.145 |
ICAN | +0.934 |
amination | +0.895 |
coinc | +0.893 |
INE | +0.881 |
Neg logit contributions | |
leys | -1.126 |
luaj | -1.117 |
ahime | -1.075 |
nen | -1.075 |
bri | -1.063 |
Token | or |
Token ID | 273 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
leys | +0.109 |
luaj | +0.107 |
bri | +0.104 |
nen | +0.102 |
jin | +0.101 |
Neg logit contributions | |
gdala | -0.117 |
ICAN | -0.095 |
amination | -0.091 |
Magikarp | -0.090 |
INE | -0.090 |
Token | Albuquerque |
Token ID | 38633 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
gdala | +1.163 |
ICAN | +0.925 |
amination | +0.885 |
INE | +0.873 |
Magikarp | +0.868 |
Neg logit contributions | |
leys | -1.235 |
luaj | -1.216 |
bri | -1.173 |
nen | -1.169 |
ahime | -1.156 |
Token | and |
Token ID | 290 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
gdala | +0.938 |
ICAN | +0.765 |
amination | +0.732 |
INE | +0.727 |
coinc | +0.716 |
Neg logit contributions | |
leys | -0.850 |
luaj | -0.836 |
bri | -0.814 |
nen | -0.796 |
ahime | -0.793 |
Token | then |
Token ID | 788 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
leys | +0.362 |
luaj | +0.356 |
bri | +0.343 |
nen | +0.339 |
ahime | +0.337 |
Neg logit contributions | |
gdala | -0.389 |
ICAN | -0.314 |
amination | -0.305 |
Magikarp | -0.298 |
INE | -0.298 |
Token | to |
Token ID | 284 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
leys | +1.719 |
luaj | +1.683 |
bri | +1.644 |
nen | +1.619 |
jin | +1.598 |
Neg logit contributions | |
gdala | -1.882 |
ICAN | -1.524 |
amination | -1.470 |
Magikarp | -1.448 |
INE | -1.444 |
Token | rural |
Token ID | 10016 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
gdala | +0.245 |
ICAN | +0.195 |
amination | +0.187 |
INE | +0.184 |
Magikarp | +0.184 |
Neg logit contributions | |
leys | -0.257 |
luaj | -0.253 |
bri | -0.245 |
nen | -0.243 |
ahime | -0.240 |
Token | Tennessee |
Token ID | 11287 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
leys | +2.737 |
luaj | +2.671 |
bri | +2.634 |
nen | +2.575 |
jin | +2.547 |
Neg logit contributions | |
gdala | -2.710 |
ICAN | -2.170 |
amination | -2.087 |
Magikarp | -2.064 |
INE | -2.045 |
Token | , |
Token ID | 11 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
leys | +6.573 |
luaj | +6.241 |
bri | +6.183 |
nen | +6.166 |
jin | +6.080 |
Neg logit contributions | |
gdala | -9.264 |
ICAN | -7.592 |
Magikarp | -7.427 |
amination | -7.331 |
renheit | -7.270 |
Token | and |
Token ID | 290 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
leys | +0.325 |
luaj | +0.321 |
bri | +0.310 |
nen | +0.307 |
ahime | +0.303 |
Neg logit contributions | |
gdala | -0.340 |
ICAN | -0.274 |
amination | -0.265 |
INE | -0.261 |
Magikarp | -0.260 |
Token | it |
Token ID | 340 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
gdala | +0.288 |
ICAN | +0.236 |
amination | +0.228 |
coinc | +0.225 |
INE | +0.224 |
Neg logit contributions | |
leys | -0.256 |
luaj | -0.254 |
bri | -0.242 |
ahime | -0.241 |
nen | -0.240 |
Token | seemed |
Token ID | 3947 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
leys | +0.173 |
luaj | +0.171 |
bri | +0.162 |
nen | +0.162 |
ahime | +0.160 |
Neg logit contributions | |
gdala | -0.228 |
ICAN | -0.188 |
amination | -0.182 |
INE | -0.180 |
coinc | -0.180 |
Token | to |
Token ID | 284 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
leys | +0.205 |
luaj | +0.201 |
bri | +0.193 |
nen | +0.192 |
ahime | +0.191 |
Neg logit contributions | |
gdala | -0.230 |
ICAN | -0.188 |
amination | -0.181 |
INE | -0.178 |
Magikarp | -0.178 |
Token |
|
Token ID | 198 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
gdala | +0.094 |
ICAN | +0.078 |
amination | +0.076 |
Magikarp | +0.075 |
INE | +0.075 |
Neg logit contributions | |
leys | -0.064 |
luaj | -0.062 |
bri | -0.060 |
nen | -0.059 |
jin | -0.059 |
Token | R |
Token ID | 49 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
gdala | +0.174 |
ICAN | +0.143 |
INE | +0.136 |
amination | +0.135 |
Magikarp | +0.135 |
Neg logit contributions | |
leys | -0.162 |
luaj | -0.159 |
bri | -0.156 |
nen | -0.152 |
ahime | -0.151 |
Token | S |
Token ID | 311 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
gdala | +0.038 |
ICAN | +0.032 |
amination | +0.031 |
INE | +0.030 |
Magikarp | +0.030 |
Neg logit contributions | |
leys | -0.031 |
luaj | -0.030 |
bri | -0.029 |
nen | -0.029 |
jin | -0.028 |
Token | enth |
Token ID | 7944 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
leys | +0.252 |
luaj | +0.247 |
bri | +0.242 |
nen | +0.237 |
jin | +0.234 |
Neg logit contributions | |
gdala | -0.247 |
ICAN | -0.198 |
amination | -0.191 |
INE | -0.187 |
Magikarp | -0.186 |
Token | il |
Token ID | 346 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
gdala | +0.399 |
ICAN | +0.316 |
amination | +0.306 |
INE | +0.300 |
renheit | +0.294 |
Neg logit contributions | |
leys | -0.423 |
luaj | -0.419 |
bri | -0.411 |
nen | -0.401 |
ahime | -0.396 |
Token | Kumar |
Token ID | 26105 |
Feature activation | +9.84e+00 |
Pos logit contributions | |
leys | +1.005 |
luaj | +0.962 |
bri | +0.926 |
nen | +0.914 |
jin | +0.901 |
Neg logit contributions | |
gdala | -2.465 |
ICAN | -2.121 |
amination | -2.070 |
Magikarp | -2.061 |
INE | -2.035 |
Token | / |
Token ID | 14 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
leys | +6.509 |
bri | +6.215 |
luaj | +6.047 |
jin | +5.936 |
nen | +5.925 |
Neg logit contributions | |
gdala | -8.708 |
ICAN | -7.329 |
Magikarp | -7.082 |
amination | -6.894 |
INE | -6.744 |
Token | Press |
Token ID | 4332 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
leys | +0.804 |
luaj | +0.789 |
bri | +0.772 |
nen | +0.761 |
jin | +0.752 |
Neg logit contributions | |
gdala | -0.709 |
ICAN | -0.560 |
amination | -0.537 |
Magikarp | -0.527 |
INE | -0.526 |
Token | Trust |
Token ID | 9870 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
leys | +1.595 |
luaj | +1.513 |
bri | +1.429 |
nen | +1.411 |
jin | +1.372 |
Neg logit contributions | |
gdala | -4.454 |
ICAN | -3.878 |
amination | -3.787 |
Magikarp | -3.761 |
INE | -3.719 |
Token | of |
Token ID | 286 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
leys | +0.757 |
luaj | +0.741 |
bri | +0.719 |
nen | +0.714 |
jin | +0.706 |
Neg logit contributions | |
gdala | -0.864 |
ICAN | -0.700 |
amination | -0.677 |
Magikarp | -0.673 |
renheit | -0.661 |
Token | India |
Token ID | 3794 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
leys | +0.628 |
luaj | +0.613 |
bri | +0.596 |
nen | +0.589 |
jin | +0.583 |
Neg logit contributions | |
gdala | -0.727 |
ICAN | -0.590 |
amination | -0.570 |
Magikarp | -0.567 |
renheit | -0.556 |
Token | don |
Token ID | 836 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
gdala | +2.059 |
ICAN | +1.675 |
amination | +1.631 |
coinc | +1.618 |
INE | +1.610 |
Neg logit contributions | |
leys | -1.645 |
luaj | -1.625 |
ahime | -1.548 |
bri | -1.534 |
nen | -1.532 |
Token | 't |
Token ID | 470 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
gdala | +1.613 |
ICAN | +1.336 |
amination | +1.290 |
INE | +1.278 |
Magikarp | +1.270 |
Neg logit contributions | |
leys | -1.228 |
luaj | -1.205 |
bri | -1.173 |
ahime | -1.139 |
nen | -1.131 |
Token | know |
Token ID | 760 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
gdala | +0.245 |
ICAN | +0.204 |
amination | +0.196 |
INE | +0.196 |
coinc | +0.195 |
Neg logit contributions | |
luaj | -0.187 |
leys | -0.186 |
ahime | -0.175 |
bri | -0.175 |
nen | -0.175 |
Token | who |
Token ID | 508 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
leys | +0.163 |
luaj | +0.161 |
bri | +0.154 |
nen | +0.154 |
ahime | +0.151 |
Neg logit contributions | |
gdala | -0.223 |
ICAN | -0.187 |
amination | -0.180 |
INE | -0.179 |
Magikarp | -0.178 |
Token | the |
Token ID | 262 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
leys | +1.345 |
luaj | +1.320 |
bri | +1.282 |
nen | +1.267 |
jin | +1.250 |
Neg logit contributions | |
gdala | -1.507 |
ICAN | -1.226 |
amination | -1.182 |
INE | -1.163 |
Magikarp | -1.162 |
Token | Koch |
Token ID | 17009 |
Feature activation | +9.73e+00 |
Pos logit contributions | |
leys | +0.468 |
luaj | +0.458 |
bri | +0.437 |
nen | +0.434 |
ahime | +0.425 |
Neg logit contributions | |
gdala | -0.856 |
ICAN | -0.729 |
amination | -0.705 |
INE | -0.698 |
Magikarp | -0.696 |
Token | brothers |
Token ID | 9397 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
leys | +4.530 |
bri | +4.210 |
luaj | +4.146 |
nen | +3.979 |
igans | +3.889 |
Neg logit contributions | |
gdala | -11.055 |
amination | -9.276 |
ICAN | -9.253 |
Magikarp | -9.099 |
renheit | -8.972 |
Token | are |
Token ID | 389 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
leys | +3.421 |
luaj | +3.274 |
bri | +3.262 |
nen | +3.136 |
jin | +3.079 |
Neg logit contributions | |
gdala | -6.120 |
ICAN | -5.159 |
amination | -5.038 |
Magikarp | -4.976 |
INE | -4.944 |
Token | ." |
Token ID | 526 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
leys | +0.219 |
luaj | +0.215 |
bri | +0.207 |
nen | +0.204 |
ahime | +0.200 |
Neg logit contributions | |
gdala | -0.312 |
ICAN | -0.259 |
amination | -0.251 |
INE | -0.248 |
Magikarp | -0.247 |
Token | It |
Token ID | 632 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
leys | +0.912 |
luaj | +0.893 |
bri | +0.866 |
nen | +0.851 |
jin | +0.837 |
Neg logit contributions | |
gdala | -1.280 |
ICAN | -1.063 |
amination | -1.028 |
INE | -1.016 |
Magikarp | -1.012 |
Token | shows |
Token ID | 2523 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
leys | +1.235 |
luaj | +1.210 |
bri | +1.173 |
nen | +1.153 |
jin | +1.137 |
Neg logit contributions | |
gdala | -1.632 |
ICAN | -1.344 |
amination | -1.305 |
INE | -1.284 |
Magikarp | -1.279 |
Token | Cl |
Token ID | 1012 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
gdala | +0.074 |
ICAN | +0.061 |
amination | +0.059 |
INE | +0.059 |
Magikarp | +0.058 |
Neg logit contributions | |
leys | -0.058 |
luaj | -0.057 |
bri | -0.055 |
nen | -0.054 |
ahime | -0.054 |
Token | ad |
Token ID | 324 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
gdala | +1.289 |
ICAN | +1.042 |
amination | +1.022 |
INE | +0.997 |
renheit | +0.983 |
Neg logit contributions | |
leys | -1.134 |
luaj | -1.126 |
bri | -1.096 |
nen | -1.067 |
jin | -1.051 |
Token | in |
Token ID | 287 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
gdala | +0.587 |
ICAN | +0.464 |
amination | +0.450 |
Magikarp | +0.439 |
INE | +0.438 |
Neg logit contributions | |
leys | -0.658 |
luaj | -0.653 |
bri | -0.638 |
nen | -0.629 |
ahime | -0.620 |
Token | a |
Token ID | 257 |
Feature activation | -6.65e-03 |
Pos logit contributions | |
gdala | +0.807 |
ICAN | +0.662 |
amination | +0.642 |
Magikarp | +0.628 |
INE | +0.625 |
Neg logit contributions | |
leys | -0.707 |
luaj | -0.698 |
bri | -0.663 |
nen | -0.663 |
ahime | -0.659 |
Token | Toronto |
Token ID | 6586 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
gdala | +0.006 |
ICAN | +0.005 |
amination | +0.005 |
INE | +0.005 |
Magikarp | +0.005 |
Neg logit contributions | |
leys | -0.005 |
luaj | -0.005 |
bri | -0.004 |
nen | -0.004 |
ahime | -0.004 |
Token | Argon |
Token ID | 49974 |
Feature activation | +9.71e+00 |
Pos logit contributions | |
leys | +1.983 |
luaj | +1.942 |
bri | +1.890 |
nen | +1.862 |
jin | +1.836 |
Neg logit contributions | |
gdala | -2.348 |
ICAN | -1.921 |
amination | -1.856 |
Magikarp | -1.824 |
INE | -1.822 |
Token | auts |
Token ID | 17712 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
leys | +4.911 |
luaj | +4.720 |
jin | +4.635 |
nen | +4.609 |
bri | +4.532 |
Neg logit contributions | |
gdala | -10.424 |
Magikarp | -8.838 |
ICAN | -8.782 |
amination | -8.628 |
renheit | -8.563 |
Token | football |
Token ID | 4346 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
gdala | +1.337 |
ICAN | +1.089 |
amination | +1.041 |
INE | +1.026 |
Magikarp | +1.017 |
Neg logit contributions | |
leys | -1.307 |
luaj | -1.283 |
bri | -1.244 |
nen | -1.232 |
ahime | -1.219 |
Token | jersey |
Token ID | 22383 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
gdala | +0.533 |
ICAN | +0.425 |
amination | +0.407 |
INE | +0.401 |
Magikarp | +0.398 |
Neg logit contributions | |
leys | -0.579 |
luaj | -0.570 |
bri | -0.553 |
nen | -0.546 |
ahime | -0.538 |
Token | , |
Token ID | 11 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
leys | +0.391 |
luaj | +0.384 |
bri | +0.372 |
nen | +0.366 |
jin | +0.361 |
Neg logit contributions | |
gdala | -0.474 |
ICAN | -0.388 |
amination | -0.376 |
INE | -0.369 |
Magikarp | -0.368 |
Token | he |
Token ID | 339 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
leys | +0.277 |
luaj | +0.272 |
bri | +0.264 |
nen | +0.261 |
ahime | +0.257 |
Neg logit contributions | |
gdala | -0.321 |
ICAN | -0.262 |
amination | -0.253 |
INE | -0.249 |
Magikarp | -0.248 |
Token | involved |
Token ID | 2950 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
leys | +0.806 |
luaj | +0.791 |
bri | +0.763 |
nen | +0.755 |
ahime | +0.739 |
Neg logit contributions | |
gdala | -1.085 |
ICAN | -0.890 |
amination | -0.869 |
INE | -0.856 |
Magikarp | -0.848 |
Token | civilians |
Token ID | 10380 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
leys | +0.727 |
luaj | +0.713 |
bri | +0.692 |
nen | +0.684 |
jin | +0.672 |
Neg logit contributions | |
gdala | -0.811 |
ICAN | -0.659 |
amination | -0.638 |
Magikarp | -0.626 |
INE | -0.624 |
Token | ," |
Token ID | 553 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
gdala | +2.228 |
ICAN | +1.781 |
amination | +1.756 |
coinc | +1.748 |
INE | +1.735 |
Neg logit contributions | |
leys | -1.950 |
luaj | -1.941 |
bri | -1.835 |
nen | -1.827 |
ahime | -1.803 |
Token | Tak |
Token ID | 15804 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
leys | +0.424 |
luaj | +0.418 |
bri | +0.404 |
nen | +0.396 |
jin | +0.390 |
Neg logit contributions | |
gdala | -0.502 |
ICAN | -0.410 |
amination | -0.398 |
INE | -0.391 |
Magikarp | -0.389 |
Token | ashi |
Token ID | 12144 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
leys | +1.633 |
luaj | +1.589 |
bri | +1.538 |
nen | +1.514 |
jin | +1.493 |
Neg logit contributions | |
gdala | -2.645 |
ICAN | -2.222 |
amination | -2.151 |
Magikarp | -2.133 |
INE | -2.122 |
Token | Kin |
Token ID | 16645 |
Feature activation | +9.62e+00 |
Pos logit contributions | |
leys | +3.152 |
luaj | +3.066 |
bri | +2.998 |
nen | +2.970 |
jin | +2.947 |
Neg logit contributions | |
gdala | -3.910 |
ICAN | -3.222 |
amination | -3.106 |
Magikarp | -3.072 |
INE | -3.038 |
Token | osh |
Token ID | 3768 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
leys | +6.032 |
nen | +5.727 |
jin | +5.674 |
luaj | +5.671 |
bri | +5.603 |
Neg logit contributions | |
gdala | -9.114 |
ICAN | -7.761 |
Magikarp | -7.605 |
INE | -7.309 |
amination | -7.299 |
Token | ita |
Token ID | 5350 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
leys | +0.808 |
luaj | +0.797 |
bri | +0.780 |
nen | +0.768 |
jin | +0.758 |
Neg logit contributions | |
gdala | -0.665 |
ICAN | -0.519 |
amination | -0.497 |
INE | -0.486 |
Magikarp | -0.483 |
Token | , |
Token ID | 11 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
leys | +1.849 |
luaj | +1.801 |
bri | +1.760 |
nen | +1.733 |
jin | +1.712 |
Neg logit contributions | |
gdala | -2.463 |
ICAN | -2.034 |
amination | -1.969 |
Magikarp | -1.943 |
INE | -1.934 |
Token | chief |
Token ID | 4039 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
leys | +0.806 |
luaj | +0.790 |
bri | +0.766 |
nen | +0.752 |
jin | +0.741 |
Neg logit contributions | |
gdala | -1.000 |
ICAN | -0.821 |
amination | -0.796 |
INE | -0.781 |
Magikarp | -0.781 |
Token | of |
Token ID | 286 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
leys | +1.999 |
luaj | +1.948 |
bri | +1.916 |
nen | +1.887 |
jin | +1.873 |
Neg logit contributions | |
gdala | -2.202 |
ICAN | -1.780 |
amination | -1.713 |
Magikarp | -1.694 |
INE | -1.681 |
Token | the |
Token ID | 262 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
leys | +2.149 |
luaj | +2.094 |
bri | +2.058 |
nen | +2.025 |
jin | +1.996 |
Neg logit contributions | |
gdala | -2.451 |
ICAN | -1.988 |
amination | -1.927 |
Magikarp | -1.907 |
INE | -1.882 |
Token | 2007 |
Token ID | 4343 |
Feature activation | +5.03e+00 |
Pos logit contributions | |
gdala | +0.047 |
ICAN | +0.038 |
amination | +0.037 |
INE | +0.036 |
Magikarp | +0.036 |
Neg logit contributions | |
leys | -0.042 |
luaj | -0.041 |
bri | -0.040 |
nen | -0.040 |
jin | -0.039 |
Token | Sy |
Token ID | 1632 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
leys | +3.577 |
luaj | +3.483 |
bri | +3.445 |
nen | +3.389 |
jin | +3.336 |
Neg logit contributions | |
gdala | -4.436 |
ICAN | -3.594 |
Magikarp | -3.509 |
amination | -3.503 |
INE | -3.413 |
Token | fy |
Token ID | 24928 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
leys | +2.560 |
luaj | +2.487 |
bri | +2.422 |
nen | +2.413 |
jin | +2.379 |
Neg logit contributions | |
gdala | -3.248 |
ICAN | -2.687 |
Magikarp | -2.598 |
amination | -2.593 |
INE | -2.553 |
Token | mini |
Token ID | 9927 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
gdala | +1.772 |
ICAN | +1.489 |
amination | +1.418 |
INE | +1.414 |
coinc | +1.379 |
Neg logit contributions | |
leys | -1.464 |
luaj | -1.451 |
bri | -1.374 |
nen | -1.356 |
igans | -1.344 |
Token | Tin |
Token ID | 22894 |
Feature activation | +9.59e+00 |
Pos logit contributions | |
leys | +0.621 |
luaj | +0.606 |
bri | +0.588 |
nen | +0.577 |
jin | +0.567 |
Neg logit contributions | |
gdala | -0.940 |
ICAN | -0.785 |
amination | -0.762 |
Magikarp | -0.751 |
INE | -0.751 |
Token | Man |
Token ID | 1869 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
leys | +5.760 |
jin | +5.248 |
bri | +5.153 |
nen | +5.112 |
luaj | +5.106 |
Neg logit contributions | |
gdala | -9.528 |
ICAN | -8.071 |
Magikarp | -8.001 |
amination | -7.786 |
INE | -7.748 |
Token | as |
Token ID | 355 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
leys | +1.446 |
luaj | +1.411 |
bri | +1.375 |
nen | +1.355 |
jin | +1.336 |
Neg logit contributions | |
gdala | -1.816 |
ICAN | -1.491 |
amination | -1.444 |
Magikarp | -1.424 |
INE | -1.417 |
Token | well |
Token ID | 880 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
gdala | +0.646 |
ICAN | +0.528 |
amination | +0.511 |
Magikarp | +0.504 |
INE | +0.502 |
Neg logit contributions | |
leys | -0.553 |
luaj | -0.546 |
bri | -0.528 |
nen | -0.521 |
jin | -0.512 |
Token | as |
Token ID | 355 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
leys | +0.842 |
luaj | +0.822 |
bri | +0.807 |
nen | +0.793 |
jin | +0.783 |
Neg logit contributions | |
gdala | -0.929 |
ICAN | -0.750 |
amination | -0.725 |
Magikarp | -0.710 |
INE | -0.707 |
Token | the |
Token ID | 262 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
gdala | +0.860 |
ICAN | +0.699 |
amination | +0.671 |
INE | +0.666 |
Magikarp | +0.655 |
Neg logit contributions | |
leys | -0.807 |
luaj | -0.800 |
bri | -0.766 |
nen | -0.756 |
jin | -0.748 |
Token | Core |
Token ID | 7231 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
leys | +1.364 |
luaj | +1.343 |
bri | +1.313 |
nen | +1.295 |
jin | +1.280 |
Neg logit contributions | |
gdala | -1.123 |
ICAN | -0.880 |
amination | -0.849 |
INE | -0.828 |
Magikarp | -0.821 |
Token | opponents |
Token ID | 7691 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
gdala | +1.648 |
ICAN | +1.360 |
amination | +1.302 |
INE | +1.297 |
Magikarp | +1.264 |
Neg logit contributions | |
leys | -1.503 |
luaj | -1.493 |
bri | -1.427 |
ahime | -1.408 |
nen | -1.405 |
Token | in |
Token ID | 287 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
leys | +1.193 |
luaj | +1.168 |
bri | +1.140 |
nen | +1.123 |
jin | +1.108 |
Neg logit contributions | |
gdala | -1.299 |
ICAN | -1.051 |
amination | -1.014 |
Magikarp | -0.999 |
INE | -0.995 |
Token | Utah |
Token ID | 10202 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
gdala | +0.657 |
ICAN | +0.528 |
amination | +0.512 |
INE | +0.501 |
Magikarp | +0.496 |
Neg logit contributions | |
leys | -0.641 |
luaj | -0.630 |
bri | -0.609 |
nen | -0.604 |
jin | -0.598 |
Token | and |
Token ID | 290 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
leys | +1.970 |
luaj | +1.919 |
bri | +1.875 |
nen | +1.846 |
jin | +1.819 |
Neg logit contributions | |
gdala | -2.501 |
ICAN | -2.049 |
amination | -1.989 |
Magikarp | -1.962 |
INE | -1.948 |
Token | Tennessee |
Token ID | 11287 |
Feature activation | +9.52e+00 |
Pos logit contributions | |
leys | +0.178 |
luaj | +0.175 |
bri | +0.170 |
nen | +0.168 |
jin | +0.166 |
Neg logit contributions | |
gdala | -0.177 |
ICAN | -0.143 |
amination | -0.138 |
INE | -0.135 |
Magikarp | -0.134 |
Token | .) |
Token ID | 2014 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
leys | +6.062 |
bri | +5.811 |
nen | +5.739 |
luaj | +5.723 |
jin | +5.603 |
Neg logit contributions | |
gdala | -8.821 |
ICAN | -7.175 |
Magikarp | -7.068 |
amination | -7.055 |
renheit | -6.891 |
Token |
|
Token ID | 198 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
leys | +1.991 |
luaj | +1.945 |
bri | +1.894 |
nen | +1.864 |
jin | +1.839 |
Neg logit contributions | |
gdala | -2.710 |
ICAN | -2.237 |
amination | -2.178 |
Magikarp | -2.153 |
INE | -2.119 |
Token |
|
Token ID | 198 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
gdala | +0.228 |
ICAN | +0.189 |
amination | +0.184 |
Magikarp | +0.181 |
INE | +0.181 |
Neg logit contributions | |
leys | -0.158 |
luaj | -0.154 |
bri | -0.150 |
nen | -0.147 |
jin | -0.145 |
Token | We |
Token ID | 1135 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
gdala | +0.130 |
ICAN | +0.106 |
INE | +0.102 |
amination | +0.101 |
Magikarp | +0.101 |
Neg logit contributions | |
leys | -0.119 |
luaj | -0.116 |
bri | -0.115 |
nen | -0.112 |
ahime | -0.111 |
Token | rated |
Token ID | 13178 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
leys | +0.960 |
luaj | +0.938 |
bri | +0.909 |
nen | +0.892 |
jin | +0.877 |
Neg logit contributions | |
gdala | -1.471 |
ICAN | -1.229 |
amination | -1.193 |
INE | -1.177 |
Magikarp | -1.176 |
Token | aging |
Token ID | 3039 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
leys | +0.671 |
luaj | +0.657 |
bri | +0.644 |
nen | +0.636 |
jin | +0.629 |
Neg logit contributions | |
gdala | -0.586 |
ICAN | -0.459 |
amination | -0.441 |
Magikarp | -0.434 |
INE | -0.430 |
Token | � |
Token ID | 447 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
gdala | +0.210 |
ICAN | +0.170 |
amination | +0.164 |
INE | +0.163 |
Magikarp | +0.162 |
Neg logit contributions | |
leys | -0.190 |
luaj | -0.188 |
bri | -0.182 |
nen | -0.180 |
ahime | -0.178 |
Token | � |
Token ID | 251 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
leys | +0.610 |
luaj | +0.600 |
bri | +0.586 |
nen | +0.578 |
jin | +0.571 |
Neg logit contributions | |
gdala | -0.547 |
ICAN | -0.432 |
amination | -0.415 |
Magikarp | -0.408 |
INE | -0.407 |
Token | in |
Token ID | 287 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
leys | +0.527 |
luaj | +0.521 |
bri | +0.504 |
nen | +0.494 |
ahime | +0.487 |
Neg logit contributions | |
gdala | -0.682 |
ICAN | -0.558 |
amination | -0.540 |
INE | -0.536 |
Magikarp | -0.534 |
Token | the |
Token ID | 262 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
gdala | +0.353 |
ICAN | +0.286 |
amination | +0.277 |
INE | +0.275 |
Magikarp | +0.273 |
Neg logit contributions | |
leys | -0.316 |
luaj | -0.312 |
bri | -0.300 |
nen | -0.298 |
jin | -0.292 |
Token | Yuk |
Token ID | 19760 |
Feature activation | +9.47e+00 |
Pos logit contributions | |
gdala | +0.278 |
ICAN | +0.227 |
amination | +0.221 |
INE | +0.219 |
Magikarp | +0.216 |
Neg logit contributions | |
leys | -0.230 |
luaj | -0.228 |
nen | -0.218 |
bri | -0.218 |
ahime | -0.214 |
Token | on |
Token ID | 261 |
Feature activation | +6.62e+00 |
Pos logit contributions | |
leys | +6.877 |
luaj | +6.493 |
jin | +6.341 |
nen | +6.299 |
bri | +6.251 |
Neg logit contributions | |
gdala | -8.313 |
ICAN | -6.776 |
Magikarp | -6.622 |
amination | -6.565 |
INE | -6.322 |
Token | . |
Token ID | 13 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
leys | +4.614 |
luaj | +4.467 |
bri | +4.419 |
nen | +4.324 |
jin | +4.281 |
Neg logit contributions | |
gdala | -5.966 |
ICAN | -4.880 |
amination | -4.749 |
Magikarp | -4.721 |
renheit | -4.639 |
Token | H |
Token ID | 367 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
leys | +0.149 |
luaj | +0.146 |
bri | +0.141 |
nen | +0.139 |
ahime | +0.137 |
Neg logit contributions | |
gdala | -0.198 |
ICAN | -0.164 |
amination | -0.157 |
INE | -0.157 |
Magikarp | -0.156 |
Token | ordes |
Token ID | 35770 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
gdala | +0.325 |
ICAN | +0.266 |
amination | +0.258 |
INE | +0.256 |
Magikarp | +0.252 |
Neg logit contributions | |
leys | -0.274 |
luaj | -0.271 |
bri | -0.262 |
nen | -0.257 |
ahime | -0.253 |
Token | will |
Token ID | 481 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
leys | +0.344 |
luaj | +0.338 |
bri | +0.330 |
nen | +0.325 |
jin | +0.321 |
Neg logit contributions | |
gdala | -0.349 |
ICAN | -0.280 |
amination | -0.269 |
Magikarp | -0.265 |
INE | -0.265 |
Token | of |
Token ID | 286 |
Feature activation | +8.50e-03 |
Pos logit contributions | |
gdala | +1.885 |
ICAN | +1.540 |
amination | +1.479 |
coinc | +1.478 |
INE | +1.464 |
Neg logit contributions | |
leys | -1.602 |
luaj | -1.569 |
nen | -1.512 |
ahime | -1.509 |
bri | -1.494 |
Token | this |
Token ID | 428 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
leys | +0.006 |
luaj | +0.006 |
bri | +0.006 |
nen | +0.006 |
ahime | +0.006 |
Neg logit contributions | |
gdala | -0.007 |
ICAN | -0.006 |
amination | -0.006 |
INE | -0.006 |
Magikarp | -0.006 |
Token | : |
Token ID | 25 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
leys | +1.115 |
luaj | +1.093 |
bri | +1.057 |
nen | +1.049 |
jin | +1.032 |
Neg logit contributions | |
gdala | -1.311 |
ICAN | -1.070 |
amination | -1.035 |
INE | -1.022 |
Magikarp | -1.018 |
Token | Success |
Token ID | 16282 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
leys | +0.472 |
luaj | +0.465 |
bri | +0.450 |
nen | +0.444 |
ahime | +0.438 |
Neg logit contributions | |
gdala | -0.554 |
ICAN | -0.452 |
amination | -0.436 |
INE | -0.431 |
Magikarp | -0.428 |
Token | like |
Token ID | 588 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
leys | +2.067 |
luaj | +2.018 |
bri | +1.957 |
nen | +1.918 |
jin | +1.892 |
Neg logit contributions | |
gdala | -3.229 |
ICAN | -2.698 |
amination | -2.620 |
Magikarp | -2.588 |
INE | -2.573 |
Token | Blackburn |
Token ID | 42603 |
Feature activation | +9.43e+00 |
Pos logit contributions | |
gdala | +0.940 |
ICAN | +0.761 |
amination | +0.736 |
INE | +0.726 |
Magikarp | +0.724 |
Neg logit contributions | |
leys | -0.871 |
luaj | -0.853 |
bri | -0.828 |
nen | -0.822 |
ahime | -0.814 |
Token | 's |
Token ID | 338 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
leys | +6.381 |
luaj | +6.157 |
bri | +5.987 |
nen | +5.960 |
jin | +5.785 |
Neg logit contributions | |
gdala | -8.587 |
ICAN | -7.176 |
amination | -6.913 |
Magikarp | -6.849 |
renheit | -6.835 |
Token | , |
Token ID | 11 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
leys | +0.895 |
luaj | +0.878 |
bri | +0.853 |
nen | +0.843 |
ahime | +0.833 |
Neg logit contributions | |
gdala | -0.944 |
ICAN | -0.760 |
amination | -0.733 |
INE | -0.724 |
Magikarp | -0.722 |
Token | aided |
Token ID | 28310 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
leys | +0.684 |
luaj | +0.672 |
bri | +0.652 |
nen | +0.645 |
ahime | +0.631 |
Neg logit contributions | |
gdala | -0.869 |
ICAN | -0.715 |
amination | -0.689 |
Magikarp | -0.683 |
INE | -0.683 |
Token | by |
Token ID | 416 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
gdala | +0.425 |
ICAN | +0.339 |
amination | +0.327 |
Magikarp | +0.322 |
INE | +0.321 |
Neg logit contributions | |
leys | -0.437 |
luaj | -0.429 |
bri | -0.419 |
nen | -0.414 |
jin | -0.407 |
Token | Jack |
Token ID | 3619 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
leys | +0.630 |
luaj | +0.618 |
bri | +0.600 |
nen | +0.593 |
jin | +0.584 |
Neg logit contributions | |
gdala | -0.726 |
ICAN | -0.593 |
amination | -0.571 |
Magikarp | -0.564 |
INE | -0.563 |
Token | called |
Token ID | 1444 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
leys | +1.060 |
luaj | +1.034 |
bri | +0.999 |
nen | +0.986 |
jin | +0.966 |
Neg logit contributions | |
gdala | -1.612 |
ICAN | -1.347 |
amination | -1.307 |
Magikarp | -1.288 |
INE | -1.287 |
Token | the |
Token ID | 262 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
leys | +0.898 |
luaj | +0.880 |
bri | +0.858 |
nen | +0.845 |
jin | +0.835 |
Neg logit contributions | |
gdala | -0.981 |
ICAN | -0.794 |
amination | -0.766 |
Magikarp | -0.754 |
INE | -0.752 |
Token | Stephen |
Token ID | 7970 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
leys | +0.177 |
luaj | +0.174 |
bri | +0.169 |
nen | +0.167 |
jin | +0.165 |
Neg logit contributions | |
gdala | -0.189 |
ICAN | -0.153 |
amination | -0.147 |
INE | -0.144 |
Magikarp | -0.144 |
Token | and |
Token ID | 290 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
gdala | +1.808 |
ICAN | +1.444 |
amination | +1.405 |
INE | +1.388 |
renheit | +1.372 |
Neg logit contributions | |
luaj | -1.771 |
leys | -1.770 |
bri | -1.717 |
nen | -1.686 |
ahime | -1.667 |
Token | Mary |
Token ID | 5335 |
Feature activation | +9.13e-01 |
Pos logit contributions | |
leys | +0.957 |
luaj | +0.939 |
bri | +0.916 |
nen | +0.904 |
jin | +0.892 |
Neg logit contributions | |
gdala | -0.962 |
ICAN | -0.772 |
amination | -0.743 |
Magikarp | -0.731 |
INE | -0.729 |
Token | Birch |
Token ID | 47631 |
Feature activation | +9.42e+00 |
Pos logit contributions | |
leys | +0.746 |
luaj | +0.734 |
bri | +0.715 |
nen | +0.706 |
jin | +0.697 |
Neg logit contributions | |
gdala | -0.720 |
ICAN | -0.573 |
amination | -0.551 |
INE | -0.542 |
Magikarp | -0.541 |
Token | Texas |
Token ID | 3936 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
leys | +6.705 |
bri | +6.218 |
luaj | +6.144 |
igans | +6.088 |
jin | +6.003 |
Neg logit contributions | |
gdala | -8.309 |
ICAN | -6.719 |
Magikarp | -6.650 |
amination | -6.544 |
INE | -6.398 |
Token | Theater |
Token ID | 22207 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
leys | +2.585 |
luaj | +2.505 |
bri | +2.451 |
nen | +2.405 |
jin | +2.373 |
Neg logit contributions | |
gdala | -3.304 |
ICAN | -2.709 |
amination | -2.634 |
Magikarp | -2.605 |
INE | -2.581 |
Token | , |
Token ID | 11 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
leys | +1.171 |
luaj | +1.145 |
bri | +1.116 |
nen | +1.098 |
jin | +1.083 |
Neg logit contributions | |
gdala | -1.408 |
ICAN | -1.152 |
amination | -1.114 |
Magikarp | -1.098 |
INE | -1.094 |
Token | for |
Token ID | 329 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
leys | +0.509 |
luaj | +0.499 |
bri | +0.486 |
nen | +0.480 |
jin | +0.473 |
Neg logit contributions | |
gdala | -0.548 |
ICAN | -0.443 |
amination | -0.427 |
Magikarp | -0.421 |
INE | -0.420 |
Token | over |
Token ID | 625 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
leys | +0.676 |
luaj | +0.664 |
bri | +0.645 |
nen | +0.637 |
jin | +0.628 |
Neg logit contributions | |
gdala | -0.756 |
ICAN | -0.615 |
amination | -0.593 |
Magikarp | -0.583 |
INE | -0.583 |
Token | onto |
Token ID | 4291 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
gdala | +0.762 |
ICAN | +0.618 |
amination | +0.598 |
INE | +0.588 |
Magikarp | +0.586 |
Neg logit contributions | |
leys | -0.689 |
luaj | -0.679 |
bri | -0.656 |
nen | -0.646 |
ahime | -0.637 |
Token | front |
Token ID | 2166 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
leys | +0.419 |
luaj | +0.410 |
bri | +0.399 |
nen | +0.393 |
jin | +0.388 |
Neg logit contributions | |
gdala | -0.466 |
ICAN | -0.379 |
amination | -0.366 |
Magikarp | -0.360 |
INE | -0.359 |
Token | stage |
Token ID | 3800 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
gdala | +3.614 |
ICAN | +2.973 |
amination | +2.962 |
INE | +2.922 |
renheit | +2.850 |
Neg logit contributions | |
leys | -2.571 |
luaj | -2.533 |
ahime | -2.382 |
nen | -2.366 |
bri | -2.364 |
Token | ( |
Token ID | 357 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
gdala | +0.052 |
ICAN | +0.042 |
amination | +0.041 |
INE | +0.040 |
Magikarp | +0.040 |
Neg logit contributions | |
leys | -0.044 |
luaj | -0.043 |
bri | -0.042 |
nen | -0.041 |
jin | -0.040 |
Token | the |
Token ID | 1169 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
gdala | +0.205 |
ICAN | +0.167 |
amination | +0.160 |
INE | +0.158 |
Magikarp | +0.157 |
Neg logit contributions | |
leys | -0.203 |
luaj | -0.200 |
bri | -0.196 |
nen | -0.191 |
ahime | -0.188 |
Token | dialect |
Token ID | 23637 |
Feature activation | +9.41e+00 |
Pos logit contributions | |
gdala | +0.635 |
ICAN | +0.527 |
amination | +0.510 |
INE | +0.501 |
Magikarp | +0.497 |
Neg logit contributions | |
leys | -0.513 |
luaj | -0.503 |
bri | -0.485 |
nen | -0.480 |
igans | -0.471 |
Token | ic |
Token ID | 291 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
leys | +6.391 |
luaj | +6.286 |
bri | +6.095 |
nen | +5.980 |
jin | +5.980 |
Neg logit contributions | |
gdala | -8.430 |
Magikarp | -6.749 |
ICAN | -6.723 |
amination | -6.592 |
renheit | -6.491 |
Token | of |
Token ID | 286 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
leys | +0.213 |
luaj | +0.210 |
bri | +0.203 |
nen | +0.201 |
jin | +0.198 |
Neg logit contributions | |
gdala | -0.220 |
ICAN | -0.178 |
amination | -0.172 |
INE | -0.170 |
Magikarp | -0.168 |
Token | an |
Token ID | 281 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
gdala | +0.334 |
ICAN | +0.274 |
amination | +0.266 |
INE | +0.262 |
Magikarp | +0.261 |
Neg logit contributions | |
leys | -0.293 |
luaj | -0.287 |
bri | -0.278 |
nen | -0.275 |
jin | -0.270 |
Token | extended |
Token ID | 7083 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
gdala | +0.648 |
ICAN | +0.530 |
amination | +0.517 |
INE | +0.508 |
Magikarp | +0.506 |
Neg logit contributions | |
leys | -0.574 |
luaj | -0.560 |
bri | -0.547 |
nen | -0.541 |
jin | -0.528 |
Token | mass |
Token ID | 2347 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
gdala | +2.628 |
ICAN | +2.160 |
amination | +2.106 |
INE | +2.106 |
coinc | +2.073 |
Neg logit contributions | |
leys | -2.123 |
luaj | -2.077 |
nen | -1.982 |
bri | -1.966 |
igans | -1.945 |
Token | Roy |
Token ID | 9817 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
gdala | +0.967 |
ICAN | +0.783 |
amination | +0.759 |
INE | +0.750 |
Magikarp | +0.736 |
Neg logit contributions | |
leys | -0.873 |
luaj | -0.852 |
nen | -0.819 |
bri | -0.818 |
ahime | -0.814 |
Token | Roman |
Token ID | 7993 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
leys | +2.498 |
luaj | +2.440 |
bri | +2.387 |
nen | +2.357 |
jin | +2.327 |
Neg logit contributions | |
gdala | -2.689 |
ICAN | -2.192 |
amination | -2.103 |
Magikarp | -2.076 |
INE | -2.062 |
Token | ow |
Token ID | 322 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
leys | +2.257 |
luaj | +2.211 |
bri | +2.156 |
nen | +2.124 |
jin | +2.096 |
Neg logit contributions | |
gdala | -2.488 |
ICAN | -2.017 |
amination | -1.947 |
Magikarp | -1.916 |
INE | -1.911 |
Token | , |
Token ID | 11 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
leys | +0.838 |
luaj | +0.821 |
bri | +0.798 |
nen | +0.783 |
jin | +0.772 |
Neg logit contributions | |
gdala | -1.040 |
ICAN | -0.857 |
amination | -0.826 |
INE | -0.814 |
Magikarp | -0.813 |
Token | the |
Token ID | 262 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
leys | +0.134 |
luaj | +0.132 |
bri | +0.127 |
nen | +0.126 |
ahime | +0.124 |
Neg logit contributions | |
gdala | -0.153 |
ICAN | -0.125 |
amination | -0.121 |
INE | -0.119 |
Magikarp | -0.118 |
Token | Saskatchewan |
Token ID | 31346 |
Feature activation | +9.38e+00 |
Pos logit contributions | |
gdala | +0.613 |
ICAN | +0.500 |
amination | +0.484 |
INE | +0.475 |
Magikarp | +0.468 |
Neg logit contributions | |
leys | -0.557 |
luaj | -0.545 |
bri | -0.525 |
nen | -0.525 |
ahime | -0.519 |
Token | premier |
Token ID | 18256 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
leys | +5.683 |
bri | +5.579 |
luaj | +5.552 |
nen | +5.390 |
jin | +5.354 |
Neg logit contributions | |
gdala | -9.112 |
ICAN | -7.523 |
Magikarp | -7.379 |
amination | -7.249 |
renheit | -7.243 |
Token | whom |
Token ID | 4150 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
leys | +1.364 |
luaj | +1.334 |
bri | +1.296 |
nen | +1.273 |
jin | +1.254 |
Neg logit contributions | |
gdala | -1.828 |
ICAN | -1.510 |
amination | -1.463 |
Magikarp | -1.441 |
INE | -1.440 |
Token | To |
Token ID | 1675 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
leys | +1.192 |
luaj | +1.170 |
bri | +1.138 |
nen | +1.123 |
jin | +1.109 |
Neg logit contributions | |
gdala | -1.240 |
ICAN | -0.998 |
amination | -0.965 |
INE | -0.947 |
Magikarp | -0.944 |
Token | pp |
Token ID | 381 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
leys | +0.979 |
luaj | +0.956 |
bri | +0.928 |
nen | +0.927 |
jin | +0.915 |
Neg logit contributions | |
gdala | -1.144 |
ICAN | -0.935 |
amination | -0.899 |
Magikarp | -0.890 |
INE | -0.883 |
Token | served |
Token ID | 4983 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
gdala | +1.702 |
ICAN | +1.405 |
coinc | +1.390 |
amination | +1.361 |
INE | +1.361 |
Neg logit contributions | |
leys | -1.150 |
luaj | -1.139 |
bri | -1.067 |
ahime | -1.061 |
nen | -1.045 |
Token | Ragnar |
Token ID | 32797 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
gdala | +0.920 |
ICAN | +0.738 |
amination | +0.707 |
INE | +0.702 |
Magikarp | +0.691 |
Neg logit contributions | |
leys | -0.943 |
luaj | -0.921 |
bri | -0.894 |
nen | -0.886 |
ahime | -0.885 |
Token | Fr |
Token ID | 1305 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
leys | +0.476 |
luaj | +0.467 |
bri | +0.455 |
nen | +0.446 |
jin | +0.441 |
Neg logit contributions | |
gdala | -0.521 |
ICAN | -0.421 |
amination | -0.408 |
INE | -0.401 |
Magikarp | -0.398 |
Token | isch |
Token ID | 25308 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
gdala | +3.357 |
ICAN | +2.707 |
amination | +2.654 |
INE | +2.586 |
renheit | +2.474 |
Neg logit contributions | |
luaj | -3.306 |
leys | -3.289 |
bri | -3.180 |
ahime | -3.091 |
nen | -3.031 |
Token | and |
Token ID | 290 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
leys | +0.363 |
luaj | +0.358 |
bri | +0.346 |
nen | +0.339 |
ahime | +0.337 |
Neg logit contributions | |
gdala | -0.390 |
ICAN | -0.315 |
amination | -0.304 |
INE | -0.298 |
Magikarp | -0.297 |
Token | Jan |
Token ID | 2365 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
leys | +0.316 |
luaj | +0.310 |
bri | +0.301 |
nen | +0.297 |
ahime | +0.295 |
Neg logit contributions | |
gdala | -0.334 |
ICAN | -0.269 |
amination | -0.260 |
INE | -0.257 |
Magikarp | -0.255 |
Token | Tin |
Token ID | 22894 |
Feature activation | +9.36e+00 |
Pos logit contributions | |
gdala | +1.628 |
ICAN | +1.290 |
amination | +1.276 |
INE | +1.256 |
Magikarp | +1.219 |
Neg logit contributions | |
leys | -1.504 |
luaj | -1.481 |
bri | -1.445 |
ahime | -1.402 |
nen | -1.395 |
Token | berg |
Token ID | 3900 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
leys | +6.513 |
nen | +6.185 |
jin | +6.163 |
bri | +6.110 |
luaj | +6.048 |
Neg logit contributions | |
gdala | -8.147 |
ICAN | -6.882 |
Magikarp | -6.719 |
amination | -6.484 |
INE | -6.474 |
Token | en |
Token ID | 268 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
gdala | +0.615 |
ICAN | +0.496 |
amination | +0.477 |
INE | +0.470 |
Magikarp | +0.465 |
Neg logit contributions | |
leys | -0.568 |
luaj | -0.563 |
bri | -0.544 |
ahime | -0.532 |
nen | -0.526 |
Token | in |
Token ID | 287 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
leys | +2.215 |
luaj | +2.165 |
bri | +2.115 |
nen | +2.088 |
jin | +2.060 |
Neg logit contributions | |
gdala | -2.508 |
ICAN | -2.040 |
amination | -1.970 |
Magikarp | -1.940 |
INE | -1.932 |
Token | 1969 |
Token ID | 16450 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
gdala | +0.316 |
ICAN | +0.252 |
amination | +0.243 |
INE | +0.239 |
Magikarp | +0.238 |
Neg logit contributions | |
leys | -0.326 |
luaj | -0.319 |
bri | -0.309 |
nen | -0.307 |
igans | -0.303 |
Token | . |
Token ID | 13 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
leys | +3.934 |
luaj | +3.871 |
bri | +3.754 |
nen | +3.720 |
jin | +3.671 |
Neg logit contributions | |
gdala | -5.123 |
ICAN | -4.212 |
amination | -4.122 |
Magikarp | -4.058 |
INE | -4.013 |
Token | 3 |
Token ID | 18 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
gdala | +1.750 |
ICAN | +1.474 |
INE | +1.414 |
amination | +1.399 |
Magikarp | +1.388 |
Neg logit contributions | |
leys | -1.370 |
luaj | -1.348 |
bri | -1.303 |
nen | -1.275 |
ahime | -1.266 |
Token | competition |
Token ID | 5449 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
gdala | +1.768 |
ICAN | +1.459 |
amination | +1.383 |
INE | +1.378 |
Magikarp | +1.356 |
Neg logit contributions | |
leys | -1.646 |
luaj | -1.611 |
bri | -1.554 |
nen | -1.535 |
ahime | -1.521 |
Token | . |
Token ID | 13 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
gdala | +0.868 |
ICAN | +0.711 |
amination | +0.681 |
INE | +0.677 |
Magikarp | +0.668 |
Neg logit contributions | |
leys | -0.796 |
luaj | -0.782 |
bri | -0.752 |
nen | -0.744 |
ahime | -0.737 |
Token |
|
Token ID | 198 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
gdala | +0.496 |
ICAN | +0.411 |
amination | +0.396 |
INE | +0.391 |
Magikarp | +0.391 |
Neg logit contributions | |
leys | -0.376 |
luaj | -0.367 |
bri | -0.356 |
nen | -0.351 |
jin | -0.345 |
Token |
|
Token ID | 198 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
gdala | +0.455 |
ICAN | +0.379 |
amination | +0.368 |
Magikarp | +0.363 |
INE | +0.361 |
Neg logit contributions | |
leys | -0.311 |
luaj | -0.304 |
bri | -0.295 |
nen | -0.290 |
jin | -0.286 |
Token | Cos |
Token ID | 36734 |
Feature activation | -9.91e+00 |
Pos logit contributions | |
gdala | +0.461 |
ICAN | +0.379 |
Magikarp | +0.360 |
amination | +0.359 |
INE | +0.359 |
Neg logit contributions | |
leys | -0.421 |
luaj | -0.412 |
bri | -0.404 |
nen | -0.396 |
ahime | -0.392 |
Token | m |
Token ID | 76 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
gdala | +6.320 |
amination | +4.868 |
ICAN | +4.726 |
INE | +4.577 |
ithmetic | +4.511 |
Neg logit contributions | |
luaj | -8.591 |
leys | -8.497 |
bri | -8.495 |
ahime | -8.278 |
nen | -8.111 |
Token | ologist |
Token ID | 7451 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
gdala | +0.744 |
ICAN | +0.607 |
amination | +0.587 |
INE | +0.575 |
Magikarp | +0.572 |
Neg logit contributions | |
leys | -0.667 |
luaj | -0.654 |
bri | -0.636 |
nen | -0.628 |
ahime | -0.617 |
Token | Eric |
Token ID | 7651 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
gdala | +2.537 |
ICAN | +2.006 |
amination | +1.968 |
INE | +1.949 |
coinc | +1.905 |
Neg logit contributions | |
leys | -2.403 |
luaj | -2.397 |
ahime | -2.291 |
bri | -2.284 |
nen | -2.276 |
Token | L |
Token ID | 406 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
gdala | +2.098 |
ICAN | +1.671 |
amination | +1.641 |
INE | +1.606 |
Magikarp | +1.571 |
Neg logit contributions | |
leys | -1.951 |
luaj | -1.925 |
bri | -1.869 |
ahime | -1.835 |
nen | -1.830 |
Token | inder |
Token ID | 5540 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
gdala | +1.935 |
ICAN | +1.570 |
amination | +1.559 |
INE | +1.512 |
renheit | +1.483 |
Neg logit contributions | |
leys | -1.581 |
luaj | -1.575 |
bri | -1.530 |
nen | -1.485 |
ahime | -1.475 |
Token | Def |
Token ID | 2896 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
leys | +0.112 |
luaj | +0.109 |
bri | +0.106 |
nen | +0.104 |
jin | +0.102 |
Neg logit contributions | |
gdala | -0.153 |
ICAN | -0.128 |
amination | -0.123 |
INE | -0.121 |
Magikarp | -0.121 |
Token | erred |
Token ID | 17436 |
Feature activation | -6.50e+00 |
Pos logit contributions | |
leys | +0.152 |
luaj | +0.147 |
bri | +0.142 |
nen | +0.141 |
jin | +0.139 |
Neg logit contributions | |
gdala | -0.234 |
ICAN | -0.195 |
amination | -0.189 |
Magikarp | -0.188 |
INE | -0.186 |
Token | Action |
Token ID | 7561 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
gdala | +3.856 |
ICAN | +2.991 |
amination | +2.870 |
INE | +2.847 |
Magikarp | +2.758 |
Neg logit contributions | |
leys | -6.145 |
luaj | -6.062 |
ahime | -5.945 |
bri | -5.898 |
igans | -5.867 |
Token | for |
Token ID | 329 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
gdala | +3.038 |
ICAN | +2.413 |
amination | +2.360 |
INE | +2.299 |
Magikarp | +2.262 |
Neg logit contributions | |
leys | -3.419 |
luaj | -3.391 |
nen | -3.274 |
bri | -3.265 |
igans | -3.193 |
Token | Childhood |
Token ID | 40992 |
Feature activation | -6.56e+00 |
Pos logit contributions | |
leys | +0.540 |
luaj | +0.537 |
bri | +0.530 |
nen | +0.521 |
ahime | +0.516 |
Neg logit contributions | |
gdala | -0.415 |
ICAN | -0.331 |
amination | -0.312 |
INE | -0.307 |
Magikarp | -0.304 |
Token | Arri |
Token ID | 27350 |
Feature activation | -9.68e+00 |
Pos logit contributions | |
gdala | +3.318 |
ICAN | +2.433 |
INE | +2.309 |
amination | +2.273 |
Magikarp | +2.196 |
Neg logit contributions | |
luaj | -6.877 |
leys | -6.723 |
ahime | -6.714 |
bri | -6.667 |
oshenko | -6.495 |
Token | vals |
Token ID | 12786 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
gdala | +6.121 |
amination | +4.711 |
ICAN | +4.482 |
INE | +4.311 |
renheit | +4.188 |
Neg logit contributions | |
luaj | -8.649 |
bri | -8.641 |
leys | -8.564 |
oshenko | -8.356 |
tyr | -8.328 |
Token | ( |
Token ID | 357 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
gdala | +3.352 |
ICAN | +2.748 |
amination | +2.586 |
INE | +2.578 |
coinc | +2.501 |
Neg logit contributions | |
luaj | -3.607 |
leys | -3.592 |
bri | -3.420 |
ahime | -3.409 |
nen | -3.393 |
Token | D |
Token ID | 35 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
gdala | +0.010 |
ICAN | +0.008 |
amination | +0.008 |
Magikarp | +0.007 |
INE | +0.007 |
Neg logit contributions | |
leys | -0.011 |
luaj | -0.011 |
bri | -0.010 |
nen | -0.010 |
jin | -0.010 |
Token | ACA |
Token ID | 26576 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
gdala | +2.938 |
ICAN | +2.537 |
amination | +2.448 |
INE | +2.437 |
renheit | +2.324 |
Neg logit contributions | |
luaj | -1.762 |
leys | -1.750 |
bri | -1.733 |
nen | -1.656 |
ahime | -1.648 |
Token | ) |
Token ID | 8 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
gdala | +3.937 |
ICAN | +3.185 |
amination | +3.012 |
INE | +2.997 |
renheit | +2.936 |
Neg logit contributions | |
luaj | -4.489 |
leys | -4.485 |
bri | -4.294 |
ahime | -4.287 |
nen | -4.278 |
Token | when |
Token ID | 618 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
gdala | +0.441 |
ICAN | +0.365 |
amination | +0.351 |
INE | +0.348 |
Magikarp | +0.347 |
Neg logit contributions | |
leys | -0.350 |
luaj | -0.342 |
bri | -0.333 |
nen | -0.327 |
ahime | -0.322 |
Token | astronomers |
Token ID | 33162 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
gdala | +0.083 |
ICAN | +0.067 |
amination | +0.064 |
INE | +0.063 |
Magikarp | +0.063 |
Neg logit contributions | |
leys | -0.082 |
luaj | -0.080 |
bri | -0.078 |
nen | -0.077 |
ahime | -0.076 |
Token | launched |
Token ID | 5611 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
gdala | +3.946 |
ICAN | +3.171 |
coinc | +3.141 |
INE | +3.084 |
amination | +3.069 |
Neg logit contributions | |
luaj | -3.413 |
leys | -3.398 |
ahime | -3.260 |
nen | -3.251 |
bri | -3.187 |
Token | the |
Token ID | 262 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
gdala | +3.246 |
ICAN | +2.622 |
amination | +2.549 |
INE | +2.500 |
Magikarp | +2.460 |
Neg logit contributions | |
leys | -3.167 |
luaj | -3.124 |
nen | -2.997 |
bri | -2.980 |
ahime | -2.967 |
Token | third |
Token ID | 2368 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
gdala | +0.011 |
ICAN | +0.009 |
amination | +0.008 |
INE | +0.008 |
Magikarp | +0.008 |
Neg logit contributions | |
leys | -0.010 |
luaj | -0.009 |
bri | -0.009 |
nen | -0.009 |
igans | -0.009 |
Token | Grav |
Token ID | 32599 |
Feature activation | -9.59e+00 |
Pos logit contributions | |
leys | +1.796 |
luaj | +1.759 |
bri | +1.716 |
nen | +1.687 |
jin | +1.666 |
Neg logit contributions | |
gdala | -2.095 |
ICAN | -1.705 |
amination | -1.648 |
Magikarp | -1.626 |
INE | -1.619 |
Token | itational |
Token ID | 22181 |
Feature activation | -6.80e+00 |
Pos logit contributions | |
gdala | +4.601 |
ICAN | +3.624 |
INE | +3.243 |
amination | +3.162 |
ithmetic | +2.941 |
Neg logit contributions | |
luaj | -9.752 |
leys | -9.737 |
bri | -9.573 |
nen | -9.573 |
oshenko | -9.382 |
Token | L |
Token ID | 406 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
gdala | +5.169 |
ICAN | +4.223 |
amination | +4.015 |
coinc | +4.003 |
INE | +4.002 |
Neg logit contributions | |
luaj | -5.412 |
leys | -5.372 |
nen | -5.201 |
ahime | -5.102 |
oshenko | -5.090 |
Token | ensing |
Token ID | 26426 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
gdala | +2.878 |
ICAN | +2.340 |
amination | +2.331 |
INE | +2.229 |
Magikarp | +2.179 |
Neg logit contributions | |
luaj | -2.853 |
leys | -2.833 |
bri | -2.732 |
nen | -2.701 |
ahime | -2.668 |
Token | Accuracy |
Token ID | 33222 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
gdala | +2.355 |
ICAN | +1.837 |
amination | +1.745 |
INE | +1.744 |
coinc | +1.699 |
Neg logit contributions | |
leys | -2.956 |
luaj | -2.955 |
nen | -2.846 |
bri | -2.826 |
ahime | -2.809 |
Token | Testing |
Token ID | 23983 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
gdala | +1.537 |
ICAN | +1.240 |
amination | +1.187 |
INE | +1.177 |
Magikarp | +1.154 |
Neg logit contributions | |
leys | -1.532 |
luaj | -1.521 |
bri | -1.465 |
nen | -1.459 |
ahime | -1.436 |
Token |
|
Token ID | 198 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
leys | +0.175 |
luaj | +0.171 |
bri | +0.166 |
nen | +0.163 |
jin | +0.160 |
Neg logit contributions | |
gdala | -0.254 |
ICAN | -0.212 |
amination | -0.205 |
INE | -0.203 |
Magikarp | -0.202 |
Token |
|
Token ID | 198 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
leys | +0.131 |
luaj | +0.127 |
bri | +0.124 |
nen | +0.122 |
jin | +0.120 |
Neg logit contributions | |
gdala | -0.188 |
ICAN | -0.156 |
amination | -0.152 |
Magikarp | -0.150 |
INE | -0.149 |
Token | Sign |
Token ID | 11712 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
leys | +0.207 |
luaj | +0.204 |
bri | +0.200 |
nen | +0.196 |
ahime | +0.193 |
Neg logit contributions | |
gdala | -0.238 |
ICAN | -0.196 |
amination | -0.187 |
INE | -0.187 |
Magikarp | -0.186 |
Token | up |
Token ID | 510 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
gdala | +0.926 |
ICAN | +0.725 |
amination | +0.702 |
INE | +0.687 |
Magikarp | +0.676 |
Neg logit contributions | |
leys | -1.171 |
luaj | -1.156 |
bri | -1.121 |
nen | -1.112 |
ahime | -1.097 |
Token | for |
Token ID | 329 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
gdala | +1.292 |
ICAN | +1.026 |
amination | +0.996 |
INE | +0.983 |
Magikarp | +0.973 |
Neg logit contributions | |
leys | -1.316 |
luaj | -1.305 |
bri | -1.254 |
nen | -1.239 |
ahime | -1.233 |
Token | BRE |
Token ID | 29377 |
Feature activation | -9.45e+00 |
Pos logit contributions | |
leys | +1.463 |
luaj | +1.432 |
bri | +1.403 |
nen | +1.383 |
jin | +1.367 |
Neg logit contributions | |
gdala | -1.397 |
ICAN | -1.113 |
amination | -1.071 |
Magikarp | -1.054 |
INE | -1.046 |
Token | AKING |
Token ID | 43602 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
gdala | +2.325 |
ICAN | +1.115 |
INE | +0.773 |
Magikarp | +0.567 |
renheit | +0.562 |
Neg logit contributions | |
bri | -12.181 |
leys | -12.154 |
luaj | -12.141 |
ahime | -12.040 |
oshenko | -11.926 |
Token | NEWS |
Token ID | 28840 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
gdala | +3.096 |
ICAN | +2.358 |
INE | +2.349 |
amination | +2.213 |
coinc | +2.205 |
Neg logit contributions | |
luaj | -4.729 |
leys | -4.537 |
ahime | -4.443 |
bri | -4.388 |
igans | -4.363 |
Token | Emails |
Token ID | 39617 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
gdala | +1.221 |
ICAN | +0.932 |
amination | +0.885 |
INE | +0.871 |
Magikarp | +0.865 |
Neg logit contributions | |
leys | -1.694 |
luaj | -1.670 |
bri | -1.635 |
nen | -1.612 |
jin | -1.598 |
Token | privacy |
Token ID | 6782 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
leys | +0.404 |
luaj | +0.390 |
bri | +0.376 |
nen | +0.367 |
jin | +0.360 |
Neg logit contributions | |
gdala | -0.807 |
ICAN | -0.686 |
amination | -0.666 |
INE | -0.664 |
Magikarp | -0.658 |
Token | policy |
Token ID | 2450 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
gdala | +0.521 |
ICAN | +0.405 |
amination | +0.393 |
coinc | +0.392 |
INE | +0.384 |
Neg logit contributions | |
leys | -0.633 |
luaj | -0.625 |
ahime | -0.604 |
nen | -0.592 |
igans | -0.588 |
Token | for |
Token ID | 329 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
gdala | +0.003 |
ICAN | +0.003 |
amination | +0.003 |
INE | +0.003 |
Magikarp | +0.003 |
Neg logit contributions | |
leys | -0.003 |
luaj | -0.003 |
bri | -0.003 |
nen | -0.003 |
jin | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
leys | +0.823 |
luaj | +0.810 |
bri | +0.780 |
nen | +0.770 |
jin | +0.761 |
Neg logit contributions | |
gdala | -0.966 |
ICAN | -0.792 |
amination | -0.762 |
INE | -0.751 |
Magikarp | -0.749 |
Token | comic |
Token ID | 9048 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
gdala | +0.302 |
ICAN | +0.250 |
amination | +0.239 |
INE | +0.237 |
Magikarp | +0.234 |
Neg logit contributions | |
leys | -0.266 |
luaj | -0.262 |
bri | -0.250 |
nen | -0.248 |
jin | -0.245 |
Token | . |
Token ID | 13 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
leys | +0.557 |
luaj | +0.547 |
bri | +0.532 |
nen | +0.524 |
jin | +0.517 |
Neg logit contributions | |
gdala | -0.623 |
ICAN | -0.506 |
amination | -0.488 |
INE | -0.480 |
Magikarp | -0.479 |
Token | Ex |
Token ID | 1475 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
gdala | +0.164 |
ICAN | +0.137 |
INE | +0.130 |
amination | +0.130 |
Magikarp | +0.130 |
Neg logit contributions | |
leys | -0.132 |
luaj | -0.130 |
bri | -0.126 |
nen | -0.123 |
ahime | -0.122 |
Token | ceptions |
Token ID | 11755 |
Feature activation | -9.12e+00 |
Pos logit contributions | |
gdala | +1.964 |
ICAN | +1.503 |
amination | +1.474 |
Magikarp | +1.402 |
INE | +1.399 |
Neg logit contributions | |
leys | -2.744 |
luaj | -2.707 |
bri | -2.642 |
nen | -2.623 |
jin | -2.573 |
Token | to |
Token ID | 284 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
gdala | +6.830 |
ICAN | +5.757 |
coinc | +5.569 |
amination | +5.530 |
INE | +5.425 |
Neg logit contributions | |
luaj | -6.929 |
leys | -6.791 |
nen | -6.558 |
ahime | -6.520 |
oshenko | -6.385 |
Token | this |
Token ID | 428 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
gdala | +1.926 |
ICAN | +1.608 |
amination | +1.521 |
INE | +1.513 |
Magikarp | +1.499 |
Neg logit contributions | |
luaj | -1.715 |
leys | -1.703 |
nen | -1.613 |
bri | -1.603 |
ahime | -1.593 |
Token | include |
Token ID | 2291 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
leys | +0.842 |
luaj | +0.829 |
bri | +0.801 |
nen | +0.794 |
jin | +0.778 |
Neg logit contributions | |
gdala | -0.995 |
ICAN | -0.815 |
amination | -0.788 |
INE | -0.775 |
Magikarp | -0.774 |
Token | " |
Token ID | 366 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
gdala | +2.108 |
ICAN | +1.729 |
Magikarp | +1.656 |
amination | +1.652 |
INE | +1.651 |
Neg logit contributions | |
luaj | -1.934 |
leys | -1.922 |
bri | -1.813 |
nen | -1.809 |
ahime | -1.785 |
Token | The |
Token ID | 464 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
gdala | +1.202 |
ICAN | +0.987 |
Magikarp | +0.945 |
amination | +0.941 |
INE | +0.934 |
Neg logit contributions | |
leys | -1.089 |
luaj | -1.073 |
bri | -1.053 |
nen | -1.022 |
ahime | -1.011 |
Token | and |
Token ID | 290 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
gdala | +1.272 |
ICAN | +0.995 |
amination | +0.960 |
INE | +0.932 |
Magikarp | +0.926 |
Neg logit contributions | |
leys | -1.530 |
luaj | -1.504 |
bri | -1.473 |
nen | -1.449 |
jin | -1.435 |
Token | Creative |
Token ID | 17404 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
leys | +0.336 |
luaj | +0.333 |
bri | +0.323 |
nen | +0.316 |
ahime | +0.312 |
Neg logit contributions | |
gdala | -0.420 |
ICAN | -0.347 |
amination | -0.336 |
INE | -0.332 |
Magikarp | -0.330 |
Token | Technology |
Token ID | 8987 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
leys | +0.030 |
luaj | +0.030 |
bri | +0.029 |
nen | +0.028 |
jin | +0.028 |
Neg logit contributions | |
gdala | -0.038 |
ICAN | -0.031 |
amination | -0.030 |
Magikarp | -0.030 |
INE | -0.030 |
Token | ( |
Token ID | 357 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
leys | +1.731 |
luaj | +1.698 |
bri | +1.647 |
nen | +1.623 |
jin | +1.600 |
Neg logit contributions | |
gdala | -2.127 |
ICAN | -1.747 |
amination | -1.687 |
INE | -1.660 |
Magikarp | -1.659 |
Token | F |
Token ID | 37 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
gdala | +0.194 |
ICAN | +0.152 |
amination | +0.144 |
INE | +0.142 |
Magikarp | +0.141 |
Neg logit contributions | |
leys | -0.250 |
luaj | -0.246 |
bri | -0.241 |
nen | -0.238 |
jin | -0.235 |
Token | ACT |
Token ID | 10659 |
Feature activation | -9.08e+00 |
Pos logit contributions | |
gdala | +2.219 |
ICAN | +1.723 |
amination | +1.614 |
INE | +1.600 |
Magikarp | +1.519 |
Neg logit contributions | |
luaj | -3.210 |
leys | -3.199 |
bri | -3.100 |
jin | -3.043 |
nen | -3.037 |
Token | ) |
Token ID | 8 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
gdala | +6.029 |
ICAN | +5.236 |
INE | +4.883 |
amination | +4.815 |
renheit | +4.758 |
Neg logit contributions | |
luaj | -7.688 |
leys | -7.484 |
bri | -7.374 |
nen | -7.253 |
igans | -7.243 |
Token | building |
Token ID | 2615 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
leys | +0.087 |
luaj | +0.085 |
bri | +0.082 |
nen | +0.082 |
jin | +0.080 |
Neg logit contributions | |
gdala | -0.092 |
ICAN | -0.076 |
amination | -0.072 |
INE | -0.071 |
Magikarp | -0.071 |
Token | in |
Token ID | 287 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
gdala | +2.283 |
ICAN | +1.813 |
amination | +1.749 |
coinc | +1.743 |
INE | +1.727 |
Neg logit contributions | |
leys | -2.507 |
luaj | -2.495 |
nen | -2.363 |
bri | -2.357 |
ahime | -2.345 |
Token | Liverpool |
Token ID | 11761 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
gdala | +0.843 |
ICAN | +0.679 |
amination | +0.660 |
INE | +0.645 |
Magikarp | +0.644 |
Neg logit contributions | |
leys | -0.781 |
luaj | -0.772 |
bri | -0.745 |
nen | -0.736 |
jin | -0.726 |
Token | , |
Token ID | 11 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
leys | +1.725 |
luaj | +1.693 |
bri | +1.647 |
nen | +1.622 |
jin | +1.600 |
Neg logit contributions | |
gdala | -1.969 |
ICAN | -1.602 |
amination | -1.545 |
Magikarp | -1.520 |
INE | -1.520 |
Token | o |
Token ID | 78 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
gdala | +0.737 |
ICAN | +0.571 |
amination | +0.547 |
INE | +0.545 |
Magikarp | +0.530 |
Neg logit contributions | |
leys | -0.957 |
luaj | -0.934 |
bri | -0.927 |
nen | -0.909 |
jin | -0.897 |
Token | Tre |
Token ID | 4700 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
gdala | +0.188 |
ICAN | +0.152 |
amination | +0.147 |
INE | +0.144 |
Magikarp | +0.144 |
Neg logit contributions | |
leys | -0.175 |
luaj | -0.171 |
bri | -0.167 |
nen | -0.164 |
jin | -0.162 |
Token | u |
Token ID | 84 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
gdala | +1.717 |
ICAN | +1.399 |
amination | +1.357 |
INE | +1.319 |
renheit | +1.304 |
Neg logit contributions | |
leys | -1.463 |
luaj | -1.452 |
bri | -1.410 |
nen | -1.374 |
ahime | -1.357 |
Token | , |
Token ID | 11 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
leys | +1.823 |
luaj | +1.778 |
bri | +1.733 |
nen | +1.709 |
jin | +1.691 |
Neg logit contributions | |
gdala | -2.218 |
ICAN | -1.817 |
amination | -1.755 |
Magikarp | -1.735 |
INE | -1.725 |
Token | an |
Token ID | 281 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
leys | +0.240 |
luaj | +0.235 |
bri | +0.227 |
nen | +0.224 |
jin | +0.221 |
Neg logit contributions | |
gdala | -0.280 |
ICAN | -0.230 |
amination | -0.223 |
INE | -0.219 |
Magikarp | -0.217 |
Token | astroph |
Token ID | 48782 |
Feature activation | -9.04e+00 |
Pos logit contributions | |
gdala | +0.214 |
ICAN | +0.165 |
amination | +0.158 |
INE | +0.154 |
Magikarp | +0.154 |
Neg logit contributions | |
leys | -0.290 |
luaj | -0.285 |
bri | -0.279 |
nen | -0.277 |
jin | -0.272 |
Token | ys |
Token ID | 893 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
gdala | +6.409 |
ICAN | +5.214 |
amination | +5.202 |
INE | +4.823 |
ithmetic | +4.727 |
Neg logit contributions | |
luaj | -7.232 |
leys | -7.178 |
bri | -7.071 |
ahime | -6.976 |
nen | -6.896 |
Token | icist |
Token ID | 48187 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
leys | +0.039 |
luaj | +0.038 |
bri | +0.037 |
nen | +0.037 |
ahime | +0.036 |
Neg logit contributions | |
gdala | -0.032 |
ICAN | -0.025 |
amination | -0.024 |
INE | -0.023 |
Magikarp | -0.023 |
Token | at |
Token ID | 379 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
gdala | +2.519 |
ICAN | +1.981 |
amination | +1.923 |
INE | +1.910 |
coinc | +1.882 |
Neg logit contributions | |
leys | -2.666 |
luaj | -2.637 |
bri | -2.560 |
ahime | -2.518 |
nen | -2.485 |
Token | the |
Token ID | 262 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
leys | +0.284 |
luaj | +0.279 |
bri | +0.272 |
nen | +0.268 |
jin | +0.265 |
Neg logit contributions | |
gdala | -0.289 |
ICAN | -0.232 |
amination | -0.224 |
Magikarp | -0.220 |
INE | -0.219 |
Token | University |
Token ID | 2059 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
gdala | +0.500 |
ICAN | +0.404 |
amination | +0.385 |
INE | +0.382 |
Magikarp | +0.375 |
Neg logit contributions | |
leys | -0.542 |
luaj | -0.531 |
bri | -0.518 |
nen | -0.514 |
ahime | -0.506 |
Token | - |
Token ID | 12 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
leys | +0.153 |
luaj | +0.149 |
bri | +0.144 |
nen | +0.141 |
jin | +0.139 |
Neg logit contributions | |
gdala | -0.221 |
ICAN | -0.184 |
amination | -0.180 |
INE | -0.176 |
Magikarp | -0.175 |
Token | lot |
Token ID | 26487 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
gdala | +1.229 |
ICAN | +1.013 |
amination | +0.973 |
INE | +0.959 |
Magikarp | +0.956 |
Neg logit contributions | |
leys | -1.097 |
luaj | -1.063 |
bri | -1.049 |
nen | -1.017 |
ahime | -1.013 |
Token | tery |
Token ID | 11471 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
gdala | +2.056 |
ICAN | +1.671 |
amination | +1.637 |
INE | +1.572 |
Magikarp | +1.552 |
Neg logit contributions | |
leys | -1.955 |
luaj | -1.917 |
bri | -1.860 |
nen | -1.823 |
ahime | -1.818 |
Token | official |
Token ID | 1743 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
gdala | +2.484 |
ICAN | +2.028 |
amination | +1.987 |
INE | +1.957 |
coinc | +1.921 |
Neg logit contributions | |
leys | -2.151 |
luaj | -2.115 |
ahime | -1.991 |
nen | -1.980 |
bri | -1.977 |
Token | , |
Token ID | 11 |
Feature activation | +8.33e-02 |
Pos logit contributions | |
gdala | +1.226 |
ICAN | +0.999 |
amination | +0.972 |
INE | +0.957 |
Magikarp | +0.949 |
Neg logit contributions | |
leys | -1.034 |
luaj | -1.010 |
bri | -0.979 |
nen | -0.957 |
ahime | -0.951 |
Token | coinc |
Token ID | 11194 |
Feature activation | -8.85e+00 |
Pos logit contributions | |
leys | +0.061 |
luaj | +0.060 |
bri | +0.058 |
nen | +0.057 |
ahime | +0.056 |
Neg logit contributions | |
gdala | -0.073 |
ICAN | -0.060 |
amination | -0.058 |
Magikarp | -0.057 |
INE | -0.057 |
Token | iding |
Token ID | 2530 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
gdala | +5.944 |
amination | +4.829 |
coinc | +4.718 |
ICAN | +4.638 |
INE | +4.534 |
Neg logit contributions | |
luaj | -7.385 |
leys | -7.318 |
bri | -7.155 |
ahime | -7.124 |
nen | -6.960 |
Token | with |
Token ID | 351 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
gdala | +3.530 |
ICAN | +2.830 |
amination | +2.754 |
INE | +2.723 |
coinc | +2.701 |
Neg logit contributions | |
leys | -3.624 |
luaj | -3.589 |
bri | -3.443 |
ahime | -3.429 |
nen | -3.422 |
Token | a |
Token ID | 257 |
Feature activation | -8.61e-02 |
Pos logit contributions | |
gdala | +0.636 |
ICAN | +0.516 |
amination | +0.498 |
Magikarp | +0.488 |
INE | +0.488 |
Neg logit contributions | |
leys | -0.596 |
luaj | -0.585 |
bri | -0.566 |
nen | -0.559 |
ahime | -0.554 |
Token | wave |
Token ID | 6769 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
gdala | +0.078 |
ICAN | +0.065 |
amination | +0.063 |
INE | +0.061 |
coinc | +0.061 |
Neg logit contributions | |
leys | -0.060 |
luaj | -0.059 |
bri | -0.056 |
nen | -0.056 |
ahime | -0.055 |
Token | of |
Token ID | 286 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
gdala | +2.663 |
ICAN | +2.142 |
amination | +2.058 |
Magikarp | +2.024 |
INE | +2.021 |
Neg logit contributions | |
leys | -2.789 |
luaj | -2.737 |
bri | -2.670 |
nen | -2.631 |
ahime | -2.590 |
Token | P |
Token ID | 47 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
gdala | +1.591 |
ICAN | +1.259 |
amination | +1.193 |
INE | +1.187 |
Magikarp | +1.178 |
Neg logit contributions | |
leys | -1.849 |
luaj | -1.820 |
bri | -1.785 |
nen | -1.748 |
jin | -1.728 |
Token | ORTS |
Token ID | 33002 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
gdala | +0.253 |
ICAN | +0.175 |
amination | +0.165 |
Magikarp | +0.161 |
INE | +0.155 |
Neg logit contributions | |
leys | -0.517 |
luaj | -0.507 |
bri | -0.499 |
nen | -0.495 |
jin | -0.490 |
Token | 100 |
Token ID | 1802 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
gdala | +0.377 |
ICAN | +0.305 |
INE | +0.291 |
amination | +0.290 |
Magikarp | +0.284 |
Neg logit contributions | |
leys | -0.357 |
luaj | -0.353 |
bri | -0.340 |
nen | -0.337 |
jin | -0.331 |
Token | % |
Token ID | 4 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
leys | +1.820 |
luaj | +1.782 |
nen | +1.739 |
bri | +1.727 |
jin | +1.723 |
Neg logit contributions | |
gdala | -1.931 |
ICAN | -1.524 |
amination | -1.522 |
Magikarp | -1.474 |
renheit | -1.466 |
Token | EX |
Token ID | 7788 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
leys | +0.725 |
luaj | +0.712 |
bri | +0.698 |
nen | +0.689 |
jin | +0.681 |
Neg logit contributions | |
gdala | -0.562 |
ICAN | -0.434 |
amination | -0.415 |
Magikarp | -0.407 |
INE | -0.404 |
Token | CEPT |
Token ID | 42006 |
Feature activation | -8.84e+00 |
Pos logit contributions | |
gdala | +2.106 |
ICAN | +1.667 |
amination | +1.561 |
INE | +1.556 |
Magikarp | +1.495 |
Neg logit contributions | |
leys | -2.958 |
luaj | -2.922 |
bri | -2.847 |
nen | -2.812 |
igans | -2.779 |
Token | THE |
Token ID | 3336 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
gdala | +6.483 |
ICAN | +5.488 |
INE | +5.396 |
amination | +5.039 |
coinc | +4.925 |
Neg logit contributions | |
luaj | -7.065 |
leys | -6.858 |
nen | -6.647 |
bri | -6.591 |
oshenko | -6.534 |
Token | SOLD |
Token ID | 48671 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
gdala | +0.511 |
ICAN | +0.415 |
amination | +0.395 |
INE | +0.394 |
Magikarp | +0.387 |
Neg logit contributions | |
leys | -0.492 |
luaj | -0.485 |
bri | -0.472 |
nen | -0.464 |
jin | -0.457 |
Token | IER |
Token ID | 38311 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
gdala | +1.107 |
ICAN | +0.819 |
INE | +0.748 |
amination | +0.730 |
Magikarp | +0.713 |
Neg logit contributions | |
leys | -2.152 |
luaj | -2.132 |
bri | -2.083 |
nen | -2.057 |
jin | -2.042 |
Token | THAT |
Token ID | 14603 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
gdala | +1.168 |
ICAN | +0.946 |
INE | +0.913 |
amination | +0.902 |
Magikarp | +0.874 |
Neg logit contributions | |
leys | -1.122 |
luaj | -1.119 |
bri | -1.078 |
nen | -1.061 |
jin | -1.049 |
Token | IS |
Token ID | 3180 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
gdala | +1.071 |
ICAN | +0.873 |
INE | +0.838 |
amination | +0.821 |
Magikarp | +0.801 |
Neg logit contributions | |
leys | -1.018 |
luaj | -1.011 |
bri | -0.974 |
nen | -0.963 |
jin | -0.952 |
Token | ² |
Token ID | 31185 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
leys | +0.789 |
luaj | +0.779 |
bri | +0.759 |
nen | +0.753 |
jin | +0.744 |
Neg logit contributions | |
gdala | -0.624 |
ICAN | -0.482 |
amination | -0.459 |
Magikarp | -0.454 |
INE | -0.448 |
Token | ) |
Token ID | 8 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
gdala | +1.479 |
ICAN | +1.203 |
amination | +1.159 |
INE | +1.145 |
Magikarp | +1.132 |
Neg logit contributions | |
leys | -1.351 |
luaj | -1.329 |
bri | -1.285 |
nen | -1.270 |
ahime | -1.249 |
Token | and |
Token ID | 290 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
gdala | +0.098 |
ICAN | +0.080 |
amination | +0.077 |
INE | +0.076 |
Magikarp | +0.076 |
Neg logit contributions | |
leys | -0.087 |
luaj | -0.086 |
bri | -0.083 |
nen | -0.082 |
jin | -0.080 |
Token | obesity |
Token ID | 13825 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
gdala | +0.256 |
ICAN | +0.205 |
amination | +0.199 |
INE | +0.197 |
Magikarp | +0.194 |
Neg logit contributions | |
leys | -0.249 |
luaj | -0.244 |
bri | -0.235 |
nen | -0.234 |
jin | -0.229 |
Token | ( |
Token ID | 357 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
gdala | +1.848 |
ICAN | +1.476 |
amination | +1.427 |
INE | +1.413 |
Magikarp | +1.388 |
Neg logit contributions | |
leys | -1.899 |
luaj | -1.869 |
bri | -1.797 |
nen | -1.795 |
igans | -1.754 |
Token | � |
Token ID | 35705 |
Feature activation | -8.75e+00 |
Pos logit contributions | |
gdala | +0.194 |
ICAN | +0.154 |
amination | +0.147 |
INE | +0.145 |
Magikarp | +0.144 |
Neg logit contributions | |
leys | -0.224 |
luaj | -0.220 |
bri | -0.216 |
nen | -0.213 |
jin | -0.209 |
Token | � |
Token ID | 98 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
gdala | +4.640 |
ICAN | +3.507 |
amination | +3.334 |
INE | +3.229 |
Magikarp | +2.997 |
Neg logit contributions | |
leys | -8.830 |
luaj | -8.720 |
nen | -8.562 |
bri | -8.359 |
ahime | -8.306 |
Token | 30 |
Token ID | 1270 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
gdala | +2.758 |
ICAN | +2.288 |
INE | +2.211 |
amination | +2.196 |
Magikarp | +2.174 |
Neg logit contributions | |
leys | -2.361 |
luaj | -2.309 |
bri | -2.228 |
nen | -2.207 |
oshenko | -2.163 |
Token | kg |
Token ID | 14211 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
gdala | +0.256 |
ICAN | +0.205 |
amination | +0.198 |
INE | +0.195 |
Magikarp | +0.194 |
Neg logit contributions | |
leys | -0.250 |
luaj | -0.245 |
bri | -0.238 |
nen | -0.236 |
jin | -0.233 |
Token | / |
Token ID | 14 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
leys | +1.175 |
luaj | +1.154 |
bri | +1.135 |
nen | +1.110 |
jin | +1.101 |
Neg logit contributions | |
gdala | -1.237 |
ICAN | -1.000 |
amination | -0.960 |
Magikarp | -0.951 |
INE | -0.940 |
Token | m |
Token ID | 76 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
gdala | +0.404 |
ICAN | +0.325 |
amination | +0.314 |
Magikarp | +0.308 |
INE | +0.308 |
Neg logit contributions | |
leys | -0.389 |
luaj | -0.381 |
bri | -0.373 |
nen | -0.366 |
jin | -0.361 |
Token | MRI |
Token ID | 30278 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
gdala | +0.655 |
ICAN | +0.531 |
amination | +0.521 |
INE | +0.509 |
Magikarp | +0.504 |
Neg logit contributions | |
leys | -0.611 |
luaj | -0.604 |
bri | -0.574 |
nen | -0.572 |
jin | -0.568 |
Token | machines |
Token ID | 8217 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
gdala | +2.169 |
ICAN | +1.755 |
amination | +1.706 |
INE | +1.700 |
Magikarp | +1.646 |
Neg logit contributions | |
leys | -2.139 |
luaj | -2.130 |
bri | -2.024 |
nen | -2.002 |
ahime | -2.000 |
Token | and |
Token ID | 290 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
leys | +0.872 |
luaj | +0.854 |
bri | +0.831 |
nen | +0.818 |
jin | +0.807 |
Neg logit contributions | |
gdala | -1.036 |
ICAN | -0.846 |
amination | -0.818 |
Magikarp | -0.805 |
INE | -0.804 |
Token | complex |
Token ID | 3716 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
leys | +0.356 |
luaj | +0.350 |
bri | +0.339 |
nen | +0.335 |
jin | +0.331 |
Neg logit contributions | |
gdala | -0.390 |
ICAN | -0.316 |
amination | -0.307 |
INE | -0.301 |
Magikarp | -0.300 |
Token | particle |
Token ID | 18758 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
leys | +2.472 |
luaj | +2.405 |
bri | +2.372 |
nen | +2.325 |
jin | +2.290 |
Neg logit contributions | |
gdala | -2.668 |
ICAN | -2.157 |
amination | -2.057 |
Magikarp | -2.051 |
INE | -2.027 |
Token | acceler |
Token ID | 8320 |
Feature activation | -8.74e+00 |
Pos logit contributions | |
gdala | +2.922 |
ICAN | +2.300 |
amination | +2.262 |
INE | +2.199 |
coinc | +2.170 |
Neg logit contributions | |
luaj | -3.565 |
leys | -3.532 |
nen | -3.355 |
ahime | -3.352 |
bri | -3.339 |
Token | ators |
Token ID | 2024 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
gdala | +5.602 |
amination | +4.671 |
ICAN | +4.279 |
INE | +4.203 |
coinc | +4.068 |
Neg logit contributions | |
luaj | -7.752 |
leys | -7.483 |
ahime | -7.440 |
nen | -7.334 |
bri | -7.304 |
Token | , |
Token ID | 11 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
gdala | +1.333 |
ICAN | +1.080 |
amination | +1.053 |
INE | +1.036 |
coinc | +1.018 |
Neg logit contributions | |
leys | -1.229 |
luaj | -1.217 |
bri | -1.165 |
nen | -1.153 |
jin | -1.139 |
Token | but |
Token ID | 475 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
leys | +0.083 |
luaj | +0.081 |
bri | +0.079 |
nen | +0.078 |
jin | +0.076 |
Neg logit contributions | |
gdala | -0.094 |
ICAN | -0.077 |
amination | -0.074 |
Magikarp | -0.073 |
INE | -0.073 |
Token | the |
Token ID | 262 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
gdala | +2.661 |
ICAN | +2.145 |
amination | +2.126 |
INE | +2.093 |
coinc | +2.087 |
Neg logit contributions | |
leys | -2.632 |
luaj | -2.630 |
ahime | -2.496 |
bri | -2.496 |
nen | -2.467 |
Token | cost |
Token ID | 1575 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
gdala | +0.530 |
ICAN | +0.432 |
amination | +0.422 |
INE | +0.412 |
Magikarp | +0.410 |
Neg logit contributions | |
leys | -0.485 |
luaj | -0.478 |
bri | -0.458 |
nen | -0.456 |
jin | -0.448 |
Token | behavior |
Token ID | 4069 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
gdala | +0.497 |
ICAN | +0.362 |
amination | +0.347 |
INE | +0.339 |
Magikarp | +0.339 |
Neg logit contributions | |
leys | -0.777 |
luaj | -0.765 |
bri | -0.742 |
nen | -0.734 |
igans | -0.732 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
leys | +0.686 |
luaj | +0.667 |
bri | +0.656 |
nen | +0.645 |
jin | +0.638 |
Neg logit contributions | |
gdala | -0.757 |
ICAN | -0.616 |
amination | -0.592 |
Magikarp | -0.584 |
INE | -0.581 |
Token | By |
Token ID | 2750 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
gdala | +0.936 |
ICAN | +0.772 |
amination | +0.745 |
INE | +0.741 |
Magikarp | +0.730 |
Neg logit contributions | |
leys | -0.692 |
luaj | -0.682 |
bri | -0.662 |
nen | -0.646 |
ahime | -0.639 |
Token | contrast |
Token ID | 6273 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
leys | +1.582 |
luaj | +1.546 |
bri | +1.509 |
nen | +1.486 |
jin | +1.466 |
Neg logit contributions | |
gdala | -1.868 |
ICAN | -1.528 |
amination | -1.473 |
Magikarp | -1.453 |
INE | -1.447 |
Token | , |
Token ID | 11 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
gdala | +0.531 |
ICAN | +0.437 |
amination | +0.424 |
Magikarp | +0.417 |
INE | +0.417 |
Neg logit contributions | |
leys | -0.409 |
luaj | -0.400 |
bri | -0.389 |
nen | -0.382 |
jin | -0.377 |
Token | flu |
Token ID | 6562 |
Feature activation | -8.65e+00 |
Pos logit contributions | |
gdala | +1.217 |
ICAN | +0.973 |
amination | +0.954 |
INE | +0.940 |
Magikarp | +0.925 |
Neg logit contributions | |
leys | -1.169 |
luaj | -1.158 |
bri | -1.115 |
nen | -1.100 |
jin | -1.092 |
Token | ox |
Token ID | 1140 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
gdala | +4.995 |
amination | +3.773 |
ICAN | +3.589 |
INE | +3.464 |
renheit | +3.412 |
Neg logit contributions | |
bri | -8.402 |
leys | -8.235 |
luaj | -8.203 |
igans | -7.966 |
nen | -7.929 |
Token | et |
Token ID | 316 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
gdala | +2.628 |
ICAN | +2.128 |
amination | +2.104 |
INE | +2.047 |
Magikarp | +2.012 |
Neg logit contributions | |
leys | -2.107 |
luaj | -2.098 |
bri | -2.055 |
nen | -1.996 |
igans | -1.964 |
Token | ine |
Token ID | 500 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
gdala | +1.808 |
ICAN | +1.364 |
amination | +1.325 |
INE | +1.318 |
Magikarp | +1.257 |
Neg logit contributions | |
leys | -2.619 |
luaj | -2.597 |
bri | -2.550 |
nen | -2.502 |
jin | -2.468 |
Token | ( |
Token ID | 357 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
gdala | +0.021 |
ICAN | +0.017 |
amination | +0.016 |
INE | +0.016 |
Magikarp | +0.016 |
Neg logit contributions | |
leys | -0.018 |
luaj | -0.018 |
bri | -0.017 |
nen | -0.017 |
jin | -0.017 |
Token | 30 |
Token ID | 1270 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
gdala | +1.132 |
ICAN | +0.934 |
amination | +0.903 |
INE | +0.894 |
Magikarp | +0.889 |
Neg logit contributions | |
leys | -0.927 |
luaj | -0.913 |
bri | -0.893 |
nen | -0.866 |
jin | -0.859 |
Token | Q |
Token ID | 48 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
gdala | +3.713 |
ICAN | +3.029 |
INE | +2.926 |
amination | +2.911 |
Magikarp | +2.882 |
Neg logit contributions | |
luaj | -3.274 |
leys | -3.265 |
bri | -3.112 |
oshenko | -3.078 |
nen | -3.078 |
Token | [ |
Token ID | 58 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
gdala | +1.579 |
ICAN | +1.262 |
amination | +1.233 |
INE | +1.222 |
Magikarp | +1.195 |
Neg logit contributions | |
leys | -1.478 |
luaj | -1.462 |
bri | -1.412 |
jin | -1.372 |
nen | -1.372 |
Token | step |
Token ID | 9662 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
gdala | +1.650 |
ICAN | +1.323 |
amination | +1.280 |
INE | +1.262 |
Magikarp | +1.253 |
Neg logit contributions | |
leys | -1.612 |
luaj | -1.588 |
bri | -1.549 |
nen | -1.516 |
oshenko | -1.498 |
Token | New |
Token ID | 3791 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
gdala | +2.451 |
ICAN | +1.979 |
amination | +1.923 |
INE | +1.893 |
Magikarp | +1.885 |
Neg logit contributions | |
leys | -2.250 |
luaj | -2.249 |
bri | -2.166 |
nen | -2.110 |
ahime | -2.094 |
Token | , |
Token ID | 11 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
gdala | +0.629 |
ICAN | +0.509 |
amination | +0.493 |
INE | +0.485 |
Magikarp | +0.484 |
Neg logit contributions | |
leys | -0.572 |
luaj | -0.566 |
bri | -0.549 |
nen | -0.536 |
jin | -0.531 |
Token | arrival |
Token ID | 10325 |
Feature activation | -8.63e+00 |
Pos logit contributions | |
gdala | +0.698 |
ICAN | +0.571 |
amination | +0.554 |
INE | +0.545 |
Magikarp | +0.543 |
Neg logit contributions | |
leys | -0.606 |
luaj | -0.595 |
bri | -0.577 |
nen | -0.566 |
jin | -0.558 |
Token | Location |
Token ID | 14749 |
Feature activation | -4.50e+00 |
Pos logit contributions | |
gdala | +6.797 |
ICAN | +5.461 |
INE | +5.321 |
Magikarp | +5.228 |
amination | +5.195 |
Neg logit contributions | |
luaj | -6.714 |
leys | -6.547 |
bri | -6.346 |
oshenko | -6.327 |
ahime | -6.190 |
Token | ] |
Token ID | 60 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
gdala | +3.694 |
ICAN | +2.978 |
INE | +2.894 |
amination | +2.854 |
Magikarp | +2.836 |
Neg logit contributions | |
luaj | -3.484 |
leys | -3.444 |
bri | -3.305 |
oshenko | -3.273 |
ahime | -3.223 |
Token | == |
Token ID | 6624 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
gdala | +0.158 |
ICAN | +0.128 |
amination | +0.123 |
INE | +0.122 |
Magikarp | +0.121 |
Neg logit contributions | |
leys | -0.148 |
luaj | -0.146 |
bri | -0.142 |
nen | -0.139 |
jin | -0.138 |
Token | False |
Token ID | 10352 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
gdala | +0.352 |
ICAN | +0.284 |
amination | +0.275 |
INE | +0.269 |
Magikarp | +0.269 |
Neg logit contributions | |
leys | -0.342 |
luaj | -0.335 |
bri | -0.324 |
nen | -0.321 |
jin | -0.316 |
Token | , |
Token ID | 11 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
leys | +0.516 |
luaj | +0.507 |
bri | +0.494 |
nen | +0.487 |
jin | +0.481 |
Neg logit contributions | |
gdala | -0.525 |
ICAN | -0.421 |
amination | -0.406 |
Magikarp | -0.399 |
INE | -0.398 |
Token | year |
Token ID | 614 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
leys | +0.427 |
luaj | +0.417 |
bri | +0.404 |
nen | +0.398 |
jin | +0.391 |
Neg logit contributions | |
gdala | -0.592 |
ICAN | -0.493 |
amination | -0.478 |
INE | -0.470 |
Magikarp | -0.470 |
Token | of |
Token ID | 286 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
gdala | +1.065 |
ICAN | +0.862 |
amination | +0.822 |
INE | +0.813 |
Magikarp | +0.809 |
Neg logit contributions | |
leys | -1.072 |
luaj | -1.053 |
bri | -1.022 |
nen | -1.004 |
jin | -0.994 |
Token | the |
Token ID | 262 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
leys | +0.244 |
luaj | +0.240 |
bri | +0.233 |
nen | +0.229 |
ahime | +0.226 |
Neg logit contributions | |
gdala | -0.266 |
ICAN | -0.216 |
amination | -0.208 |
INE | -0.205 |
Magikarp | -0.204 |
Token | first |
Token ID | 717 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
gdala | +0.599 |
ICAN | +0.496 |
amination | +0.477 |
Magikarp | +0.466 |
INE | +0.465 |
Neg logit contributions | |
leys | -0.520 |
luaj | -0.509 |
bri | -0.491 |
nen | -0.485 |
igans | -0.482 |
Token | lunar |
Token ID | 25572 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
gdala | +0.242 |
ICAN | +0.199 |
amination | +0.192 |
INE | +0.188 |
Magikarp | +0.187 |
Neg logit contributions | |
leys | -0.213 |
luaj | -0.208 |
bri | -0.202 |
nen | -0.198 |
igans | -0.196 |
Token | landing |
Token ID | 9581 |
Feature activation | -8.62e+00 |
Pos logit contributions | |
gdala | +1.879 |
ICAN | +1.553 |
amination | +1.507 |
INE | +1.488 |
coinc | +1.471 |
Neg logit contributions | |
leys | -1.451 |
luaj | -1.437 |
bri | -1.381 |
ahime | -1.360 |
nen | -1.357 |
Token | . |
Token ID | 13 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
gdala | +6.237 |
ICAN | +4.994 |
coinc | +4.949 |
INE | +4.822 |
amination | +4.795 |
Neg logit contributions | |
luaj | -7.131 |
leys | -7.059 |
ahime | -6.700 |
bri | -6.686 |
nen | -6.576 |
Token |
|
Token ID | 198 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
leys | +0.014 |
luaj | +0.014 |
bri | +0.013 |
nen | +0.013 |
jin | +0.013 |
Neg logit contributions | |
gdala | -0.019 |
ICAN | -0.016 |
amination | -0.015 |
INE | -0.015 |
Magikarp | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
gdala | +0.013 |
ICAN | +0.011 |
amination | +0.011 |
Magikarp | +0.010 |
INE | +0.010 |
Neg logit contributions | |
leys | -0.009 |
luaj | -0.009 |
bri | -0.009 |
nen | -0.008 |
jin | -0.008 |
Token | SP |
Token ID | 4303 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
gdala | +0.038 |
ICAN | +0.031 |
amination | +0.029 |
INE | +0.029 |
Magikarp | +0.029 |
Neg logit contributions | |
leys | -0.041 |
luaj | -0.040 |
bri | -0.040 |
nen | -0.039 |
igans | -0.038 |
Token | Y |
Token ID | 56 |
Feature activation | +7.93e-01 |
Pos logit contributions | |
gdala | +2.313 |
ICAN | +1.825 |
INE | +1.743 |
amination | +1.643 |
Magikarp | +1.611 |
Neg logit contributions | |
leys | -3.422 |
luaj | -3.382 |
bri | -3.308 |
nen | -3.236 |
oshenko | -3.211 |
Token |
|
Token ID | 198 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
leys | +0.173 |
luaj | +0.169 |
bri | +0.164 |
nen | +0.162 |
ahime | +0.159 |
Neg logit contributions | |
gdala | -0.218 |
ICAN | -0.180 |
amination | -0.173 |
INE | -0.172 |
Magikarp | -0.170 |
Token |
|
Token ID | 198 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
leys | +0.218 |
luaj | +0.212 |
bri | +0.205 |
nen | +0.203 |
jin | +0.200 |
Neg logit contributions | |
gdala | -0.326 |
ICAN | -0.271 |
amination | -0.264 |
Magikarp | -0.260 |
INE | -0.258 |
Token | Bl |
Token ID | 3629 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
leys | +0.277 |
luaj | +0.272 |
bri | +0.267 |
nen | +0.261 |
ahime | +0.258 |
Neg logit contributions | |
gdala | -0.299 |
ICAN | -0.243 |
amination | -0.234 |
INE | -0.232 |
Magikarp | -0.231 |
Token | acks |
Token ID | 4595 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
leys | +0.039 |
luaj | +0.038 |
bri | +0.037 |
nen | +0.037 |
jin | +0.036 |
Neg logit contributions | |
gdala | -0.044 |
ICAN | -0.035 |
amination | -0.035 |
INE | -0.034 |
Magikarp | -0.033 |
Token | in |
Token ID | 287 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
gdala | +0.911 |
ICAN | +0.750 |
amination | +0.727 |
INE | +0.720 |
Magikarp | +0.704 |
Neg logit contributions | |
leys | -0.716 |
luaj | -0.707 |
bri | -0.680 |
nen | -0.671 |
ahime | -0.666 |
Token | Philly |
Token ID | 30029 |
Feature activation | -8.58e+00 |
Pos logit contributions | |
gdala | +0.709 |
ICAN | +0.569 |
amination | +0.550 |
INE | +0.540 |
Magikarp | +0.532 |
Neg logit contributions | |
leys | -0.711 |
luaj | -0.703 |
bri | -0.677 |
nen | -0.671 |
jin | -0.666 |
Token | have |
Token ID | 423 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
gdala | +7.073 |
ICAN | +5.748 |
coinc | +5.603 |
INE | +5.582 |
amination | +5.464 |
Neg logit contributions | |
luaj | -5.839 |
leys | -5.838 |
ahime | -5.596 |
nen | -5.523 |
oshenko | -5.514 |
Token | a |
Token ID | 257 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
gdala | +0.816 |
ICAN | +0.667 |
amination | +0.638 |
INE | +0.638 |
coinc | +0.631 |
Neg logit contributions | |
leys | -0.720 |
luaj | -0.709 |
bri | -0.671 |
nen | -0.671 |
jin | -0.666 |
Token | different |
Token ID | 1180 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
leys | +0.808 |
luaj | +0.788 |
bri | +0.765 |
nen | +0.755 |
jin | +0.744 |
Neg logit contributions | |
gdala | -0.994 |
ICAN | -0.816 |
amination | -0.788 |
INE | -0.777 |
Magikarp | -0.771 |
Token | overall |
Token ID | 4045 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
leys | +1.501 |
luaj | +1.459 |
bri | +1.410 |
nen | +1.393 |
jin | +1.372 |
Neg logit contributions | |
gdala | -2.324 |
ICAN | -1.946 |
amination | -1.889 |
INE | -1.862 |
Magikarp | -1.856 |
Token | accent |
Token ID | 18702 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
leys | +0.979 |
luaj | +0.952 |
bri | +0.921 |
nen | +0.912 |
jin | +0.897 |
Neg logit contributions | |
gdala | -1.431 |
ICAN | -1.193 |
amination | -1.157 |
INE | -1.140 |
Magikarp | -1.130 |
Token | Smith |
Token ID | 17919 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
leys | +0.488 |
luaj | +0.481 |
bri | +0.472 |
nen | +0.464 |
igans | +0.454 |
Neg logit contributions | |
gdala | -0.440 |
ICAN | -0.351 |
amination | -0.335 |
INE | -0.332 |
Magikarp | -0.331 |
Token | sonian |
Token ID | 35202 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
gdala | +0.195 |
ICAN | +0.137 |
INE | +0.125 |
amination | +0.123 |
Magikarp | +0.121 |
Neg logit contributions | |
leys | -0.421 |
luaj | -0.413 |
bri | -0.406 |
nen | -0.404 |
ahime | -0.402 |
Token | Center |
Token ID | 3337 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
gdala | +3.490 |
ICAN | +2.859 |
INE | +2.758 |
amination | +2.699 |
Magikarp | +2.622 |
Neg logit contributions | |
luaj | -4.004 |
leys | -3.999 |
oshenko | -3.870 |
bri | -3.842 |
ahime | -3.818 |
Token | for |
Token ID | 329 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
gdala | +2.747 |
ICAN | +2.117 |
amination | +2.085 |
INE | +2.052 |
Magikarp | +1.984 |
Neg logit contributions | |
leys | -3.151 |
luaj | -3.118 |
oshenko | -2.998 |
bri | -2.986 |
nen | -2.965 |
Token | Ast |
Token ID | 8304 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
leys | +0.782 |
luaj | +0.769 |
bri | +0.755 |
nen | +0.745 |
jin | +0.739 |
Neg logit contributions | |
gdala | -0.562 |
ICAN | -0.428 |
amination | -0.407 |
Magikarp | -0.399 |
INE | -0.397 |
Token | roph |
Token ID | 10051 |
Feature activation | -8.51e+00 |
Pos logit contributions | |
gdala | +1.845 |
ICAN | +1.571 |
amination | +1.536 |
INE | +1.514 |
Magikarp | +1.510 |
Neg logit contributions | |
leys | -0.885 |
luaj | -0.867 |
bri | -0.836 |
nen | -0.815 |
jin | -0.796 |
Token | ysics |
Token ID | 23154 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
gdala | +2.857 |
amination | +1.763 |
ICAN | +1.643 |
INE | +1.520 |
ithmetic | +1.188 |
Neg logit contributions | |
luaj | -10.394 |
bri | -10.238 |
leys | -10.219 |
nen | -10.009 |
oshenko | -9.970 |
Token | and |
Token ID | 290 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
gdala | +2.489 |
ICAN | +1.998 |
coinc | +1.938 |
amination | +1.937 |
INE | +1.926 |
Neg logit contributions | |
luaj | -2.316 |
leys | -2.302 |
bri | -2.182 |
nen | -2.169 |
ahime | -2.163 |
Token | his |
Token ID | 465 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
gdala | +0.038 |
ICAN | +0.031 |
amination | +0.030 |
INE | +0.030 |
Magikarp | +0.029 |
Neg logit contributions | |
leys | -0.036 |
luaj | -0.036 |
bri | -0.035 |
nen | -0.035 |
igans | -0.034 |
Token | coll |
Token ID | 2927 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
gdala | +1.344 |
ICAN | +1.110 |
amination | +1.074 |
INE | +1.060 |
coinc | +1.044 |
Neg logit contributions | |
leys | -1.114 |
luaj | -1.091 |
nen | -1.050 |
bri | -1.048 |
ahime | -1.036 |
Token | agues |
Token ID | 6120 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
gdala | +0.876 |
ICAN | +0.708 |
amination | +0.684 |
INE | +0.674 |
Magikarp | +0.654 |
Neg logit contributions | |
leys | -0.908 |
luaj | -0.901 |
bri | -0.880 |
nen | -0.862 |
jin | -0.853 |
Token | the |
Token ID | 262 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
leys | +0.539 |
luaj | +0.529 |
bri | +0.515 |
nen | +0.508 |
jin | +0.502 |
Neg logit contributions | |
gdala | -0.586 |
ICAN | -0.474 |
amination | -0.456 |
INE | -0.450 |
Magikarp | -0.449 |
Token | Laser |
Token ID | 23222 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
leys | +0.035 |
luaj | +0.035 |
bri | +0.034 |
nen | +0.033 |
jin | +0.033 |
Neg logit contributions | |
gdala | -0.037 |
ICAN | -0.030 |
amination | -0.028 |
INE | -0.028 |
Magikarp | -0.028 |
Token | Inter |
Token ID | 4225 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
gdala | +1.993 |
ICAN | +1.643 |
amination | +1.561 |
INE | +1.560 |
Magikarp | +1.541 |
Neg logit contributions | |
leys | -1.772 |
luaj | -1.759 |
bri | -1.678 |
nen | -1.678 |
ahime | -1.645 |
Token | fer |
Token ID | 2232 |
Feature activation | -6.58e+00 |
Pos logit contributions | |
leys | +0.901 |
luaj | +0.888 |
bri | +0.866 |
nen | +0.857 |
jin | +0.840 |
Neg logit contributions | |
gdala | -0.919 |
ICAN | -0.733 |
amination | -0.711 |
INE | -0.697 |
Magikarp | -0.693 |
Token | ometer |
Token ID | 15635 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
gdala | +4.349 |
ICAN | +3.299 |
amination | +3.189 |
renheit | +3.071 |
INE | +2.998 |
Neg logit contributions | |
luaj | -6.088 |
leys | -5.975 |
bri | -5.912 |
nen | -5.783 |
ahime | -5.783 |
Token | Grav |
Token ID | 32599 |
Feature activation | -8.46e+00 |
Pos logit contributions | |
gdala | +2.700 |
ICAN | +2.104 |
coinc | +2.034 |
INE | +1.932 |
amination | +1.893 |
Neg logit contributions | |
luaj | -4.215 |
leys | -4.160 |
nen | -4.040 |
oshenko | -4.019 |
ahime | -4.006 |
Token | itational |
Token ID | 22181 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
gdala | +3.660 |
ICAN | +2.533 |
amination | +2.361 |
INE | +2.194 |
ithmetic | +2.027 |
Neg logit contributions | |
luaj | -9.525 |
leys | -9.237 |
nen | -9.202 |
bri | -9.085 |
oshenko | -8.973 |
Token | - |
Token ID | 12 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
gdala | +4.579 |
ICAN | +3.768 |
amination | +3.616 |
coinc | +3.600 |
INE | +3.588 |
Neg logit contributions | |
luaj | -3.886 |
leys | -3.828 |
nen | -3.661 |
bri | -3.619 |
ahime | -3.617 |
Token | wave |
Token ID | 19204 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
gdala | +0.351 |
ICAN | +0.287 |
amination | +0.278 |
Magikarp | +0.274 |
INE | +0.273 |
Neg logit contributions | |
leys | -0.280 |
luaj | -0.274 |
bri | -0.267 |
nen | -0.262 |
jin | -0.259 |
Token | Observatory |
Token ID | 25758 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
gdala | +2.352 |
ICAN | +1.696 |
amination | +1.573 |
coinc | +1.546 |
INE | +1.532 |
Neg logit contributions | |
luaj | -4.443 |
leys | -4.384 |
nen | -4.275 |
bri | -4.239 |
ahime | -4.195 |
Token | ( |
Token ID | 357 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
gdala | +3.093 |
ICAN | +2.481 |
INE | +2.385 |
coinc | +2.352 |
amination | +2.348 |
Neg logit contributions | |
luaj | -3.248 |
leys | -3.200 |
bri | -3.050 |
nen | -3.033 |
ahime | -3.015 |
Token | Hait |
Token ID | 19456 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
leys | +0.652 |
luaj | +0.640 |
bri | +0.619 |
nen | +0.617 |
ahime | +0.610 |
Neg logit contributions | |
gdala | -0.652 |
ICAN | -0.525 |
amination | -0.507 |
INE | -0.497 |
Magikarp | -0.494 |
Token | ians |
Token ID | 1547 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
gdala | +0.837 |
ICAN | +0.713 |
amination | +0.694 |
INE | +0.685 |
Magikarp | +0.680 |
Neg logit contributions | |
leys | -0.469 |
luaj | -0.458 |
bri | -0.445 |
nen | -0.436 |
jin | -0.424 |
Token | are |
Token ID | 389 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
leys | +0.322 |
luaj | +0.317 |
bri | +0.303 |
nen | +0.302 |
ahime | +0.296 |
Neg logit contributions | |
gdala | -0.440 |
ICAN | -0.362 |
amination | -0.354 |
INE | -0.349 |
coinc | -0.346 |
Token | the |
Token ID | 262 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
gdala | +0.818 |
ICAN | +0.656 |
amination | +0.637 |
INE | +0.626 |
coinc | +0.625 |
Neg logit contributions | |
leys | -0.813 |
luaj | -0.810 |
bri | -0.772 |
nen | -0.771 |
ahime | -0.766 |
Token | latest |
Token ID | 3452 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
leys | +0.124 |
luaj | +0.122 |
bri | +0.118 |
nen | +0.117 |
ahime | +0.116 |
Neg logit contributions | |
gdala | -0.129 |
ICAN | -0.104 |
amination | -0.101 |
INE | -0.099 |
Magikarp | -0.098 |
Token | arrivals |
Token ID | 34462 |
Feature activation | -8.34e+00 |
Pos logit contributions | |
leys | +1.048 |
luaj | +1.031 |
bri | +1.003 |
nen | +0.991 |
jin | +0.978 |
Neg logit contributions | |
gdala | -0.966 |
ICAN | -0.767 |
amination | -0.739 |
Magikarp | -0.724 |
INE | -0.724 |
Token | . |
Token ID | 13 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
gdala | +6.110 |
ICAN | +4.903 |
coinc | +4.901 |
amination | +4.776 |
INE | +4.670 |
Neg logit contributions | |
luaj | -6.682 |
leys | -6.628 |
bri | -6.185 |
ahime | -6.139 |
oshenko | -6.128 |
Token | This |
Token ID | 770 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
leys | +0.198 |
luaj | +0.194 |
bri | +0.189 |
nen | +0.185 |
jin | +0.182 |
Neg logit contributions | |
gdala | -0.265 |
ICAN | -0.220 |
amination | -0.212 |
INE | -0.209 |
Magikarp | -0.209 |
Token | churn |
Token ID | 28488 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
leys | +2.390 |
luaj | +2.330 |
bri | +2.280 |
nen | +2.232 |
jin | +2.205 |
Neg logit contributions | |
gdala | -3.222 |
ICAN | -2.664 |
amination | -2.576 |
Magikarp | -2.552 |
INE | -2.533 |
Token | ing |
Token ID | 278 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
leys | +0.844 |
luaj | +0.829 |
bri | +0.804 |
nen | +0.793 |
jin | +0.779 |
Neg logit contributions | |
gdala | -1.082 |
ICAN | -0.892 |
amination | -0.868 |
INE | -0.852 |
Magikarp | -0.848 |
Token | mix |
Token ID | 5022 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
gdala | +0.255 |
ICAN | +0.206 |
amination | +0.200 |
INE | +0.196 |
Magikarp | +0.194 |
Neg logit contributions | |
leys | -0.245 |
luaj | -0.242 |
bri | -0.232 |
nen | -0.231 |
ahime | -0.229 |
Token | , |
Token ID | 11 |
Feature activation | -6.51e-03 |
Pos logit contributions | |
leys | +0.732 |
luaj | +0.716 |
bri | +0.695 |
nen | +0.684 |
jin | +0.675 |
Neg logit contributions | |
gdala | -0.897 |
ICAN | -0.735 |
amination | -0.713 |
Magikarp | -0.699 |
INE | -0.699 |
Token | and |
Token ID | 290 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
gdala | +0.006 |
ICAN | +0.005 |
amination | +0.004 |
Magikarp | +0.004 |
INE | +0.004 |
Neg logit contributions | |
leys | -0.005 |
luaj | -0.005 |
bri | -0.005 |
nen | -0.005 |
jin | -0.005 |
Token | that |
Token ID | 326 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
gdala | +0.594 |
ICAN | +0.480 |
amination | +0.463 |
INE | +0.455 |
Magikarp | +0.454 |
Neg logit contributions | |
leys | -0.561 |
luaj | -0.553 |
bri | -0.532 |
nen | -0.528 |
ahime | -0.523 |
Token | the |
Token ID | 262 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
gdala | +1.058 |
ICAN | +0.849 |
amination | +0.828 |
coinc | +0.811 |
INE | +0.810 |
Neg logit contributions | |
leys | -1.041 |
luaj | -1.029 |
nen | -0.981 |
bri | -0.979 |
ahime | -0.975 |
Token | Moon |
Token ID | 6869 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
gdala | +0.171 |
ICAN | +0.140 |
amination | +0.135 |
INE | +0.132 |
Magikarp | +0.132 |
Neg logit contributions | |
leys | -0.154 |
luaj | -0.151 |
bri | -0.146 |
nen | -0.145 |
jin | -0.143 |
Token | landing |
Token ID | 9581 |
Feature activation | -8.30e+00 |
Pos logit contributions | |
leys | +0.996 |
luaj | +0.977 |
bri | +0.956 |
nen | +0.943 |
jin | +0.932 |
Neg logit contributions | |
gdala | -0.873 |
ICAN | -0.687 |
amination | -0.660 |
Magikarp | -0.648 |
INE | -0.646 |
Token | was |
Token ID | 373 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
gdala | +6.717 |
coinc | +5.565 |
ICAN | +5.447 |
INE | +5.370 |
amination | +5.364 |
Neg logit contributions | |
luaj | -6.116 |
leys | -6.076 |
ahime | -5.804 |
nen | -5.752 |
bri | -5.737 |
Token | fake |
Token ID | 8390 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
gdala | +0.364 |
ICAN | +0.299 |
amination | +0.289 |
Magikarp | +0.285 |
coinc | +0.284 |
Neg logit contributions | |
leys | -0.311 |
luaj | -0.304 |
bri | -0.291 |
nen | -0.289 |
ahime | -0.285 |
Token | . |
Token ID | 13 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
gdala | +1.946 |
ICAN | +1.600 |
amination | +1.547 |
coinc | +1.535 |
INE | +1.515 |
Neg logit contributions | |
leys | -1.821 |
luaj | -1.780 |
nen | -1.698 |
bri | -1.697 |
ahime | -1.662 |
Token | Flynn |
Token ID | 14654 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
gdala | +0.483 |
ICAN | +0.399 |
amination | +0.385 |
INE | +0.382 |
Magikarp | +0.379 |
Neg logit contributions | |
leys | -0.362 |
luaj | -0.356 |
bri | -0.345 |
nen | -0.338 |
ahime | -0.333 |
Token | � |
Token ID | 447 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
gdala | +2.602 |
ICAN | +2.080 |
coinc | +2.049 |
INE | +2.044 |
amination | +2.039 |
Neg logit contributions | |
luaj | -2.196 |
leys | -2.183 |
bri | -2.069 |
ahime | -2.060 |
nen | -2.048 |
Token | 3 |
Token ID | 18 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
gdala | +2.873 |
ICAN | +2.388 |
amination | +2.297 |
INE | +2.292 |
Magikarp | +2.256 |
Neg logit contributions | |
leys | -2.216 |
luaj | -2.179 |
bri | -2.134 |
nen | -2.072 |
ahime | -2.070 |
Token | week |
Token ID | 1285 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
gdala | +2.964 |
ICAN | +2.374 |
INE | +2.301 |
amination | +2.300 |
Magikarp | +2.272 |
Neg logit contributions | |
leys | -2.825 |
luaj | -2.766 |
bri | -2.715 |
nen | -2.677 |
ahime | -2.644 |
Token | , |
Token ID | 11 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
gdala | +2.109 |
ICAN | +1.693 |
amination | +1.648 |
INE | +1.625 |
Magikarp | +1.611 |
Neg logit contributions | |
leys | -1.881 |
luaj | -1.851 |
bri | -1.800 |
nen | -1.754 |
ahime | -1.744 |
Token | as |
Token ID | 355 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
gdala | +0.777 |
ICAN | +0.605 |
amination | +0.585 |
Magikarp | +0.578 |
INE | +0.576 |
Neg logit contributions | |
leys | -0.912 |
luaj | -0.901 |
bri | -0.874 |
nen | -0.863 |
ahime | -0.856 |
Token | word |
Token ID | 1573 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
gdala | +2.020 |
ICAN | +1.619 |
amination | +1.587 |
INE | +1.578 |
Magikarp | +1.557 |
Neg logit contributions | |
leys | -1.848 |
luaj | -1.845 |
bri | -1.769 |
nen | -1.747 |
ahime | -1.743 |
Token | dropped |
Token ID | 5710 |
Feature activation | -8.28e+00 |
Pos logit contributions | |
gdala | +2.708 |
ICAN | +2.218 |
amination | +2.174 |
INE | +2.113 |
coinc | +2.107 |
Neg logit contributions | |
leys | -2.390 |
luaj | -2.357 |
ahime | -2.248 |
bri | -2.242 |
nen | -2.231 |
Token | yesterday |
Token ID | 7415 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
gdala | +5.882 |
coinc | +4.717 |
amination | +4.545 |
ICAN | +4.536 |
INE | +4.397 |
Neg logit contributions | |
luaj | -6.878 |
leys | -6.738 |
ahime | -6.562 |
nen | -6.362 |
bri | -6.312 |
Token | that |
Token ID | 326 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
gdala | +2.912 |
ICAN | +2.306 |
amination | +2.230 |
coinc | +2.213 |
INE | +2.189 |
Neg logit contributions | |
luaj | -2.910 |
leys | -2.909 |
bri | -2.779 |
ahime | -2.761 |
nen | -2.754 |
Token | Blue |
Token ID | 4518 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
gdala | +2.050 |
ICAN | +1.655 |
amination | +1.606 |
INE | +1.592 |
Magikarp | +1.571 |
Neg logit contributions | |
leys | -1.904 |
luaj | -1.890 |
bri | -1.814 |
nen | -1.805 |
ahime | -1.787 |
Token | hole |
Token ID | 13207 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
leys | +0.771 |
luaj | +0.747 |
bri | +0.715 |
nen | +0.704 |
jin | +0.693 |
Neg logit contributions | |
gdala | -1.652 |
ICAN | -1.415 |
amination | -1.376 |
Magikarp | -1.362 |
INE | -1.360 |
Token | was |
Token ID | 373 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
gdala | +3.033 |
ICAN | +2.521 |
amination | +2.462 |
INE | +2.435 |
Magikarp | +2.398 |
Neg logit contributions | |
leys | -2.152 |
luaj | -2.101 |
bri | -2.057 |
nen | -2.002 |
ahime | -1.991 |
Token | , |
Token ID | 11 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
leys | +0.194 |
luaj | +0.190 |
bri | +0.185 |
nen | +0.182 |
ahime | +0.179 |
Neg logit contributions | |
gdala | -0.232 |
ICAN | -0.191 |
amination | -0.184 |
INE | -0.182 |
Magikarp | -0.182 |
Token | this |
Token ID | 428 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
leys | +0.260 |
luaj | +0.256 |
nen | +0.247 |
bri | +0.246 |
ahime | +0.242 |
Neg logit contributions | |
gdala | -0.293 |
ICAN | -0.239 |
amination | -0.230 |
INE | -0.228 |
Magikarp | -0.228 |
Token | may |
Token ID | 743 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
leys | +1.142 |
luaj | +1.117 |
bri | +1.080 |
nen | +1.070 |
jin | +1.049 |
Neg logit contributions | |
gdala | -1.558 |
ICAN | -1.293 |
amination | -1.252 |
INE | -1.234 |
Magikarp | -1.232 |
Token | tax |
Token ID | 1687 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
leys | +1.202 |
luaj | +1.185 |
bri | +1.135 |
nen | +1.126 |
ahime | +1.112 |
Neg logit contributions | |
gdala | -1.486 |
ICAN | -1.227 |
amination | -1.186 |
INE | -1.178 |
Magikarp | -1.164 |
Token | your |
Token ID | 534 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
leys | +1.223 |
luaj | +1.192 |
bri | +1.158 |
nen | +1.136 |
jin | +1.119 |
Neg logit contributions | |
gdala | -1.856 |
ICAN | -1.549 |
amination | -1.504 |
Magikarp | -1.484 |
INE | -1.480 |
Token | blender |
Token ID | 40047 |
Feature activation | +7.09e+00 |
Pos logit contributions | |
leys | +0.161 |
luaj | +0.157 |
bri | +0.152 |
nen | +0.150 |
ahime | +0.148 |
Neg logit contributions | |
gdala | -0.186 |
ICAN | -0.152 |
amination | -0.147 |
INE | -0.145 |
Magikarp | -0.144 |
Token | a |
Token ID | 257 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
leys | +4.840 |
bri | +4.721 |
luaj | +4.688 |
jin | +4.598 |
nen | +4.589 |
Neg logit contributions | |
gdala | -6.343 |
ICAN | -5.124 |
amination | -5.004 |
Magikarp | -4.960 |
renheit | -4.816 |
Token | little |
Token ID | 1310 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
leys | +0.748 |
luaj | +0.730 |
bri | +0.701 |
nen | +0.690 |
jin | +0.678 |
Neg logit contributions | |
gdala | -1.262 |
ICAN | -1.064 |
amination | -1.034 |
INE | -1.022 |
Magikarp | -1.020 |
Token | , |
Token ID | 11 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
leys | +1.654 |
luaj | +1.613 |
bri | +1.565 |
nen | +1.536 |
jin | +1.512 |
Neg logit contributions | |
gdala | -2.560 |
ICAN | -2.141 |
amination | -2.079 |
Magikarp | -2.051 |
INE | -2.046 |
Token | but |
Token ID | 475 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
leys | +0.446 |
luaj | +0.438 |
bri | +0.422 |
nen | +0.420 |
ahime | +0.413 |
Neg logit contributions | |
gdala | -0.495 |
ICAN | -0.404 |
amination | -0.390 |
Magikarp | -0.385 |
INE | -0.385 |
Token | as |
Token ID | 355 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
gdala | +1.823 |
ICAN | +1.503 |
INE | +1.452 |
amination | +1.447 |
coinc | +1.439 |
Neg logit contributions | |
luaj | -1.691 |
leys | -1.686 |
nen | -1.616 |
ahime | -1.609 |
bri | -1.570 |
Token |
|
Token ID | 198 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
gdala | +0.680 |
ICAN | +0.565 |
amination | +0.547 |
Magikarp | +0.540 |
INE | +0.539 |
Neg logit contributions | |
leys | -0.482 |
luaj | -0.471 |
bri | -0.458 |
nen | -0.449 |
jin | -0.442 |
Token | V |
Token ID | 53 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
gdala | +0.629 |
ICAN | +0.519 |
amination | +0.494 |
Magikarp | +0.494 |
INE | +0.493 |
Neg logit contributions | |
leys | -0.582 |
luaj | -0.572 |
bri | -0.563 |
nen | -0.549 |
ahime | -0.544 |
Token | ish |
Token ID | 680 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
leys | +1.615 |
luaj | +1.576 |
bri | +1.531 |
nen | +1.505 |
jin | +1.482 |
Neg logit contributions | |
gdala | -2.314 |
ICAN | -1.923 |
amination | -1.865 |
Magikarp | -1.840 |
INE | -1.835 |
Token | nu |
Token ID | 28803 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
leys | +1.010 |
luaj | +0.973 |
bri | +0.933 |
nen | +0.910 |
jin | +0.889 |
Neg logit contributions | |
gdala | -2.602 |
ICAN | -2.242 |
amination | -2.188 |
Magikarp | -2.168 |
INE | -2.161 |
Token | at |
Token ID | 379 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
leys | +1.521 |
luaj | +1.487 |
bri | +1.446 |
nen | +1.423 |
jin | +1.402 |
Neg logit contributions | |
gdala | -1.986 |
ICAN | -1.638 |
amination | -1.586 |
Magikarp | -1.563 |
INE | -1.560 |
Token | Va |
Token ID | 17668 |
Feature activation | +7.69e+00 |
Pos logit contributions | |
leys | +0.671 |
luaj | +0.655 |
bri | +0.639 |
nen | +0.631 |
jin | +0.622 |
Neg logit contributions | |
gdala | -0.750 |
ICAN | -0.610 |
amination | -0.589 |
Magikarp | -0.579 |
INE | -0.579 |
Token | ik |
Token ID | 1134 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
leys | +5.202 |
luaj | +5.020 |
jin | +4.859 |
bri | +4.847 |
nen | +4.824 |
Neg logit contributions | |
gdala | -7.036 |
ICAN | -5.757 |
Magikarp | -5.601 |
amination | -5.483 |
INE | -5.439 |
Token | unta |
Token ID | 44424 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
leys | +0.818 |
luaj | +0.812 |
bri | +0.782 |
nen | +0.766 |
jin | +0.752 |
Neg logit contributions | |
gdala | -1.008 |
ICAN | -0.824 |
amination | -0.803 |
INE | -0.790 |
Magikarp | -0.784 |
Token | Th |
Token ID | 536 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
leys | +4.055 |
luaj | +3.956 |
bri | +3.874 |
jin | +3.797 |
nen | +3.793 |
Neg logit contributions | |
gdala | -4.981 |
ICAN | -4.060 |
amination | -3.910 |
Magikarp | -3.884 |
renheit | -3.839 |
Token | ad |
Token ID | 324 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
leys | +1.714 |
luaj | +1.678 |
bri | +1.637 |
nen | +1.614 |
jin | +1.593 |
Neg logit contributions | |
gdala | -1.850 |
ICAN | -1.496 |
amination | -1.442 |
Magikarp | -1.422 |
INE | -1.416 |
Token | ik |
Token ID | 1134 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
leys | +1.156 |
luaj | +1.119 |
bri | +1.075 |
nen | +1.048 |
jin | +1.026 |
Neg logit contributions | |
gdala | -2.691 |
ICAN | -2.309 |
amination | -2.252 |
Magikarp | -2.227 |
INE | -2.222 |
Token |
|
Token ID | 198 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
leys | +0.429 |
luaj | +0.419 |
bri | +0.403 |
nen | +0.402 |
jin | +0.397 |
Neg logit contributions | |
gdala | -0.670 |
ICAN | -0.557 |
amination | -0.545 |
Magikarp | -0.538 |
renheit | -0.533 |
Token | � |
Token ID | 447 |
Feature activation | +5.58e-02 |
Pos logit contributions | |
leys | +0.431 |
luaj | +0.424 |
bri | +0.417 |
nen | +0.408 |
ahime | +0.402 |
Neg logit contributions | |
gdala | -0.454 |
ICAN | -0.372 |
amination | -0.354 |
Magikarp | -0.352 |
INE | -0.352 |
Token | � |
Token ID | 250 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
leys | +0.049 |
luaj | +0.048 |
bri | +0.047 |
nen | +0.046 |
jin | +0.046 |
Neg logit contributions | |
gdala | -0.041 |
ICAN | -0.032 |
amination | -0.031 |
INE | -0.030 |
Magikarp | -0.030 |
Token | Make |
Token ID | 12050 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
gdala | +0.107 |
ICAN | +0.088 |
amination | +0.084 |
INE | +0.084 |
Magikarp | +0.082 |
Neg logit contributions | |
leys | -0.095 |
luaj | -0.093 |
bri | -0.091 |
nen | -0.089 |
jin | -0.088 |
Token | a |
Token ID | 257 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
leys | +3.543 |
luaj | +3.444 |
bri | +3.380 |
nen | +3.312 |
jin | +3.281 |
Neg logit contributions | |
gdala | -4.305 |
ICAN | -3.520 |
amination | -3.388 |
Magikarp | -3.376 |
INE | -3.341 |
Token | file |
Token ID | 2393 |
Feature activation | +7.91e+00 |
Pos logit contributions | |
leys | +1.108 |
luaj | +1.088 |
bri | +1.048 |
nen | +1.041 |
jin | +1.021 |
Neg logit contributions | |
gdala | -1.372 |
ICAN | -1.127 |
amination | -1.092 |
INE | -1.074 |
Magikarp | -1.066 |
Token | now |
Token ID | 783 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
leys | +5.705 |
luaj | +5.527 |
bri | +5.461 |
nen | +5.293 |
jin | +5.258 |
Neg logit contributions | |
gdala | -6.784 |
ICAN | -5.564 |
amination | -5.357 |
Magikarp | -5.342 |
renheit | -5.338 |
Token | with |
Token ID | 351 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
leys | +1.292 |
luaj | +1.265 |
bri | +1.233 |
nen | +1.215 |
jin | +1.198 |
Neg logit contributions | |
gdala | -1.471 |
ICAN | -1.197 |
amination | -1.156 |
Magikarp | -1.137 |
INE | -1.135 |
Token | proof |
Token ID | 6617 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
leys | +0.457 |
luaj | +0.451 |
bri | +0.432 |
nen | +0.432 |
ahime | +0.423 |
Neg logit contributions | |
gdala | -0.546 |
ICAN | -0.450 |
amination | -0.435 |
INE | -0.428 |
Magikarp | -0.423 |
Token | of |
Token ID | 286 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
gdala | +1.834 |
ICAN | +1.477 |
amination | +1.429 |
INE | +1.407 |
Magikarp | +1.388 |
Neg logit contributions | |
leys | -1.856 |
luaj | -1.833 |
bri | -1.770 |
nen | -1.762 |
ahime | -1.733 |
Token | your |
Token ID | 534 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
gdala | +0.329 |
ICAN | +0.266 |
amination | +0.259 |
INE | +0.255 |
Magikarp | +0.253 |
Neg logit contributions | |
leys | -0.310 |
luaj | -0.308 |
bri | -0.294 |
nen | -0.292 |
ahime | -0.287 |
Token | chair |
Token ID | 5118 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
gdala | +0.686 |
ICAN | +0.571 |
amination | +0.553 |
INE | +0.545 |
coinc | +0.535 |
Neg logit contributions | |
leys | -0.531 |
luaj | -0.524 |
bri | -0.498 |
nen | -0.497 |
igans | -0.488 |
Token | of |
Token ID | 286 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
leys | +1.880 |
luaj | +1.822 |
bri | +1.796 |
nen | +1.776 |
jin | +1.754 |
Neg logit contributions | |
gdala | -1.873 |
ICAN | -1.498 |
amination | -1.431 |
Magikarp | -1.428 |
INE | -1.411 |
Token | Federal |
Token ID | 5618 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
leys | +0.720 |
luaj | +0.705 |
bri | +0.687 |
nen | +0.677 |
jin | +0.668 |
Neg logit contributions | |
gdala | -0.807 |
ICAN | -0.656 |
amination | -0.633 |
Magikarp | -0.622 |
INE | -0.622 |
Token | Council |
Token ID | 4281 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
gdala | +1.565 |
ICAN | +1.302 |
amination | +1.257 |
INE | +1.236 |
coinc | +1.207 |
Neg logit contributions | |
leys | -1.241 |
luaj | -1.212 |
bri | -1.177 |
nen | -1.168 |
jin | -1.146 |
Token | of |
Token ID | 286 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
leys | +0.103 |
luaj | +0.101 |
bri | +0.098 |
nen | +0.097 |
jin | +0.095 |
Neg logit contributions | |
gdala | -0.111 |
ICAN | -0.090 |
amination | -0.087 |
INE | -0.085 |
Magikarp | -0.085 |
Token | Negro |
Token ID | 27115 |
Feature activation | +6.88e+00 |
Pos logit contributions | |
leys | +0.839 |
luaj | +0.822 |
bri | +0.797 |
nen | +0.786 |
jin | +0.773 |
Neg logit contributions | |
gdala | -1.099 |
ICAN | -0.908 |
amination | -0.880 |
INE | -0.865 |
Magikarp | -0.864 |
Token | Affairs |
Token ID | 10665 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
leys | +4.871 |
luaj | +4.734 |
bri | +4.599 |
nen | +4.483 |
jin | +4.480 |
Neg logit contributions | |
gdala | -6.104 |
ICAN | -4.974 |
Magikarp | -4.926 |
amination | -4.794 |
INE | -4.751 |
Token | . |
Token ID | 13 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
leys | +0.959 |
luaj | +0.937 |
bri | +0.913 |
nen | +0.897 |
jin | +0.886 |
Neg logit contributions | |
gdala | -1.218 |
ICAN | -1.000 |
amination | -0.969 |
Magikarp | -0.956 |
INE | -0.951 |
Token | Among |
Token ID | 9754 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
gdala | +0.453 |
ICAN | +0.372 |
amination | +0.357 |
INE | +0.354 |
Magikarp | +0.349 |
Neg logit contributions | |
leys | -0.386 |
luaj | -0.379 |
bri | -0.370 |
nen | -0.362 |
igans | -0.357 |
Token | her |
Token ID | 607 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
leys | +1.929 |
luaj | +1.888 |
bri | +1.842 |
nen | +1.811 |
jin | +1.787 |
Neg logit contributions | |
gdala | -2.329 |
ICAN | -1.903 |
amination | -1.838 |
Magikarp | -1.820 |
INE | -1.810 |
Token | honors |
Token ID | 25279 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
gdala | +2.549 |
ICAN | +2.095 |
coinc | +2.015 |
amination | +1.996 |
INE | +1.994 |
Neg logit contributions | |
leys | -2.213 |
luaj | -2.168 |
ahime | -2.070 |
igans | -2.056 |
jin | -2.048 |
Token | � |
Token ID | 247 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
leys | +1.469 |
luaj | +1.432 |
bri | +1.402 |
nen | +1.379 |
jin | +1.363 |
Neg logit contributions | |
gdala | -1.681 |
ICAN | -1.366 |
amination | -1.321 |
Magikarp | -1.303 |
INE | -1.289 |
Token | ll |
Token ID | 297 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
leys | +0.544 |
luaj | +0.537 |
bri | +0.520 |
nen | +0.508 |
jin | +0.502 |
Neg logit contributions | |
gdala | -0.692 |
ICAN | -0.568 |
amination | -0.553 |
INE | -0.542 |
Magikarp | -0.539 |
Token | see |
Token ID | 766 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
leys | +1.427 |
luaj | +1.406 |
bri | +1.350 |
nen | +1.332 |
jin | +1.308 |
Neg logit contributions | |
gdala | -1.969 |
ICAN | -1.629 |
amination | -1.586 |
INE | -1.562 |
Magikarp | -1.553 |
Token | in |
Token ID | 287 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
leys | +2.739 |
luaj | +2.671 |
bri | +2.613 |
nen | +2.571 |
jin | +2.539 |
Neg logit contributions | |
gdala | -3.152 |
ICAN | -2.565 |
amination | -2.474 |
Magikarp | -2.441 |
INE | -2.426 |
Token | the |
Token ID | 262 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
leys | +0.173 |
luaj | +0.170 |
bri | +0.165 |
nen | +0.162 |
jin | +0.161 |
Neg logit contributions | |
gdala | -0.193 |
ICAN | -0.156 |
amination | -0.151 |
INE | -0.149 |
Magikarp | -0.148 |
Token | video |
Token ID | 2008 |
Feature activation | +6.71e+00 |
Pos logit contributions | |
leys | +0.124 |
luaj | +0.122 |
bri | +0.118 |
nen | +0.116 |
jin | +0.115 |
Neg logit contributions | |
gdala | -0.144 |
ICAN | -0.117 |
amination | -0.114 |
INE | -0.112 |
Magikarp | -0.111 |
Token | clip |
Token ID | 10651 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
leys | +4.530 |
luaj | +4.351 |
bri | +4.294 |
nen | +4.199 |
jin | +4.160 |
Neg logit contributions | |
gdala | -6.040 |
ICAN | -5.093 |
Magikarp | -4.866 |
amination | -4.865 |
renheit | -4.789 |
Token | above |
Token ID | 2029 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
leys | +1.174 |
luaj | +1.151 |
bri | +1.120 |
nen | +1.103 |
jin | +1.088 |
Neg logit contributions | |
gdala | -1.379 |
ICAN | -1.124 |
amination | -1.088 |
Magikarp | -1.069 |
INE | -1.069 |
Token | , |
Token ID | 11 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
gdala | +0.210 |
ICAN | +0.171 |
amination | +0.166 |
INE | +0.164 |
Magikarp | +0.163 |
Neg logit contributions | |
leys | -0.175 |
luaj | -0.171 |
bri | -0.166 |
nen | -0.164 |
jin | -0.162 |
Token | Major |
Token ID | 8386 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
gdala | +0.346 |
ICAN | +0.278 |
amination | +0.269 |
INE | +0.265 |
Magikarp | +0.264 |
Neg logit contributions | |
leys | -0.327 |
luaj | -0.322 |
bri | -0.312 |
nen | -0.307 |
jin | -0.304 |
Token | Nelson |
Token ID | 12996 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
gdala | +2.443 |
ICAN | +1.994 |
INE | +1.905 |
amination | +1.884 |
Magikarp | +1.850 |
Neg logit contributions | |
luaj | -2.251 |
leys | -2.212 |
bri | -2.177 |
nen | -2.143 |
ahime | -2.129 |
Token | k |
Token ID | 479 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
gdala | +2.300 |
ICAN | +1.901 |
amination | +1.862 |
INE | +1.828 |
coinc | +1.800 |
Neg logit contributions | |
leys | -1.705 |
luaj | -1.685 |
bri | -1.563 |
nen | -1.554 |
ahime | -1.537 |
Token | ar |
Token ID | 283 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
leys | +2.782 |
luaj | +2.707 |
bri | +2.643 |
nen | +2.611 |
jin | +2.580 |
Neg logit contributions | |
gdala | -3.355 |
ICAN | -2.753 |
amination | -2.649 |
Magikarp | -2.641 |
INE | -2.610 |
Token | ne |
Token ID | 710 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
leys | +1.162 |
luaj | +1.145 |
bri | +1.093 |
nen | +1.076 |
jin | +1.063 |
Neg logit contributions | |
gdala | -1.505 |
ICAN | -1.251 |
amination | -1.215 |
INE | -1.191 |
Magikarp | -1.178 |
Token | ki |
Token ID | 47748 |
Feature activation | +7.56e+00 |
Pos logit contributions | |
leys | +2.113 |
luaj | +2.065 |
bri | +2.004 |
nen | +1.970 |
jin | +1.940 |
Neg logit contributions | |
gdala | -2.981 |
ICAN | -2.475 |
amination | -2.400 |
Magikarp | -2.365 |
INE | -2.361 |
Token | jar |
Token ID | 17379 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
leys | +5.064 |
bri | +4.907 |
luaj | +4.866 |
nen | +4.764 |
jin | +4.715 |
Neg logit contributions | |
gdala | -6.996 |
ICAN | -5.741 |
amination | -5.550 |
Magikarp | -5.547 |
renheit | -5.469 |
Token | urat |
Token ID | 39928 |
Feature activation | +5.24e+00 |
Pos logit contributions | |
leys | +0.410 |
luaj | +0.405 |
bri | +0.387 |
nen | +0.379 |
jin | +0.375 |
Neg logit contributions | |
gdala | -0.556 |
ICAN | -0.460 |
amination | -0.448 |
INE | -0.440 |
Magikarp | -0.434 |
Token | n |
Token ID | 299 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
leys | +3.522 |
luaj | +3.426 |
bri | +3.373 |
nen | +3.314 |
jin | +3.264 |
Neg logit contributions | |
gdala | -4.867 |
ICAN | -4.024 |
amination | -3.884 |
Magikarp | -3.878 |
INE | -3.819 |
Token | ahi |
Token ID | 32810 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
leys | +1.782 |
luaj | +1.730 |
bri | +1.673 |
nen | +1.641 |
jin | +1.612 |
Neg logit contributions | |
gdala | -3.255 |
ICAN | -2.755 |
amination | -2.677 |
Magikarp | -2.651 |
INE | -2.639 |
Token | ha |
Token ID | 387 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
leys | +2.900 |
luaj | +2.823 |
bri | +2.769 |
nen | +2.714 |
jin | +2.677 |
Neg logit contributions | |
gdala | -4.127 |
ICAN | -3.424 |
amination | -3.320 |
Magikarp | -3.286 |
INE | -3.260 |
Token | i |
Token ID | 72 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
leys | +2.155 |
luaj | +2.112 |
bri | +2.066 |
nen | +2.037 |
jin | +2.013 |
Neg logit contributions | |
gdala | -2.101 |
ICAN | -1.676 |
amination | -1.614 |
Magikarp | -1.589 |
INE | -1.580 |
Token | , |
Token ID | 11 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
leys | +2.606 |
luaj | +2.539 |
bri | +2.490 |
nen | +2.438 |
jin | +2.406 |
Neg logit contributions | |
gdala | -3.692 |
ICAN | -3.059 |
amination | -2.967 |
Magikarp | -2.937 |
INE | -2.916 |
Token | year |
Token ID | 614 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
gdala | +1.458 |
ICAN | +1.231 |
INE | +1.193 |
amination | +1.189 |
Magikarp | +1.162 |
Neg logit contributions | |
leys | -0.983 |
luaj | -0.975 |
nen | -0.919 |
bri | -0.908 |
jin | -0.898 |
Token | and |
Token ID | 290 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
gdala | +1.630 |
ICAN | +1.345 |
amination | +1.286 |
INE | +1.276 |
Magikarp | +1.268 |
Neg logit contributions | |
leys | -1.370 |
luaj | -1.341 |
bri | -1.294 |
nen | -1.288 |
jin | -1.256 |
Token | 0 |
Token ID | 657 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
gdala | +0.347 |
ICAN | +0.280 |
amination | +0.272 |
INE | +0.266 |
Magikarp | +0.266 |
Neg logit contributions | |
leys | -0.340 |
luaj | -0.335 |
bri | -0.324 |
nen | -0.321 |
jin | -0.315 |
Token | . |
Token ID | 13 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
gdala | +0.964 |
ICAN | +0.789 |
amination | +0.762 |
INE | +0.747 |
Magikarp | +0.746 |
Neg logit contributions | |
leys | -0.851 |
luaj | -0.830 |
bri | -0.810 |
nen | -0.795 |
jin | -0.784 |
Token | 5 |
Token ID | 20 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
gdala | +0.778 |
ICAN | +0.636 |
amination | +0.606 |
INE | +0.606 |
Magikarp | +0.598 |
Neg logit contributions | |
leys | -0.728 |
luaj | -0.717 |
bri | -0.702 |
nen | -0.683 |
ahime | -0.679 |
Token | per |
Token ID | 583 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
gdala | +1.214 |
ICAN | +0.974 |
amination | +0.936 |
INE | +0.923 |
Magikarp | +0.916 |
Neg logit contributions | |
leys | -1.377 |
luaj | -1.353 |
bri | -1.304 |
nen | -1.303 |
ahime | -1.284 |
Token | cent |
Token ID | 1247 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
leys | +0.901 |
luaj | +0.878 |
bri | +0.857 |
nen | +0.837 |
jin | +0.823 |
Neg logit contributions | |
gdala | -1.577 |
ICAN | -1.329 |
amination | -1.288 |
Magikarp | -1.281 |
INE | -1.269 |
Token | for |
Token ID | 329 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
leys | +0.578 |
luaj | +0.567 |
bri | +0.550 |
nen | +0.543 |
jin | +0.536 |
Neg logit contributions | |
gdala | -0.613 |
ICAN | -0.497 |
amination | -0.480 |
Magikarp | -0.470 |
INE | -0.470 |
Token | this |
Token ID | 428 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
leys | +0.853 |
luaj | +0.837 |
bri | +0.812 |
nen | +0.802 |
jin | +0.791 |
Neg logit contributions | |
gdala | -0.919 |
ICAN | -0.745 |
amination | -0.720 |
INE | -0.707 |
Magikarp | -0.705 |
Token | year |
Token ID | 614 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
leys | +0.669 |
luaj | +0.653 |
bri | +0.626 |
nen | +0.620 |
jin | +0.610 |
Neg logit contributions | |
gdala | -1.078 |
ICAN | -0.907 |
amination | -0.881 |
INE | -0.869 |
Magikarp | -0.863 |
Token | . |
Token ID | 13 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
gdala | +0.956 |
ICAN | +0.786 |
amination | +0.756 |
INE | +0.745 |
Magikarp | +0.740 |
Neg logit contributions | |
leys | -0.794 |
luaj | -0.778 |
bri | -0.753 |
nen | -0.746 |
jin | -0.730 |
Token |
|
Token ID | 198 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
leys | +0.083 |
luaj | +0.081 |
bri | +0.078 |
nen | +0.077 |
jin | +0.076 |
Neg logit contributions | |
gdala | -0.123 |
ICAN | -0.102 |
amination | -0.099 |
Magikarp | -0.098 |
INE | -0.098 |
Token | But |
Token ID | 1537 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
leys | +0.103 |
luaj | +0.101 |
bri | +0.099 |
nen | +0.097 |
ahime | +0.096 |
Neg logit contributions | |
gdala | -0.107 |
ICAN | -0.087 |
amination | -0.083 |
INE | -0.082 |
Magikarp | -0.082 |
Token | at |
Token ID | 379 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
gdala | +0.671 |
ICAN | +0.543 |
amination | +0.527 |
INE | +0.519 |
Magikarp | +0.511 |
Neg logit contributions | |
leys | -0.630 |
luaj | -0.626 |
bri | -0.601 |
nen | -0.594 |
ahime | -0.593 |
Token | the |
Token ID | 262 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
leys | +1.032 |
luaj | +1.013 |
bri | +0.979 |
nen | +0.967 |
jin | +0.957 |
Neg logit contributions | |
gdala | -1.197 |
ICAN | -0.980 |
amination | -0.947 |
INE | -0.931 |
Magikarp | -0.923 |
Token | Conservative |
Token ID | 11132 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
leys | +0.086 |
luaj | +0.084 |
bri | +0.081 |
nen | +0.081 |
ahime | +0.080 |
Neg logit contributions | |
gdala | -0.096 |
ICAN | -0.078 |
amination | -0.075 |
INE | -0.075 |
Magikarp | -0.073 |
Token | Political |
Token ID | 14611 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
leys | +2.749 |
luaj | +2.646 |
bri | +2.575 |
nen | +2.530 |
jin | +2.498 |
Neg logit contributions | |
gdala | -4.573 |
ICAN | -3.827 |
amination | -3.741 |
Magikarp | -3.686 |
renheit | -3.671 |
Token | Action |
Token ID | 7561 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
leys | +1.550 |
luaj | +1.536 |
bri | +1.483 |
nen | +1.473 |
ahime | +1.460 |
Neg logit contributions | |
gdala | -1.338 |
ICAN | -1.056 |
amination | -0.994 |
INE | -0.994 |
Magikarp | -0.984 |
Token | Conference |
Token ID | 8785 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
gdala | +0.404 |
ICAN | +0.345 |
amination | +0.331 |
INE | +0.329 |
Magikarp | +0.328 |
Neg logit contributions | |
leys | -0.229 |
luaj | -0.228 |
bri | -0.217 |
nen | -0.214 |
ahime | -0.210 |
Token | in |
Token ID | 287 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
leys | +1.474 |
luaj | +1.442 |
bri | +1.410 |
nen | +1.390 |
jin | +1.372 |
Neg logit contributions | |
gdala | -1.545 |
ICAN | -1.243 |
amination | -1.201 |
Magikarp | -1.183 |
INE | -1.177 |
Token | February |
Token ID | 3945 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
gdala | +0.696 |
ICAN | +0.566 |
amination | +0.539 |
INE | +0.533 |
Magikarp | +0.530 |
Neg logit contributions | |
leys | -0.681 |
luaj | -0.673 |
bri | -0.648 |
nen | -0.647 |
ahime | -0.637 |
Token | , |
Token ID | 11 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
gdala | +1.050 |
ICAN | +0.862 |
amination | +0.823 |
INE | +0.815 |
coinc | +0.809 |
Neg logit contributions | |
leys | -0.912 |
luaj | -0.899 |
bri | -0.864 |
nen | -0.853 |
ahime | -0.847 |
Token | uffy |
Token ID | 15352 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
gdala | +0.247 |
ICAN | +0.205 |
amination | +0.197 |
INE | +0.197 |
Magikarp | +0.193 |
Neg logit contributions | |
leys | -0.201 |
luaj | -0.200 |
bri | -0.194 |
nen | -0.189 |
ahime | -0.185 |
Token | Am |
Token ID | 1703 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
gdala | +1.098 |
ICAN | +0.896 |
amination | +0.874 |
INE | +0.855 |
Magikarp | +0.855 |
Neg logit contributions | |
leys | -0.822 |
luaj | -0.819 |
bri | -0.793 |
nen | -0.775 |
ahime | -0.760 |
Token | i |
Token ID | 72 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
leys | +0.223 |
luaj | +0.222 |
bri | +0.216 |
nen | +0.211 |
jin | +0.207 |
Neg logit contributions | |
gdala | -0.277 |
ICAN | -0.225 |
amination | -0.219 |
INE | -0.214 |
renheit | -0.211 |
Token | Y |
Token ID | 575 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
leys | +1.651 |
luaj | +1.619 |
bri | +1.580 |
nen | +1.557 |
jin | +1.537 |
Neg logit contributions | |
gdala | -1.694 |
ICAN | -1.362 |
amination | -1.313 |
Magikarp | -1.291 |
INE | -1.287 |
Token | umi |
Token ID | 12994 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
leys | +2.339 |
luaj | +2.283 |
bri | +2.221 |
nen | +2.191 |
jin | +2.171 |
Neg logit contributions | |
gdala | -3.039 |
ICAN | -2.504 |
amination | -2.423 |
Magikarp | -2.394 |
INE | -2.381 |
Token | ". |
Token ID | 1911 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
leys | +1.918 |
luaj | +1.872 |
bri | +1.821 |
nen | +1.792 |
jin | +1.767 |
Neg logit contributions | |
gdala | -2.620 |
ICAN | -2.170 |
amination | -2.101 |
Magikarp | -2.073 |
INE | -2.067 |
Token | He |
Token ID | 679 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
leys | +1.132 |
luaj | +1.107 |
bri | +1.076 |
nen | +1.058 |
jin | +1.041 |
Neg logit contributions | |
gdala | -1.558 |
ICAN | -1.291 |
amination | -1.250 |
Magikarp | -1.233 |
INE | -1.231 |
Token | is |
Token ID | 318 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
leys | +0.478 |
luaj | +0.472 |
bri | +0.457 |
nen | +0.448 |
jin | +0.441 |
Neg logit contributions | |
gdala | -0.614 |
ICAN | -0.506 |
amination | -0.490 |
INE | -0.483 |
Magikarp | -0.479 |
Token | currently |
Token ID | 3058 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
gdala | +0.167 |
ICAN | +0.135 |
amination | +0.131 |
INE | +0.129 |
Magikarp | +0.128 |
Neg logit contributions | |
leys | -0.156 |
luaj | -0.155 |
bri | -0.149 |
nen | -0.147 |
jin | -0.145 |
Token | serving |
Token ID | 7351 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
leys | +3.275 |
luaj | +3.183 |
bri | +3.131 |
nen | +3.091 |
jin | +3.048 |
Neg logit contributions | |
gdala | -3.787 |
ICAN | -3.072 |
amination | -2.965 |
Magikarp | -2.934 |
INE | -2.903 |
Token | as |
Token ID | 355 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
gdala | +0.369 |
ICAN | +0.300 |
amination | +0.289 |
INE | +0.284 |
Magikarp | +0.284 |
Neg logit contributions | |
leys | -0.372 |
luaj | -0.370 |
bri | -0.354 |
nen | -0.352 |
jin | -0.345 |
Token | want |
Token ID | 765 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
gdala | +0.513 |
ICAN | +0.421 |
amination | +0.409 |
INE | +0.405 |
Magikarp | +0.401 |
Neg logit contributions | |
leys | -0.392 |
luaj | -0.385 |
bri | -0.369 |
nen | -0.368 |
ahime | -0.361 |
Token | this |
Token ID | 428 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
leys | +1.729 |
luaj | +1.689 |
bri | +1.651 |
nen | +1.624 |
jin | +1.601 |
Neg logit contributions | |
gdala | -2.100 |
ICAN | -1.721 |
amination | -1.658 |
Magikarp | -1.638 |
INE | -1.631 |
Token | extr |
Token ID | 22820 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
leys | +1.542 |
luaj | +1.511 |
bri | +1.476 |
nen | +1.452 |
jin | +1.434 |
Neg logit contributions | |
gdala | -1.761 |
ICAN | -1.433 |
amination | -1.382 |
Magikarp | -1.361 |
INE | -1.358 |
Token | usion |
Token ID | 4241 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
gdala | +2.361 |
ICAN | +1.749 |
amination | +1.731 |
INE | +1.641 |
renheit | +1.572 |
Neg logit contributions | |
leys | -3.782 |
luaj | -3.711 |
bri | -3.685 |
nen | -3.598 |
ahime | -3.535 |
Token | to |
Token ID | 284 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
gdala | +2.185 |
ICAN | +1.745 |
amination | +1.729 |
INE | +1.698 |
coinc | +1.679 |
Neg logit contributions | |
leys | -2.090 |
luaj | -2.049 |
bri | -1.960 |
nen | -1.940 |
ahime | -1.927 |
Token | change |
Token ID | 1487 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
gdala | +0.867 |
ICAN | +0.715 |
amination | +0.698 |
INE | +0.691 |
coinc | +0.689 |
Neg logit contributions | |
leys | -0.666 |
luaj | -0.656 |
bri | -0.622 |
nen | -0.622 |
ahime | -0.616 |
Token | over |
Token ID | 625 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
leys | +1.743 |
luaj | +1.698 |
bri | +1.672 |
nen | +1.641 |
jin | +1.625 |
Neg logit contributions | |
gdala | -1.994 |
ICAN | -1.622 |
amination | -1.554 |
Magikarp | -1.536 |
INE | -1.525 |
Token | time |
Token ID | 640 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
gdala | +0.142 |
ICAN | +0.112 |
amination | +0.109 |
Magikarp | +0.106 |
INE | +0.106 |
Neg logit contributions | |
leys | -0.157 |
luaj | -0.155 |
bri | -0.150 |
nen | -0.148 |
jin | -0.146 |
Token | . |
Token ID | 13 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
gdala | +1.738 |
ICAN | +1.402 |
amination | +1.372 |
INE | +1.343 |
coinc | +1.333 |
Neg logit contributions | |
leys | -1.622 |
luaj | -1.616 |
bri | -1.547 |
nen | -1.532 |
ahime | -1.513 |
Token | When |
Token ID | 1649 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
gdala | +0.458 |
ICAN | +0.377 |
amination | +0.366 |
INE | +0.363 |
Magikarp | +0.359 |
Neg logit contributions | |
leys | -0.346 |
luaj | -0.337 |
bri | -0.327 |
nen | -0.323 |
ahime | -0.320 |
Token | you |
Token ID | 345 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
leys | +0.902 |
luaj | +0.883 |
bri | +0.860 |
nen | +0.847 |
jin | +0.837 |
Neg logit contributions | |
gdala | -0.967 |
ICAN | -0.781 |
amination | -0.756 |
Magikarp | -0.742 |
INE | -0.741 |
Token | press |
Token ID | 1803 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
gdala | +0.899 |
ICAN | +0.741 |
amination | +0.713 |
INE | +0.708 |
Magikarp | +0.698 |
Neg logit contributions | |
leys | -0.765 |
luaj | -0.751 |
bri | -0.719 |
nen | -0.713 |
ahime | -0.701 |
Token | secretary |
Token ID | 7705 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
leys | +0.965 |
luaj | +0.940 |
bri | +0.909 |
nen | +0.892 |
jin | +0.876 |
Neg logit contributions | |
gdala | -1.653 |
ICAN | -1.393 |
amination | -1.354 |
Magikarp | -1.337 |
INE | -1.334 |
Token | . |
Token ID | 13 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
leys | +0.090 |
luaj | +0.088 |
bri | +0.085 |
nen | +0.084 |
ahime | +0.083 |
Neg logit contributions | |
gdala | -0.104 |
ICAN | -0.085 |
amination | -0.082 |
INE | -0.081 |
Magikarp | -0.081 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
leys | +0.054 |
luaj | +0.053 |
bri | +0.051 |
nen | +0.050 |
jin | +0.050 |
Neg logit contributions | |
gdala | -0.067 |
ICAN | -0.055 |
amination | -0.053 |
INE | -0.053 |
Magikarp | -0.052 |
Token | AL |
Token ID | 1847 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
leys | +1.667 |
luaj | +1.633 |
bri | +1.589 |
nen | +1.569 |
jin | +1.550 |
Neg logit contributions | |
gdala | -1.862 |
ICAN | -1.508 |
amination | -1.459 |
Magikarp | -1.433 |
INE | -1.427 |
Token | B |
Token ID | 33 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
gdala | +0.499 |
ICAN | +0.399 |
amination | +0.377 |
INE | +0.377 |
Magikarp | +0.367 |
Neg logit contributions | |
leys | -0.566 |
luaj | -0.559 |
bri | -0.548 |
nen | -0.541 |
jin | -0.531 |
Token | ION |
Token ID | 2849 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
gdala | +1.606 |
ICAN | +1.425 |
INE | +1.393 |
amination | +1.347 |
Magikarp | +1.310 |
Neg logit contributions | |
luaj | -0.755 |
leys | -0.752 |
bri | -0.710 |
nen | -0.694 |
oshenko | -0.677 |
Token | are |
Token ID | 389 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
gdala | +0.664 |
ICAN | +0.549 |
INE | +0.525 |
amination | +0.518 |
Magikarp | +0.503 |
Neg logit contributions | |
leys | -0.580 |
luaj | -0.574 |
bri | -0.552 |
nen | -0.542 |
ahime | -0.540 |
Token | delighted |
Token ID | 20707 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
gdala | +0.853 |
ICAN | +0.696 |
amination | +0.669 |
INE | +0.668 |
Magikarp | +0.660 |
Neg logit contributions | |
leys | -0.740 |
luaj | -0.734 |
bri | -0.704 |
nen | -0.696 |
ahime | -0.691 |
Token | to |
Token ID | 284 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
gdala | +0.439 |
ICAN | +0.357 |
amination | +0.343 |
INE | +0.341 |
Magikarp | +0.338 |
Neg logit contributions | |
leys | -0.397 |
luaj | -0.390 |
bri | -0.379 |
nen | -0.374 |
jin | -0.369 |
Token | announce |
Token ID | 5453 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
gdala | +0.446 |
ICAN | +0.361 |
INE | +0.349 |
amination | +0.348 |
coinc | +0.342 |
Neg logit contributions | |
leys | -0.417 |
luaj | -0.416 |
bri | -0.397 |
nen | -0.395 |
ahime | -0.395 |
Token | � |
Token ID | 447 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
leys | +2.420 |
luaj | +2.365 |
bri | +2.308 |
nen | +2.275 |
jin | +2.243 |
Neg logit contributions | |
gdala | -2.856 |
ICAN | -2.326 |
amination | -2.255 |
Magikarp | -2.225 |
INE | -2.208 |
Token | � |
Token ID | 247 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
leys | +0.347 |
luaj | +0.340 |
bri | +0.331 |
nen | +0.326 |
jin | +0.322 |
Neg logit contributions | |
gdala | -0.393 |
ICAN | -0.320 |
amination | -0.308 |
Magikarp | -0.303 |
INE | -0.303 |
Token | s |
Token ID | 82 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
leys | +0.032 |
luaj | +0.032 |
bri | +0.031 |
nen | +0.030 |
jin | +0.030 |
Neg logit contributions | |
gdala | -0.037 |
ICAN | -0.030 |
amination | -0.029 |
INE | -0.029 |
Magikarp | -0.029 |
Token | opponent |
Token ID | 6125 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
leys | +1.440 |
luaj | +1.415 |
bri | +1.370 |
nen | +1.353 |
jin | +1.334 |
Neg logit contributions | |
gdala | -1.684 |
ICAN | -1.376 |
amination | -1.331 |
INE | -1.312 |
Magikarp | -1.306 |
Token | . |
Token ID | 13 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
leys | +0.860 |
luaj | +0.843 |
bri | +0.820 |
nen | +0.808 |
jin | +0.797 |
Neg logit contributions | |
gdala | -0.965 |
ICAN | -0.783 |
amination | -0.757 |
INE | -0.744 |
Magikarp | -0.743 |
Token | Take |
Token ID | 7214 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
leys | +0.147 |
luaj | +0.142 |
bri | +0.139 |
nen | +0.136 |
ahime | +0.135 |
Neg logit contributions | |
gdala | -0.194 |
ICAN | -0.161 |
amination | -0.155 |
INE | -0.155 |
Magikarp | -0.152 |
Token | a |
Token ID | 257 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
leys | +0.583 |
luaj | +0.571 |
bri | +0.549 |
nen | +0.545 |
ahime | +0.533 |
Neg logit contributions | |
gdala | -0.666 |
ICAN | -0.541 |
amination | -0.529 |
INE | -0.518 |
Magikarp | -0.509 |
Token | look |
Token ID | 804 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
leys | +0.977 |
luaj | +0.957 |
bri | +0.916 |
nen | +0.906 |
jin | +0.885 |
Neg logit contributions | |
gdala | -1.569 |
ICAN | -1.312 |
amination | -1.281 |
INE | -1.261 |
Magikarp | -1.255 |
Token | . |
Token ID | 13 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
leys | +2.288 |
luaj | +2.239 |
bri | +2.191 |
nen | +2.155 |
jin | +2.131 |
Neg logit contributions | |
gdala | -2.505 |
ICAN | -2.033 |
amination | -1.955 |
Magikarp | -1.934 |
INE | -1.920 |
Token |
|
Token ID | 198 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
leys | +0.391 |
luaj | +0.379 |
bri | +0.370 |
nen | +0.363 |
ahime | +0.358 |
Neg logit contributions | |
gdala | -0.524 |
ICAN | -0.434 |
amination | -0.421 |
INE | -0.415 |
Magikarp | -0.411 |
Token |
|
Token ID | 198 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
leys | +0.313 |
luaj | +0.305 |
bri | +0.295 |
nen | +0.292 |
jin | +0.288 |
Neg logit contributions | |
gdala | -0.475 |
ICAN | -0.396 |
amination | -0.385 |
Magikarp | -0.381 |
INE | -0.377 |
Token | , |
Token ID | 11 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
leys | +2.758 |
luaj | +2.669 |
bri | +2.617 |
nen | +2.562 |
jin | +2.536 |
Neg logit contributions | |
gdala | -3.591 |
ICAN | -2.963 |
amination | -2.856 |
Magikarp | -2.846 |
INE | -2.818 |
Token | the |
Token ID | 262 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
leys | +0.234 |
luaj | +0.230 |
bri | +0.221 |
nen | +0.220 |
jin | +0.216 |
Neg logit contributions | |
gdala | -0.296 |
ICAN | -0.244 |
amination | -0.235 |
Magikarp | -0.233 |
INE | -0.231 |
Token | Rams |
Token ID | 16077 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
gdala | +0.469 |
ICAN | +0.377 |
amination | +0.364 |
INE | +0.356 |
Magikarp | +0.354 |
Neg logit contributions | |
leys | -0.471 |
luaj | -0.464 |
nen | -0.451 |
bri | -0.448 |
ahime | -0.440 |
Token | ran |
Token ID | 4966 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
gdala | +3.086 |
ICAN | +2.528 |
coinc | +2.465 |
INE | +2.442 |
amination | +2.423 |
Neg logit contributions | |
luaj | -2.150 |
leys | -2.117 |
nen | -2.030 |
ahime | -2.022 |
bri | -1.996 |
Token | out |
Token ID | 503 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
leys | +2.352 |
luaj | +2.297 |
bri | +2.254 |
nen | +2.212 |
jin | +2.185 |
Neg logit contributions | |
gdala | -2.594 |
ICAN | -2.101 |
amination | -2.025 |
Magikarp | -1.996 |
INE | -1.988 |
Token | the |
Token ID | 262 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
gdala | +0.369 |
ICAN | +0.299 |
amination | +0.289 |
Magikarp | +0.284 |
INE | +0.283 |
Neg logit contributions | |
leys | -0.339 |
luaj | -0.333 |
bri | -0.324 |
nen | -0.319 |
jin | -0.315 |
Token | clock |
Token ID | 8801 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
leys | +0.591 |
luaj | +0.583 |
bri | +0.565 |
nen | +0.564 |
jin | +0.554 |
Neg logit contributions | |
gdala | -0.483 |
ICAN | -0.378 |
amination | -0.362 |
Magikarp | -0.353 |
INE | -0.353 |
Token | and |
Token ID | 290 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
gdala | +0.350 |
ICAN | +0.282 |
amination | +0.275 |
INE | +0.269 |
coinc | +0.265 |
Neg logit contributions | |
leys | -0.334 |
luaj | -0.331 |
bri | -0.319 |
nen | -0.315 |
ahime | -0.312 |
Token | celebrated |
Token ID | 13943 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
leys | +0.396 |
luaj | +0.393 |
nen | +0.375 |
bri | +0.372 |
ahime | +0.365 |
Neg logit contributions | |
gdala | -0.548 |
ICAN | -0.454 |
amination | -0.438 |
INE | -0.434 |
Magikarp | -0.433 |
Token | their |
Token ID | 511 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
gdala | +2.038 |
ICAN | +1.644 |
amination | +1.576 |
INE | +1.572 |
coinc | +1.569 |
Neg logit contributions | |
leys | -2.105 |
luaj | -2.080 |
nen | -1.995 |
ahime | -1.979 |
bri | -1.972 |
Token | first |
Token ID | 717 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
gdala | +0.664 |
ICAN | +0.544 |
amination | +0.518 |
INE | +0.517 |
Magikarp | +0.511 |
Neg logit contributions | |
leys | -0.620 |
luaj | -0.601 |
nen | -0.583 |
bri | -0.580 |
ahime | -0.574 |
Token | sou |
Token ID | 24049 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
leys | +0.754 |
luaj | +0.742 |
bri | +0.714 |
nen | +0.710 |
jin | +0.699 |
Neg logit contributions | |
gdala | -0.916 |
ICAN | -0.752 |
amination | -0.728 |
INE | -0.719 |
Magikarp | -0.715 |
Token | ps |
Token ID | 862 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
leys | +3.347 |
luaj | +3.207 |
bri | +3.132 |
jin | +3.081 |
nen | +3.077 |
Neg logit contributions | |
gdala | -4.021 |
ICAN | -3.332 |
Magikarp | -3.209 |
amination | -3.163 |
INE | -3.115 |
Token | , |
Token ID | 11 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
leys | +0.658 |
luaj | +0.645 |
bri | +0.625 |
nen | +0.617 |
jin | +0.607 |
Neg logit contributions | |
gdala | -0.828 |
ICAN | -0.680 |
amination | -0.659 |
INE | -0.649 |
Magikarp | -0.648 |
Token | and |
Token ID | 290 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
leys | +0.907 |
luaj | +0.891 |
bri | +0.861 |
nen | +0.852 |
jin | +0.839 |
Neg logit contributions | |
gdala | -1.140 |
ICAN | -0.937 |
amination | -0.907 |
INE | -0.893 |
Magikarp | -0.892 |
Token | beans |
Token ID | 16567 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
leys | +0.289 |
luaj | +0.286 |
bri | +0.272 |
nen | +0.272 |
ahime | +0.270 |
Neg logit contributions | |
gdala | -0.340 |
ICAN | -0.278 |
amination | -0.269 |
INE | -0.266 |
Magikarp | -0.262 |
Token | . |
Token ID | 13 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
gdala | +0.602 |
ICAN | +0.490 |
amination | +0.475 |
INE | +0.469 |
Magikarp | +0.463 |
Neg logit contributions | |
leys | -0.533 |
luaj | -0.527 |
nen | -0.504 |
bri | -0.503 |
ahime | -0.494 |
Token | The |
Token ID | 383 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
leys | +0.677 |
luaj | +0.664 |
bri | +0.644 |
nen | +0.633 |
ahime | +0.623 |
Neg logit contributions | |
gdala | -0.919 |
ICAN | -0.763 |
amination | -0.733 |
INE | -0.731 |
Magikarp | -0.729 |
Token | last |
Token ID | 938 |
Feature activation | +6.54e-02 |
Pos logit contributions | |
leys | +1.146 |
luaj | +1.124 |
bri | +1.092 |
nen | +1.080 |
jin | +1.063 |
Neg logit contributions | |
gdala | -1.284 |
ICAN | -1.044 |
amination | -1.008 |
Magikarp | -0.992 |
INE | -0.991 |
Token | time |
Token ID | 640 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
leys | +0.047 |
luaj | +0.047 |
bri | +0.045 |
nen | +0.045 |
jin | +0.044 |
Neg logit contributions | |
gdala | -0.057 |
ICAN | -0.047 |
amination | -0.046 |
INE | -0.045 |
Magikarp | -0.045 |
Token | he |
Token ID | 339 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
gdala | +1.747 |
ICAN | +1.418 |
INE | +1.347 |
amination | +1.346 |
Magikarp | +1.324 |
Neg logit contributions | |
leys | -1.850 |
luaj | -1.831 |
nen | -1.756 |
bri | -1.738 |
ahime | -1.737 |
Token | told |
Token ID | 1297 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
leys | +0.214 |
luaj | +0.212 |
nen | +0.201 |
bri | +0.201 |
ahime | +0.198 |
Neg logit contributions | |
gdala | -0.273 |
ICAN | -0.225 |
amination | -0.217 |
INE | -0.215 |
Magikarp | -0.212 |
Token | had |
Token ID | 550 |
Feature activation | -5.02e-02 |
Pos logit contributions | |
gdala | +0.216 |
ICAN | +0.176 |
amination | +0.172 |
INE | +0.169 |
coinc | +0.169 |
Neg logit contributions | |
leys | -0.159 |
luaj | -0.158 |
nen | -0.150 |
bri | -0.149 |
ahime | -0.147 |
Token | intended |
Token ID | 5292 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
gdala | +0.045 |
ICAN | +0.037 |
amination | +0.036 |
INE | +0.035 |
coinc | +0.035 |
Neg logit contributions | |
leys | -0.036 |
luaj | -0.035 |
bri | -0.033 |
nen | -0.033 |
ahime | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
gdala | +2.774 |
ICAN | +2.256 |
amination | +2.193 |
INE | +2.138 |
Magikarp | +2.127 |
Neg logit contributions | |
leys | -2.659 |
luaj | -2.648 |
bri | -2.529 |
nen | -2.526 |
ahime | -2.505 |
Token | hit |
Token ID | 2277 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
gdala | +0.741 |
ICAN | +0.609 |
amination | +0.586 |
INE | +0.580 |
coinc | +0.578 |
Neg logit contributions | |
leys | -0.618 |
luaj | -0.616 |
nen | -0.582 |
bri | -0.575 |
ahime | -0.573 |
Token | a |
Token ID | 257 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
leys | +0.088 |
luaj | +0.088 |
bri | +0.084 |
nen | +0.083 |
ahime | +0.082 |
Neg logit contributions | |
gdala | -0.101 |
ICAN | -0.082 |
amination | -0.079 |
INE | -0.078 |
Magikarp | -0.077 |
Token | building |
Token ID | 2615 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
leys | +0.519 |
luaj | +0.509 |
bri | +0.490 |
nen | +0.486 |
jin | +0.478 |
Neg logit contributions | |
gdala | -0.636 |
ICAN | -0.522 |
amination | -0.504 |
INE | -0.497 |
Magikarp | -0.492 |
Token | nearby |
Token ID | 6716 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
gdala | +1.547 |
ICAN | +1.238 |
amination | +1.203 |
coinc | +1.194 |
INE | +1.185 |
Neg logit contributions | |
leys | -1.500 |
luaj | -1.494 |
nen | -1.415 |
bri | -1.412 |
ahime | -1.401 |
Token | which |
Token ID | 543 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
leys | +1.396 |
luaj | +1.370 |
bri | +1.331 |
nen | +1.314 |
jin | +1.294 |
Neg logit contributions | |
gdala | -1.626 |
ICAN | -1.325 |
amination | -1.280 |
INE | -1.257 |
Magikarp | -1.257 |
Token | was |
Token ID | 373 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
leys | +1.244 |
luaj | +1.226 |
bri | +1.182 |
nen | +1.168 |
jin | +1.149 |
Neg logit contributions | |
gdala | -1.657 |
ICAN | -1.366 |
amination | -1.325 |
INE | -1.307 |
Magikarp | -1.297 |
Token | being |
Token ID | 852 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
gdala | +0.340 |
ICAN | +0.277 |
amination | +0.267 |
INE | +0.263 |
Magikarp | +0.262 |
Neg logit contributions | |
leys | -0.299 |
luaj | -0.294 |
bri | -0.283 |
nen | -0.281 |
jin | -0.276 |
Token | used |
Token ID | 973 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
leys | +0.404 |
luaj | +0.396 |
bri | +0.377 |
nen | +0.374 |
jin | +0.365 |
Neg logit contributions | |
gdala | -0.739 |
ICAN | -0.626 |
amination | -0.608 |
INE | -0.601 |
Magikarp | -0.595 |
Token | re |
Token ID | 260 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
leys | +0.489 |
luaj | +0.482 |
bri | +0.467 |
nen | +0.457 |
jin | +0.452 |
Neg logit contributions | |
gdala | -0.628 |
ICAN | -0.516 |
amination | -0.501 |
INE | -0.495 |
Magikarp | -0.490 |
Token | now |
Token ID | 783 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
gdala | +1.671 |
ICAN | +1.344 |
INE | +1.292 |
amination | +1.286 |
Magikarp | +1.281 |
Neg logit contributions | |
leys | -1.599 |
luaj | -1.580 |
bri | -1.520 |
nen | -1.516 |
jin | -1.484 |
Token | seeing |
Token ID | 4379 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
leys | +2.271 |
luaj | +2.226 |
bri | +2.179 |
nen | +2.144 |
jin | +2.120 |
Neg logit contributions | |
gdala | -2.264 |
ICAN | -1.812 |
amination | -1.747 |
Magikarp | -1.716 |
INE | -1.708 |
Token | it |
Token ID | 340 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
leys | +1.117 |
luaj | +1.099 |
bri | +1.059 |
nen | +1.047 |
jin | +1.034 |
Neg logit contributions | |
gdala | -1.437 |
ICAN | -1.184 |
amination | -1.143 |
INE | -1.129 |
Magikarp | -1.125 |
Token | with |
Token ID | 351 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
leys | +0.512 |
luaj | +0.505 |
bri | +0.488 |
nen | +0.482 |
jin | +0.476 |
Neg logit contributions | |
gdala | -0.554 |
ICAN | -0.447 |
amination | -0.433 |
INE | -0.426 |
Magikarp | -0.423 |
Token | gay |
Token ID | 5650 |
Feature activation | -4.91e+00 |
Pos logit contributions | |
leys | +1.059 |
luaj | +1.037 |
bri | +1.009 |
nen | +0.996 |
jin | +0.982 |
Neg logit contributions | |
gdala | -1.199 |
ICAN | -0.975 |
amination | -0.942 |
Magikarp | -0.925 |
INE | -0.925 |
Token | rights |
Token ID | 2489 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
gdala | +4.300 |
ICAN | +3.551 |
amination | +3.448 |
INE | +3.404 |
coinc | +3.370 |
Neg logit contributions | |
leys | -3.449 |
luaj | -3.370 |
nen | -3.208 |
bri | -3.174 |
ahime | -3.172 |
Token | . |
Token ID | 13 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
leys | +1.139 |
luaj | +1.114 |
bri | +1.087 |
nen | +1.068 |
jin | +1.053 |
Neg logit contributions | |
gdala | -1.415 |
ICAN | -1.161 |
amination | -1.123 |
Magikarp | -1.107 |
INE | -1.103 |
Token | Our |
Token ID | 3954 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
leys | +0.277 |
luaj | +0.270 |
bri | +0.263 |
nen | +0.259 |
jin | +0.255 |
Neg logit contributions | |
gdala | -0.341 |
ICAN | -0.280 |
amination | -0.270 |
INE | -0.266 |
Magikarp | -0.266 |
Token | moral |
Token ID | 6573 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
leys | +0.636 |
luaj | +0.624 |
bri | +0.604 |
nen | +0.596 |
jin | +0.588 |
Neg logit contributions | |
gdala | -0.823 |
ICAN | -0.679 |
amination | -0.655 |
INE | -0.646 |
Magikarp | -0.644 |
Token | values |
Token ID | 3815 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
gdala | +0.103 |
ICAN | +0.084 |
amination | +0.081 |
INE | +0.080 |
Magikarp | +0.079 |
Neg logit contributions | |
leys | -0.087 |
luaj | -0.086 |
nen | -0.082 |
bri | -0.082 |
jin | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
gdala | +2.422 |
ICAN | +1.927 |
amination | +1.865 |
INE | +1.833 |
Magikarp | +1.800 |
Neg logit contributions | |
leys | -2.554 |
luaj | -2.517 |
bri | -2.443 |
nen | -2.410 |
jin | -2.386 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
gdala | +0.522 |
ICAN | +0.434 |
amination | +0.421 |
INE | +0.417 |
Magikarp | +0.415 |
Neg logit contributions | |
leys | -0.370 |
luaj | -0.363 |
bri | -0.351 |
nen | -0.344 |
ahime | -0.340 |
Token | After |
Token ID | 3260 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
leys | +1.174 |
luaj | +1.150 |
bri | +1.122 |
nen | +1.104 |
jin | +1.089 |
Neg logit contributions | |
gdala | -1.304 |
ICAN | -1.059 |
amination | -1.021 |
Magikarp | -1.006 |
INE | -1.004 |
Token | Saturday |
Token ID | 3909 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
leys | +0.193 |
luaj | +0.189 |
bri | +0.184 |
nen | +0.181 |
jin | +0.179 |
Neg logit contributions | |
gdala | -0.206 |
ICAN | -0.166 |
amination | -0.161 |
Magikarp | -0.158 |
INE | -0.158 |
Token | 's |
Token ID | 338 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
gdala | +0.979 |
ICAN | +0.806 |
amination | +0.778 |
INE | +0.768 |
Magikarp | +0.759 |
Neg logit contributions | |
leys | -0.782 |
luaj | -0.779 |
bri | -0.745 |
nen | -0.734 |
ahime | -0.729 |
Token | terrorist |
Token ID | 7417 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
leys | +0.468 |
luaj | +0.458 |
bri | +0.446 |
nen | +0.440 |
jin | +0.433 |
Neg logit contributions | |
gdala | -0.543 |
ICAN | -0.443 |
amination | -0.428 |
Magikarp | -0.421 |
INE | -0.421 |
Token | attacks |
Token ID | 3434 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
gdala | +4.325 |
amination | +3.351 |
ICAN | +3.350 |
coinc | +3.320 |
INE | +3.302 |
Neg logit contributions | |
luaj | -4.704 |
leys | -4.620 |
ahime | -4.359 |
nen | -4.351 |
igans | -4.331 |
Token | in |
Token ID | 287 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
gdala | +1.686 |
ICAN | +1.323 |
amination | +1.287 |
INE | +1.263 |
Magikarp | +1.252 |
Neg logit contributions | |
leys | -1.842 |
luaj | -1.830 |
bri | -1.763 |
nen | -1.743 |
ahime | -1.723 |
Token | London |
Token ID | 3576 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
gdala | +0.931 |
ICAN | +0.752 |
amination | +0.726 |
INE | +0.713 |
Magikarp | +0.711 |
Neg logit contributions | |
leys | -0.869 |
luaj | -0.858 |
bri | -0.829 |
nen | -0.820 |
jin | -0.808 |
Token | left |
Token ID | 1364 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
leys | +0.865 |
luaj | +0.851 |
bri | +0.825 |
nen | +0.812 |
jin | +0.800 |
Neg logit contributions | |
gdala | -1.061 |
ICAN | -0.868 |
amination | -0.840 |
INE | -0.827 |
Magikarp | -0.826 |
Token | seven |
Token ID | 3598 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
gdala | +2.005 |
ICAN | +1.558 |
amination | +1.545 |
coinc | +1.522 |
INE | +1.514 |
Neg logit contributions | |
luaj | -2.264 |
leys | -2.223 |
nen | -2.143 |
ahime | -2.115 |
bri | -2.107 |
Token | ailed |
Token ID | 6255 |
Feature activation | -5.32e+00 |
Pos logit contributions | |
gdala | +1.579 |
ICAN | +1.184 |
amination | +1.131 |
INE | +1.102 |
Magikarp | +1.086 |
Neg logit contributions | |
leys | -2.421 |
luaj | -2.378 |
bri | -2.347 |
nen | -2.309 |
jin | -2.279 |
Token | to |
Token ID | 284 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
gdala | +4.130 |
ICAN | +3.325 |
amination | +3.269 |
INE | +3.205 |
Magikarp | +3.190 |
Neg logit contributions | |
leys | -4.205 |
luaj | -4.055 |
nen | -3.984 |
oshenko | -3.945 |
jin | -3.943 |
Token | $ |
Token ID | 720 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
gdala | +1.808 |
ICAN | +1.442 |
amination | +1.394 |
INE | +1.384 |
Magikarp | +1.360 |
Neg logit contributions | |
leys | -1.881 |
luaj | -1.836 |
nen | -1.783 |
bri | -1.775 |
jin | -1.753 |
Token | ($ |
Token ID | 16763 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
leys | +1.122 |
luaj | +1.098 |
bri | +1.060 |
nen | +1.044 |
jin | +1.031 |
Neg logit contributions | |
gdala | -1.574 |
ICAN | -1.296 |
amination | -1.257 |
Magikarp | -1.244 |
INE | -1.237 |
Token | _. |
Token ID | 44807 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
leys | +0.782 |
luaj | +0.760 |
bri | +0.734 |
nen | +0.722 |
jin | +0.714 |
Neg logit contributions | |
gdala | -1.199 |
ICAN | -0.997 |
amination | -0.968 |
Magikarp | -0.959 |
INE | -0.955 |
Token | Exception |
Token ID | 16922 |
Feature activation | -4.63e+00 |
Pos logit contributions | |
gdala | +1.176 |
ICAN | +0.872 |
amination | +0.815 |
INE | +0.803 |
Magikarp | +0.797 |
Neg logit contributions | |
leys | -2.111 |
luaj | -2.067 |
bri | -2.049 |
nen | -2.022 |
ahime | -1.992 |
Token | . |
Token ID | 13 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
gdala | +3.772 |
ICAN | +3.097 |
amination | +2.915 |
INE | +2.911 |
Magikarp | +2.868 |
Neg logit contributions | |
leys | -3.606 |
luaj | -3.549 |
bri | -3.483 |
ahime | -3.404 |
nen | -3.391 |
Token | Message |
Token ID | 12837 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
gdala | +1.463 |
ICAN | +1.274 |
amination | +1.228 |
Magikarp | +1.226 |
INE | +1.221 |
Neg logit contributions | |
leys | -0.664 |
luaj | -0.639 |
bri | -0.619 |
nen | -0.600 |
ahime | -0.597 |
Token | )" |
Token ID | 16725 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
gdala | +0.643 |
ICAN | +0.522 |
amination | +0.504 |
Magikarp | +0.496 |
INE | +0.495 |
Neg logit contributions | |
leys | -0.574 |
luaj | -0.563 |
bri | -0.548 |
nen | -0.541 |
jin | -0.533 |
Token | break |
Token ID | 2270 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
gdala | +0.313 |
ICAN | +0.262 |
amination | +0.253 |
INE | +0.252 |
Magikarp | +0.249 |
Neg logit contributions | |
leys | -0.217 |
luaj | -0.211 |
bri | -0.203 |
nen | -0.203 |
ahime | -0.199 |
Token | } |
Token ID | 1782 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
gdala | +3.456 |
ICAN | +2.913 |
INE | +2.838 |
amination | +2.800 |
Magikarp | +2.794 |
Neg logit contributions | |
leys | -2.067 |
luaj | -2.018 |
bri | -1.931 |
nen | -1.904 |
ahime | -1.874 |
Token | highlight |
Token ID | 7238 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
leys | +0.996 |
luaj | +0.975 |
bri | +0.944 |
nen | +0.933 |
jin | +0.919 |
Neg logit contributions | |
gdala | -1.173 |
ICAN | -0.956 |
amination | -0.930 |
INE | -0.912 |
Magikarp | -0.906 |
Token | of |
Token ID | 286 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
leys | +0.044 |
luaj | +0.043 |
bri | +0.041 |
nen | +0.041 |
jin | +0.040 |
Neg logit contributions | |
gdala | -0.048 |
ICAN | -0.039 |
amination | -0.038 |
INE | -0.038 |
Magikarp | -0.037 |
Token | Light |
Token ID | 4401 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
leys | +0.053 |
luaj | +0.052 |
bri | +0.049 |
nen | +0.049 |
igans | +0.049 |
Neg logit contributions | |
gdala | -0.064 |
ICAN | -0.052 |
amination | -0.051 |
INE | -0.050 |
Magikarp | -0.049 |
Token | Grey |
Token ID | 13980 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
leys | +0.263 |
luaj | +0.256 |
bri | +0.248 |
nen | +0.243 |
jin | +0.240 |
Neg logit contributions | |
gdala | -0.434 |
ICAN | -0.364 |
amination | -0.355 |
INE | -0.350 |
Magikarp | -0.349 |
Token | ( |
Token ID | 357 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
gdala | +0.176 |
ICAN | +0.143 |
amination | +0.140 |
INE | +0.137 |
Magikarp | +0.135 |
Neg logit contributions | |
leys | -0.157 |
luaj | -0.154 |
nen | -0.149 |
bri | -0.148 |
jin | -0.146 |
Token | before |
Token ID | 19052 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
gdala | +0.245 |
ICAN | +0.199 |
amination | +0.192 |
Magikarp | +0.189 |
INE | +0.189 |
Neg logit contributions | |
leys | -0.233 |
luaj | -0.228 |
bri | -0.223 |
nen | -0.219 |
igans | -0.216 |
Token | : |
Token ID | 25 |
Feature activation | -7.26e-02 |
Pos logit contributions | |
gdala | +3.623 |
amination | +2.968 |
ICAN | +2.928 |
INE | +2.890 |
coinc | +2.850 |
Neg logit contributions | |
leys | -3.274 |
luaj | -3.266 |
ahime | -3.077 |
igans | -3.065 |
nen | -3.044 |
Token | left |
Token ID | 1364 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
gdala | +0.063 |
ICAN | +0.051 |
amination | +0.050 |
INE | +0.049 |
Magikarp | +0.049 |
Neg logit contributions | |
leys | -0.053 |
luaj | -0.052 |
bri | -0.050 |
nen | -0.050 |
jin | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | +9.68e-02 |
Pos logit contributions | |
gdala | +1.492 |
ICAN | +1.198 |
amination | +1.192 |
INE | +1.151 |
coinc | +1.137 |
Neg logit contributions | |
leys | -1.351 |
luaj | -1.332 |
bri | -1.273 |
nen | -1.267 |
jin | -1.256 |
Token | after |
Token ID | 706 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
leys | +0.067 |
luaj | +0.066 |
bri | +0.063 |
nen | +0.062 |
jin | +0.062 |
Neg logit contributions | |
gdala | -0.088 |
ICAN | -0.072 |
amination | -0.071 |
Magikarp | -0.069 |
INE | -0.069 |
Token | : |
Token ID | 25 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
gdala | +0.587 |
ICAN | +0.455 |
amination | +0.441 |
INE | +0.431 |
Magikarp | +0.427 |
Neg logit contributions | |
leys | -0.737 |
luaj | -0.727 |
bri | -0.703 |
nen | -0.700 |
jin | -0.692 |
Token | , |
Token ID | 11 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
leys | +1.555 |
luaj | +1.518 |
bri | +1.480 |
nen | +1.452 |
jin | +1.434 |
Neg logit contributions | |
gdala | -1.901 |
ICAN | -1.546 |
amination | -1.498 |
Magikarp | -1.488 |
INE | -1.476 |
Token | according |
Token ID | 1864 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
leys | +0.890 |
luaj | +0.881 |
bri | +0.852 |
nen | +0.841 |
jin | +0.830 |
Neg logit contributions | |
gdala | -0.988 |
ICAN | -0.802 |
amination | -0.776 |
INE | -0.761 |
Magikarp | -0.761 |
Token | to |
Token ID | 284 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
gdala | +1.259 |
ICAN | +1.028 |
amination | +0.994 |
Magikarp | +0.978 |
INE | +0.976 |
Neg logit contributions | |
leys | -1.075 |
luaj | -1.054 |
bri | -1.026 |
nen | -1.009 |
jin | -0.996 |
Token | an |
Token ID | 281 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
gdala | +1.973 |
ICAN | +1.605 |
amination | +1.557 |
INE | +1.524 |
coinc | +1.513 |
Neg logit contributions | |
luaj | -1.903 |
leys | -1.869 |
bri | -1.792 |
ahime | -1.790 |
nen | -1.788 |
Token | NYPD |
Token ID | 27615 |
Feature activation | -6.68e+00 |
Pos logit contributions | |
gdala | +0.161 |
ICAN | +0.129 |
amination | +0.125 |
INE | +0.123 |
Magikarp | +0.122 |
Neg logit contributions | |
leys | -0.167 |
luaj | -0.164 |
bri | -0.160 |
nen | -0.159 |
jin | -0.156 |
Token | flyer |
Token ID | 42464 |
Feature activation | -6.39e+00 |
Pos logit contributions | |
gdala | +5.025 |
ICAN | +4.071 |
amination | +3.957 |
INE | +3.919 |
coinc | +3.890 |
Neg logit contributions | |
luaj | -5.339 |
leys | -5.253 |
ahime | -5.052 |
nen | -4.956 |
oshenko | -4.939 |
Token | . |
Token ID | 13 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
gdala | +5.186 |
ICAN | +4.178 |
amination | +4.148 |
coinc | +4.121 |
INE | +4.058 |
Neg logit contributions | |
luaj | -4.833 |
leys | -4.783 |
nen | -4.483 |
ahime | -4.472 |
bri | -4.466 |
Token |
|
Token ID | 198 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
gdala | +0.015 |
ICAN | +0.013 |
amination | +0.012 |
INE | +0.012 |
Magikarp | +0.012 |
Neg logit contributions | |
leys | -0.011 |
luaj | -0.011 |
bri | -0.011 |
nen | -0.011 |
jin | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
leys | +0.105 |
luaj | +0.103 |
bri | +0.100 |
nen | +0.098 |
jin | +0.097 |
Neg logit contributions | |
gdala | -0.154 |
ICAN | -0.128 |
amination | -0.125 |
Magikarp | -0.123 |
INE | -0.122 |
Token | His |
Token ID | 6653 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
leys | +0.174 |
luaj | +0.172 |
bri | +0.168 |
nen | +0.164 |
ahime | +0.162 |
Neg logit contributions | |
gdala | -0.192 |
ICAN | -0.157 |
amination | -0.150 |
INE | -0.150 |
Magikarp | -0.149 |
Token | show |
Token ID | 905 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
gdala | +0.448 |
ICAN | +0.364 |
amination | +0.355 |
INE | +0.349 |
Magikarp | +0.347 |
Neg logit contributions | |
leys | -0.389 |
luaj | -0.383 |
bri | -0.368 |
nen | -0.366 |
jin | -0.360 |