Token | Russia |
Token ID | 3284 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
ities | +0.638 |
fins | +0.638 |
isite | +0.606 |
Advantage | +0.603 |
ity | +0.592 |
Neg logit contributions | |
hell | -0.661 |
undo | -0.661 |
dash | -0.659 |
boro | -0.630 |
ALEC | -0.625 |
Token | . |
Token ID | 13 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
fins | +1.004 |
ities | +1.003 |
Advantage | +0.954 |
isite | +0.950 |
ity | +0.946 |
Neg logit contributions | |
dash | -0.846 |
hell | -0.838 |
undo | -0.829 |
ALEC | -0.804 |
boro | -0.787 |
Token |
|
Token ID | 198 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
ities | +0.143 |
fins | +0.142 |
Advantage | +0.139 |
isite | +0.137 |
ity | +0.134 |
Neg logit contributions | |
hell | -0.117 |
dash | -0.117 |
undo | -0.117 |
boro | -0.111 |
ALEC | -0.111 |
Token |
|
Token ID | 198 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
hell | +0.317 |
dash | +0.315 |
undo | +0.307 |
ALEC | +0.298 |
boro | +0.293 |
Neg logit contributions | |
fins | -0.536 |
ities | -0.525 |
isite | -0.520 |
Advantage | -0.512 |
iaz | -0.508 |
Token | Image |
Token ID | 5159 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ities | +0.407 |
fins | +0.396 |
isite | +0.385 |
ity | +0.379 |
Advantage | +0.375 |
Neg logit contributions | |
undo | -0.461 |
hell | -0.459 |
dash | -0.459 |
ALEC | -0.455 |
boro | -0.446 |
Token | copyright |
Token ID | 6634 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
fins | +2.507 |
ities | +2.438 |
Advantage | +2.338 |
isite | +2.321 |
ity | +2.246 |
Neg logit contributions | |
dash | -3.610 |
hell | -3.570 |
undo | -3.526 |
boro | -3.423 |
ALEC | -3.388 |
Token | AFP |
Token ID | 8916 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
fins | +6.576 |
ities | +6.575 |
Advantage | +6.366 |
ity | +6.223 |
Flames | +6.012 |
Neg logit contributions | |
dash | -9.254 |
hell | -9.104 |
undo | -9.029 |
boro | -8.919 |
robe | -8.743 |
Token | Image |
Token ID | 7412 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
ities | +2.373 |
fins | +2.305 |
Advantage | +2.190 |
ity | +2.124 |
isite | +2.102 |
Neg logit contributions | |
dash | -4.819 |
hell | -4.752 |
undo | -4.651 |
ALEC | -4.619 |
boro | -4.592 |
Token | caption |
Token ID | 8305 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
fins | +1.290 |
ities | +1.262 |
isite | +1.212 |
Advantage | +1.197 |
iaz | +1.171 |
Neg logit contributions | |
dash | -2.429 |
hell | -2.429 |
undo | -2.409 |
ALEC | -2.362 |
boro | -2.327 |
Token | The |
Token ID | 383 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
ities | +4.942 |
Advantage | +4.845 |
fins | +4.709 |
ity | +4.644 |
Flames | +4.549 |
Neg logit contributions | |
undo | -6.464 |
hell | -6.426 |
dash | -6.397 |
boro | -6.092 |
acus | -6.090 |
Token | Kurds |
Token ID | 23880 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
fins | +2.168 |
ities | +2.164 |
Advantage | +2.044 |
isite | +2.029 |
ity | +2.003 |
Neg logit contributions | |
hell | -2.917 |
dash | -2.916 |
undo | -2.913 |
boro | -2.820 |
ALEC | -2.793 |
Token | . |
Token ID | 13 |
Feature activation | -8.51e-02 |
Pos logit contributions | |
dash | +1.828 |
hell | +1.828 |
undo | +1.808 |
ALEC | +1.750 |
boro | +1.720 |
Neg logit contributions | |
fins | -2.395 |
ities | -2.385 |
isite | -2.303 |
Advantage | -2.292 |
iaz | -2.256 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
undo | +0.278 |
hell | +0.277 |
dash | +0.277 |
boro | +0.267 |
ALEC | +0.265 |
Neg logit contributions | |
ities | -0.216 |
fins | -0.214 |
Advantage | -0.208 |
isite | -0.203 |
ity | -0.200 |
Token | � |
Token ID | 251 |
Feature activation | -9.95e-03 |
Pos logit contributions | |
fins | +0.309 |
ities | +0.307 |
Advantage | +0.293 |
isite | +0.291 |
pta | +0.286 |
Neg logit contributions | |
hell | -0.378 |
dash | -0.377 |
undo | -0.373 |
ALEC | -0.364 |
boro | -0.360 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
undo | +0.028 |
dash | +0.028 |
hell | +0.028 |
boro | +0.027 |
ALEC | +0.027 |
Neg logit contributions | |
ities | -0.030 |
fins | -0.030 |
Advantage | -0.029 |
isite | -0.028 |
ity | -0.028 |
Token | Image |
Token ID | 5159 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
dash | +1.144 |
hell | +1.142 |
undo | +1.139 |
ALEC | +1.122 |
boro | +1.095 |
Neg logit contributions | |
ities | -1.112 |
fins | -1.105 |
isite | -1.063 |
Advantage | -1.050 |
iaz | -1.041 |
Token | copyright |
Token ID | 6634 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
fins | +1.104 |
ities | +1.082 |
Advantage | +1.041 |
isite | +1.027 |
iaz | +1.004 |
Neg logit contributions | |
dash | -1.520 |
hell | -1.500 |
undo | -1.498 |
ALEC | -1.452 |
boro | -1.447 |
Token | publicity |
Token ID | 19403 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Advantage | +7.080 |
fins | +7.062 |
ities | +7.034 |
ity | +6.683 |
Flames | +6.549 |
Neg logit contributions | |
dash | -8.267 |
undo | -8.071 |
hell | -8.046 |
boro | -7.918 |
FTWARE | -7.678 |
Token | Image |
Token ID | 7412 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ities | +2.947 |
fins | +2.916 |
Advantage | +2.804 |
ity | +2.793 |
pta | +2.744 |
Neg logit contributions | |
dash | -2.913 |
hell | -2.862 |
undo | -2.855 |
ALEC | -2.796 |
FTWARE | -2.780 |
Token | caption |
Token ID | 8305 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
fins | +2.056 |
ities | +2.046 |
isite | +1.912 |
Advantage | +1.896 |
iaz | +1.841 |
Neg logit contributions | |
dash | -4.344 |
hell | -4.344 |
undo | -4.314 |
ALEC | -4.223 |
boro | -4.186 |
Token | The |
Token ID | 383 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
Advantage | +5.999 |
ities | +5.993 |
fins | +5.953 |
ity | +5.674 |
Flames | +5.650 |
Neg logit contributions | |
undo | -6.101 |
dash | -6.028 |
hell | -5.943 |
acus | -5.645 |
boro | -5.628 |
Token | Greeks |
Token ID | 25059 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
fins | +2.251 |
ities | +2.212 |
Advantage | +2.118 |
isite | +2.094 |
ity | +2.057 |
Neg logit contributions | |
hell | -2.521 |
dash | -2.519 |
undo | -2.504 |
boro | -2.405 |
ALEC | -2.391 |
Token | ported |
Token ID | 9213 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
ities | +1.526 |
fins | +1.470 |
isite | +1.440 |
Advantage | +1.400 |
ity | +1.398 |
Neg logit contributions | |
hell | -2.977 |
dash | -2.972 |
undo | -2.885 |
ALEC | -2.874 |
boro | -2.809 |
Token | License |
Token ID | 13789 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
hell | +0.960 |
dash | +0.960 |
undo | +0.952 |
ALEC | +0.920 |
boro | +0.909 |
Neg logit contributions | |
ities | -0.866 |
fins | -0.864 |
Advantage | -0.828 |
isite | -0.828 |
iaz | -0.805 |
Token | . |
Token ID | 13 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
ities | +2.399 |
fins | +2.389 |
Advantage | +2.338 |
ity | +2.263 |
isite | +2.262 |
Neg logit contributions | |
dash | -2.143 |
hell | -2.142 |
undo | -2.118 |
boro | -2.051 |
ALEC | -2.046 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
dash | +0.911 |
hell | +0.911 |
undo | +0.900 |
ALEC | +0.876 |
boro | +0.868 |
Neg logit contributions | |
fins | -0.787 |
ities | -0.784 |
Advantage | -0.750 |
isite | -0.749 |
iaz | -0.733 |
Token | Image |
Token ID | 5159 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
dash | +1.161 |
hell | +1.159 |
undo | +1.156 |
ALEC | +1.138 |
boro | +1.111 |
Neg logit contributions | |
ities | -1.121 |
fins | -1.114 |
isite | -1.071 |
Advantage | -1.058 |
iaz | -1.049 |
Token | copyright |
Token ID | 6634 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
fins | +1.026 |
ities | +1.006 |
Advantage | +0.966 |
isite | +0.954 |
iaz | +0.934 |
Neg logit contributions | |
dash | -1.414 |
hell | -1.398 |
undo | -1.394 |
ALEC | -1.354 |
boro | -1.347 |
Token | AP |
Token ID | 3486 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Advantage | +7.005 |
fins | +7.000 |
ities | +6.958 |
ity | +6.597 |
Flames | +6.455 |
Neg logit contributions | |
dash | -8.158 |
undo | -7.949 |
hell | -7.934 |
boro | -7.807 |
FTWARE | -7.569 |
Token | Image |
Token ID | 7412 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
ities | +2.027 |
fins | +1.980 |
Advantage | +1.916 |
ity | +1.838 |
isite | +1.832 |
Neg logit contributions | |
dash | -4.071 |
hell | -4.011 |
undo | -3.959 |
ALEC | -3.905 |
boro | -3.885 |
Token | caption |
Token ID | 8305 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
fins | +1.699 |
ities | +1.681 |
isite | +1.592 |
Advantage | +1.574 |
iaz | +1.533 |
Neg logit contributions | |
hell | -3.405 |
dash | -3.405 |
undo | -3.380 |
ALEC | -3.312 |
boro | -3.272 |
Token | Peace |
Token ID | 12689 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ities | +5.301 |
Advantage | +5.239 |
fins | +5.171 |
ity | +4.959 |
Flames | +4.951 |
Neg logit contributions | |
undo | -5.952 |
dash | -5.927 |
hell | -5.855 |
acus | -5.550 |
boro | -5.529 |
Token | talks |
Token ID | 6130 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
hell | +3.312 |
dash | +3.297 |
undo | +3.269 |
ALEC | +3.185 |
boro | +3.147 |
Neg logit contributions | |
fins | -3.112 |
ities | -3.095 |
isite | -2.982 |
Advantage | -2.952 |
iaz | -2.906 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
fins | +1.241 |
ities | +1.234 |
ity | +1.179 |
Advantage | +1.174 |
isite | +1.170 |
Neg logit contributions | |
undo | -1.094 |
hell | -1.089 |
dash | -1.085 |
ALEC | -1.050 |
boro | -1.038 |
Token | � |
Token ID | 447 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
dash | +0.340 |
hell | +0.340 |
undo | +0.338 |
ALEC | +0.328 |
boro | +0.325 |
Neg logit contributions | |
fins | -0.277 |
ities | -0.276 |
Advantage | -0.264 |
isite | -0.263 |
iaz | -0.257 |
Token | � |
Token ID | 251 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
dash | +0.072 |
hell | +0.072 |
undo | +0.071 |
ALEC | +0.070 |
boro | +0.069 |
Neg logit contributions | |
fins | -0.057 |
ities | -0.057 |
Advantage | -0.054 |
isite | -0.053 |
pta | -0.053 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
fins | +0.758 |
ities | +0.757 |
Advantage | +0.726 |
isite | +0.717 |
iaz | +0.708 |
Neg logit contributions | |
dash | -0.738 |
undo | -0.735 |
hell | -0.733 |
ALEC | -0.708 |
boro | -0.702 |
Token | Image |
Token ID | 5159 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
dash | +0.909 |
hell | +0.907 |
undo | +0.906 |
ALEC | +0.894 |
boro | +0.871 |
Neg logit contributions | |
ities | -0.881 |
fins | -0.874 |
isite | -0.842 |
Advantage | -0.830 |
iaz | -0.825 |
Token | copyright |
Token ID | 6634 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
fins | +1.053 |
ities | +1.032 |
Advantage | +0.993 |
isite | +0.980 |
iaz | +0.957 |
Neg logit contributions | |
dash | -1.444 |
hell | -1.425 |
undo | -1.422 |
ALEC | -1.380 |
boro | -1.374 |
Token | Deadline |
Token ID | 35954 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
Advantage | +7.000 |
fins | +6.995 |
ities | +6.952 |
ity | +6.605 |
Flames | +6.467 |
Neg logit contributions | |
dash | -8.083 |
undo | -7.885 |
hell | -7.870 |
boro | -7.728 |
FTWARE | -7.510 |
Token |
|
Token ID | 198 |
Feature activation | +6.50e-02 |
Pos logit contributions | |
ities | +0.427 |
fins | +0.422 |
isite | +0.407 |
Advantage | +0.407 |
ity | +0.394 |
Neg logit contributions | |
dash | -0.568 |
hell | -0.559 |
undo | -0.554 |
ALEC | -0.545 |
boro | -0.534 |
Token |
|
Token ID | 198 |
Feature activation | +9.56e-02 |
Pos logit contributions | |
fins | +0.234 |
ities | +0.231 |
isite | +0.227 |
Advantage | +0.223 |
iaz | +0.222 |
Neg logit contributions | |
hell | -0.146 |
dash | -0.145 |
undo | -0.142 |
ALEC | -0.138 |
boro | -0.135 |
Token | Police |
Token ID | 9039 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ities | +0.264 |
fins | +0.258 |
isite | +0.249 |
Advantage | +0.246 |
ity | +0.245 |
Neg logit contributions | |
dash | -0.287 |
undo | -0.286 |
hell | -0.285 |
ALEC | -0.283 |
boro | -0.276 |
Token | have |
Token ID | 423 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
hell | +3.405 |
undo | +3.356 |
dash | +3.349 |
ALEC | +3.268 |
boro | +3.237 |
Neg logit contributions | |
fins | -3.089 |
ities | -3.081 |
isite | -3.055 |
pta | -2.969 |
iaz | -2.964 |
Token | Serve |
Token ID | 35557 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
fins | +0.545 |
ities | +0.538 |
isite | +0.520 |
Advantage | +0.512 |
iaz | +0.508 |
Neg logit contributions | |
hell | -0.656 |
dash | -0.656 |
undo | -0.648 |
ALEC | -0.635 |
boro | -0.625 |
Token | hot |
Token ID | 3024 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
fins | +0.860 |
ities | +0.854 |
isite | +0.817 |
Advantage | +0.810 |
iaz | +0.793 |
Neg logit contributions | |
dash | -1.174 |
hell | -1.174 |
undo | -1.164 |
ALEC | -1.137 |
boro | -1.122 |
Token | ! |
Token ID | 0 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
dash | +1.037 |
hell | +1.035 |
undo | +1.004 |
ALEC | +0.977 |
boro | +0.934 |
Neg logit contributions | |
fins | -2.598 |
ities | -2.562 |
isite | -2.550 |
Advantage | -2.512 |
iaz | -2.509 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
hell | +0.643 |
undo | +0.640 |
dash | +0.639 |
ALEC | +0.619 |
boro | +0.611 |
Neg logit contributions | |
fins | -0.656 |
ities | -0.652 |
Advantage | -0.629 |
isite | -0.628 |
iaz | -0.614 |
Token | Image |
Token ID | 5159 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
dash | +0.922 |
hell | +0.920 |
undo | +0.919 |
ALEC | +0.908 |
boro | +0.885 |
Neg logit contributions | |
ities | -0.890 |
fins | -0.882 |
isite | -0.850 |
Advantage | -0.837 |
iaz | -0.832 |
Token | copyright |
Token ID | 6634 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
fins | +1.170 |
ities | +1.144 |
Advantage | +1.103 |
isite | +1.087 |
iaz | +1.063 |
Neg logit contributions | |
dash | -1.608 |
hell | -1.589 |
undo | -1.585 |
ALEC | -1.538 |
boro | -1.534 |
Token | ESA |
Token ID | 42212 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
Advantage | +6.944 |
fins | +6.943 |
ities | +6.876 |
ity | +6.531 |
Flames | +6.405 |
Neg logit contributions | |
dash | -8.110 |
undo | -7.916 |
hell | -7.900 |
boro | -7.795 |
FTWARE | -7.534 |
Token | Image |
Token ID | 7412 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
fins | +0.204 |
ities | +0.202 |
Advantage | +0.194 |
isite | +0.191 |
pta | +0.187 |
Neg logit contributions | |
dash | -0.278 |
hell | -0.275 |
undo | -0.274 |
ALEC | -0.268 |
boro | -0.264 |
Token | caption |
Token ID | 8305 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
fins | +1.401 |
ities | +1.386 |
isite | +1.315 |
Advantage | +1.301 |
iaz | +1.270 |
Neg logit contributions | |
hell | -2.754 |
dash | -2.753 |
undo | -2.733 |
ALEC | -2.676 |
boro | -2.642 |
Token | Go |
Token ID | 1514 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
fins | +5.296 |
Advantage | +5.214 |
ities | +5.214 |
Flames | +4.916 |
ity | +4.855 |
Neg logit contributions | |
undo | -6.576 |
dash | -6.506 |
hell | -6.422 |
boro | -6.220 |
acus | -6.134 |
Token | ce |
Token ID | 344 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
fins | +1.041 |
ities | +1.039 |
isite | +0.973 |
Advantage | +0.970 |
pta | +0.966 |
Neg logit contributions | |
dash | -1.093 |
undo | -1.089 |
hell | -1.075 |
ALEC | -1.068 |
boro | -1.037 |
Token | million |
Token ID | 1510 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
fins | +3.195 |
ities | +3.159 |
Advantage | +2.990 |
isite | +2.966 |
pta | +2.963 |
Neg logit contributions | |
undo | -3.708 |
dash | -3.657 |
hell | -3.602 |
ALEC | -3.527 |
boro | -3.484 |
Token | years |
Token ID | 812 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
fins | +1.867 |
ities | +1.863 |
isite | +1.739 |
ity | +1.715 |
arily | +1.699 |
Neg logit contributions | |
undo | -3.002 |
dash | -3.001 |
hell | -2.964 |
boro | -2.893 |
ALEC | -2.883 |
Token | . |
Token ID | 13 |
Feature activation | +4.61e-03 |
Pos logit contributions | |
ities | +2.641 |
fins | +2.635 |
Advantage | +2.518 |
isite | +2.497 |
iaz | +2.478 |
Neg logit contributions | |
dash | -2.147 |
hell | -2.116 |
undo | -2.100 |
ALEC | -2.038 |
boro | -2.016 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
fins | +0.014 |
ities | +0.014 |
Advantage | +0.013 |
isite | +0.013 |
pta | +0.013 |
Neg logit contributions | |
dash | -0.013 |
hell | -0.013 |
undo | -0.013 |
ALEC | -0.012 |
boro | -0.012 |
Token | Image |
Token ID | 5159 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
dash | +1.210 |
hell | +1.208 |
undo | +1.205 |
ALEC | +1.188 |
boro | +1.159 |
Neg logit contributions | |
ities | -1.164 |
fins | -1.157 |
isite | -1.113 |
Advantage | -1.098 |
iaz | -1.089 |
Token | copyright |
Token ID | 6634 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
fins | +1.020 |
ities | +0.999 |
Advantage | +0.961 |
isite | +0.950 |
iaz | +0.929 |
Neg logit contributions | |
dash | -1.402 |
hell | -1.386 |
undo | -1.382 |
ALEC | -1.341 |
boro | -1.334 |
Token | AFP |
Token ID | 8916 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Advantage | +6.893 |
fins | +6.879 |
ities | +6.832 |
ity | +6.481 |
Flames | +6.354 |
Neg logit contributions | |
dash | -8.135 |
undo | -7.923 |
hell | -7.905 |
boro | -7.777 |
FTWARE | -7.534 |
Token |
|
Token ID | 198 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
ities | +2.458 |
fins | +2.409 |
Advantage | +2.318 |
ity | +2.224 |
pta | +2.184 |
Neg logit contributions | |
dash | -4.713 |
hell | -4.610 |
undo | -4.523 |
ALEC | -4.492 |
boro | -4.483 |
Token |
|
Token ID | 198 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
hell | +0.358 |
dash | +0.355 |
undo | +0.346 |
ALEC | +0.338 |
boro | +0.331 |
Neg logit contributions | |
fins | -0.618 |
ities | -0.604 |
isite | -0.599 |
Advantage | -0.587 |
iaz | -0.587 |
Token | The |
Token ID | 464 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
ities | +0.382 |
fins | +0.375 |
isite | +0.361 |
Advantage | +0.356 |
ity | +0.355 |
Neg logit contributions | |
dash | -0.421 |
hell | -0.420 |
undo | -0.419 |
ALEC | -0.414 |
boro | -0.404 |
Token | Bank |
Token ID | 5018 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
hell | +1.189 |
dash | +1.188 |
undo | +1.178 |
ALEC | +1.153 |
boro | +1.135 |
Neg logit contributions | |
fins | -0.847 |
ities | -0.841 |
isite | -0.806 |
Advantage | -0.798 |
iaz | -0.783 |
Token | ... |
Token ID | 986 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
dash | +0.185 |
undo | +0.185 |
hell | +0.183 |
ALEC | +0.179 |
boro | +0.176 |
Neg logit contributions | |
ities | -0.166 |
fins | -0.164 |
Advantage | -0.158 |
isite | -0.156 |
ity | -0.156 |
Token | Flag |
Token ID | 19762 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ities | +1.753 |
fins | +1.737 |
Advantage | +1.705 |
isite | +1.688 |
ity | +1.654 |
Neg logit contributions | |
dash | -1.845 |
undo | -1.831 |
hell | -1.807 |
ALEC | -1.761 |
boro | -1.748 |
Token |
|
Token ID | 198 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
dash | +0.335 |
hell | +0.335 |
undo | +0.331 |
ALEC | +0.320 |
boro | +0.315 |
Neg logit contributions | |
fins | -0.463 |
ities | -0.461 |
isite | -0.446 |
Advantage | -0.443 |
iaz | -0.437 |
Token |
|
Token ID | 198 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
ities | +1.895 |
fins | +1.879 |
Advantage | +1.815 |
isite | +1.810 |
ity | +1.791 |
Neg logit contributions | |
dash | -1.385 |
undo | -1.382 |
hell | -1.376 |
ALEC | -1.336 |
boro | -1.304 |
Token | Flag |
Token ID | 34227 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
ities | +1.780 |
fins | +1.747 |
iaz | +1.708 |
pta | +1.700 |
isite | +1.687 |
Neg logit contributions | |
ALEC | -2.185 |
hell | -2.148 |
dash | -2.146 |
undo | -2.145 |
FTWARE | -2.107 |
Token | Reply |
Token ID | 14883 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
hell | +1.945 |
dash | +1.939 |
undo | +1.938 |
ALEC | +1.908 |
boro | +1.860 |
Neg logit contributions | |
fins | -1.488 |
ities | -1.482 |
isite | -1.428 |
Advantage | -1.390 |
iaz | -1.379 |
Token |
|
Token ID | 198 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
fins | +7.201 |
Advantage | +7.051 |
ities | +7.046 |
isite | +6.679 |
Flames | +6.582 |
Neg logit contributions | |
hell | -7.718 |
undo | -7.602 |
FTWARE | -7.524 |
dash | -7.443 |
acus | -7.396 |
Token |
|
Token ID | 198 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
fins | +0.741 |
ities | +0.737 |
isite | +0.715 |
Advantage | +0.710 |
iaz | +0.701 |
Neg logit contributions | |
hell | -0.487 |
dash | -0.487 |
undo | -0.481 |
ALEC | -0.464 |
boro | -0.456 |
Token | 14 |
Token ID | 1415 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ities | +1.289 |
fins | +1.270 |
isite | +1.225 |
Advantage | +1.218 |
pta | +1.213 |
Neg logit contributions | |
undo | -1.512 |
hell | -1.508 |
dash | -1.503 |
ALEC | -1.476 |
boro | -1.447 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
dash | +0.465 |
hell | +0.465 |
undo | +0.462 |
ALEC | +0.448 |
boro | +0.445 |
Neg logit contributions | |
fins | -0.367 |
ities | -0.365 |
isite | -0.348 |
Advantage | -0.347 |
pta | -0.339 |
Token |
|
Token ID | 198 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
ities | +2.738 |
fins | +2.718 |
Advantage | +2.621 |
isite | +2.619 |
ity | +2.584 |
Neg logit contributions | |
dash | -1.983 |
hell | -1.976 |
undo | -1.956 |
ALEC | -1.891 |
boro | -1.852 |
Token | Bird |
Token ID | 42562 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
ities | +1.026 |
fins | +1.000 |
isite | +0.968 |
ity | +0.958 |
Advantage | +0.945 |
Neg logit contributions | |
dash | -1.101 |
ALEC | -1.097 |
hell | -1.094 |
undo | -1.090 |
boro | -1.051 |
Token | sey |
Token ID | 4397 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
dash | +2.533 |
hell | +2.533 |
undo | +2.509 |
ALEC | +2.438 |
boro | +2.400 |
Neg logit contributions | |
fins | -2.675 |
ities | -2.661 |
isite | -2.564 |
Advantage | -2.548 |
iaz | -2.504 |
Token | e |
Token ID | 68 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
dash | +0.069 |
hell | +0.069 |
undo | +0.069 |
ALEC | +0.068 |
boro | +0.066 |
Neg logit contributions | |
ities | -0.060 |
fins | -0.059 |
isite | -0.057 |
Advantage | -0.056 |
ity | -0.055 |
Token | view |
Token ID | 1570 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
fins | +0.487 |
ities | +0.481 |
Advantage | +0.461 |
isite | +0.456 |
ity | +0.449 |
Neg logit contributions | |
dash | -0.486 |
hell | -0.483 |
undo | -0.479 |
ALEC | -0.465 |
boro | -0.459 |
Token | of |
Token ID | 286 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
fins | +1.691 |
ities | +1.671 |
Advantage | +1.578 |
isite | +1.569 |
ity | +1.544 |
Neg logit contributions | |
hell | -1.836 |
dash | -1.825 |
undo | -1.795 |
ALEC | -1.777 |
boro | -1.749 |
Token | Brigham |
Token ID | 37434 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
ities | +2.012 |
fins | +2.008 |
Advantage | +1.908 |
isite | +1.883 |
ity | +1.855 |
Neg logit contributions | |
dash | -2.632 |
hell | -2.598 |
undo | -2.597 |
ALEC | -2.475 |
boro | -2.434 |
Token | City |
Token ID | 2254 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
ities | +5.261 |
ity | +4.900 |
Advantage | +4.872 |
fins | +4.626 |
isite | +4.474 |
Neg logit contributions | |
undo | -9.357 |
FTWARE | -9.310 |
dash | -9.237 |
hell | -9.203 |
acus | -8.941 |
Token | , |
Token ID | 11 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ities | +1.612 |
fins | +1.609 |
Advantage | +1.551 |
isite | +1.532 |
ity | +1.511 |
Neg logit contributions | |
dash | -1.340 |
undo | -1.337 |
hell | -1.332 |
ALEC | -1.269 |
FTWARE | -1.237 |
Token | Utah |
Token ID | 10202 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ities | +3.111 |
fins | +3.096 |
Advantage | +2.974 |
isite | +2.905 |
ity | +2.894 |
Neg logit contributions | |
hell | -3.168 |
dash | -3.136 |
undo | -3.081 |
ALEC | -2.946 |
boro | -2.927 |
Token | Date |
Token ID | 7536 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
ities | +3.465 |
fins | +3.431 |
Advantage | +3.325 |
isite | +3.269 |
ity | +3.227 |
Neg logit contributions | |
dash | -3.337 |
undo | -3.298 |
hell | -3.294 |
FTWARE | -3.129 |
ALEC | -3.127 |
Token | : |
Token ID | 25 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ities | +2.154 |
fins | +2.135 |
Advantage | +2.073 |
isite | +2.047 |
ity | +2.013 |
Neg logit contributions | |
hell | -2.157 |
dash | -2.132 |
undo | -2.094 |
ALEC | -2.054 |
boro | -1.998 |
Token | arsenal |
Token ID | 24375 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
ities | +0.689 |
fins | +0.688 |
Advantage | +0.653 |
isite | +0.652 |
ity | +0.641 |
Neg logit contributions | |
dash | -0.703 |
hell | -0.702 |
undo | -0.692 |
ALEC | -0.675 |
boro | -0.671 |
Token | of |
Token ID | 286 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
ities | +0.584 |
fins | +0.583 |
isite | +0.549 |
Advantage | +0.547 |
ity | +0.541 |
Neg logit contributions | |
dash | -0.661 |
undo | -0.650 |
hell | -0.643 |
boro | -0.632 |
ALEC | -0.632 |
Token | the |
Token ID | 262 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
fins | +0.697 |
ities | +0.686 |
Advantage | +0.645 |
isite | +0.644 |
iaz | +0.626 |
Neg logit contributions | |
dash | -1.068 |
hell | -1.062 |
undo | -1.059 |
ALEC | -1.032 |
boro | -1.027 |
Token | Ban |
Token ID | 10274 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
fins | +1.382 |
ities | +1.373 |
Advantage | +1.296 |
isite | +1.295 |
iaz | +1.271 |
Neg logit contributions | |
dash | -1.794 |
undo | -1.775 |
hell | -1.774 |
ALEC | -1.741 |
boro | -1.715 |
Token | u |
Token ID | 84 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
ities | +2.290 |
fins | +2.253 |
isite | +2.182 |
ity | +2.137 |
iaz | +2.128 |
Neg logit contributions | |
ALEC | -1.525 |
dash | -1.497 |
hell | -1.472 |
boro | -1.453 |
undo | -1.443 |
Token | Qur |
Token ID | 17599 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
ities | +3.010 |
fins | +2.966 |
Advantage | +2.607 |
iaz | +2.556 |
ity | +2.551 |
Neg logit contributions | |
undo | -8.088 |
dash | -8.009 |
ALEC | -7.997 |
hell | -7.952 |
FTWARE | -7.864 |
Token | ay |
Token ID | 323 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
ities | +6.661 |
iaz | +6.277 |
isite | +6.198 |
ity | +6.149 |
fins | +6.119 |
Neg logit contributions | |
ALEC | -7.978 |
FTWARE | -7.809 |
dash | -7.670 |
undo | -7.575 |
boro | -7.434 |
Token | za |
Token ID | 4496 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
ities | +1.553 |
fins | +1.545 |
isite | +1.497 |
Advantage | +1.487 |
iaz | +1.485 |
Neg logit contributions | |
hell | -0.841 |
dash | -0.832 |
undo | -0.830 |
ALEC | -0.816 |
boro | -0.787 |
Token | which |
Token ID | 543 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
ities | +1.957 |
fins | +1.953 |
Advantage | +1.852 |
isite | +1.829 |
ity | +1.808 |
Neg logit contributions | |
dash | -2.010 |
undo | -1.991 |
hell | -1.982 |
ALEC | -1.945 |
boro | -1.899 |
Token | consisted |
Token ID | 19954 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
dash | +0.413 |
hell | +0.411 |
undo | +0.408 |
ALEC | +0.396 |
boro | +0.391 |
Neg logit contributions | |
fins | -0.397 |
ities | -0.396 |
isite | -0.378 |
Advantage | -0.377 |
pta | -0.370 |
Token | of |
Token ID | 286 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
dash | +1.216 |
hell | +1.209 |
undo | +1.200 |
ALEC | +1.168 |
boro | +1.154 |
Neg logit contributions | |
fins | -1.160 |
ities | -1.155 |
isite | -1.109 |
Advantage | -1.100 |
iaz | -1.081 |
Token | said |
Token ID | 531 |
Feature activation | -6.65e-04 |
Pos logit contributions | |
ities | +0.389 |
fins | +0.389 |
Advantage | +0.368 |
isite | +0.364 |
iaz | +0.362 |
Neg logit contributions | |
dash | -0.400 |
hell | -0.394 |
undo | -0.393 |
ALEC | -0.382 |
boro | -0.376 |
Token | : |
Token ID | 25 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
dash | +0.002 |
hell | +0.002 |
undo | +0.002 |
ALEC | +0.002 |
boro | +0.002 |
Neg logit contributions | |
fins | -0.002 |
ities | -0.002 |
Advantage | -0.002 |
isite | -0.002 |
ity | -0.002 |
Token | � |
Token ID | 564 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
ities | +2.800 |
fins | +2.759 |
Advantage | +2.654 |
isite | +2.641 |
ity | +2.618 |
Neg logit contributions | |
dash | -3.167 |
hell | -3.123 |
undo | -3.114 |
ALEC | -3.026 |
boro | -3.007 |
Token | � |
Token ID | 250 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
fins | +1.279 |
ities | +1.219 |
Advantage | +1.196 |
isite | +1.166 |
pta | +1.140 |
Neg logit contributions | |
dash | -2.131 |
hell | -2.103 |
undo | -2.084 |
ALEC | -2.072 |
boro | -2.045 |
Token | Le |
Token ID | 3123 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
ities | +0.633 |
fins | +0.632 |
Advantage | +0.606 |
isite | +0.598 |
ity | +0.596 |
Neg logit contributions | |
dash | -0.619 |
undo | -0.610 |
hell | -0.609 |
ALEC | -0.599 |
boro | -0.584 |
Token | icester |
Token ID | 26382 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
ities | +0.859 |
fins | +0.848 |
isite | +0.807 |
Advantage | +0.806 |
ity | +0.798 |
Neg logit contributions | |
dash | -1.003 |
undo | -0.989 |
hell | -0.977 |
ALEC | -0.975 |
boro | -0.940 |
Token | have |
Token ID | 423 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
fins | +6.488 |
ities | +6.475 |
Advantage | +6.440 |
ity | +6.064 |
iaz | +5.984 |
Neg logit contributions | |
undo | -7.973 |
dash | -7.911 |
hell | -7.854 |
ALEC | -7.654 |
FTWARE | -7.543 |
Token | an |
Token ID | 281 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
fins | +2.007 |
ities | +1.960 |
Advantage | +1.891 |
isite | +1.836 |
ity | +1.835 |
Neg logit contributions | |
dash | -2.077 |
hell | -2.044 |
undo | -2.036 |
ALEC | -1.964 |
boro | -1.939 |
Token | excellent |
Token ID | 6275 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
ities | +0.439 |
fins | +0.437 |
Advantage | +0.422 |
isite | +0.412 |
iaz | +0.405 |
Neg logit contributions | |
dash | -0.613 |
hell | -0.609 |
undo | -0.601 |
ALEC | -0.587 |
boro | -0.586 |
Token | home |
Token ID | 1363 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
fins | +1.404 |
ities | +1.397 |
Advantage | +1.340 |
ity | +1.314 |
iaz | +1.309 |
Neg logit contributions | |
hell | -1.798 |
dash | -1.789 |
undo | -1.772 |
ALEC | -1.734 |
boro | -1.705 |
Token | record |
Token ID | 1700 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
ities | +3.354 |
fins | +3.285 |
Advantage | +3.269 |
ity | +3.238 |
iaz | +3.142 |
Neg logit contributions | |
hell | -3.497 |
undo | -3.489 |
dash | -3.448 |
ALEC | -3.392 |
boro | -3.303 |
Token | ? |
Token ID | 30 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
dash | +0.464 |
hell | +0.463 |
undo | +0.462 |
ALEC | +0.443 |
boro | +0.441 |
Neg logit contributions | |
ities | -0.521 |
fins | -0.519 |
Advantage | -0.497 |
isite | -0.495 |
iaz | -0.486 |
Token | Flag |
Token ID | 19762 |
Feature activation | +8.51e-02 |
Pos logit contributions | |
ities | +0.640 |
fins | +0.639 |
Advantage | +0.622 |
isite | +0.612 |
ity | +0.598 |
Neg logit contributions | |
dash | -0.716 |
undo | -0.713 |
hell | -0.711 |
boro | -0.677 |
ALEC | -0.675 |
Token |
|
Token ID | 198 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
fins | +0.291 |
ities | +0.290 |
Advantage | +0.281 |
isite | +0.281 |
iaz | +0.276 |
Neg logit contributions | |
dash | -0.203 |
hell | -0.203 |
undo | -0.200 |
ALEC | -0.193 |
boro | -0.190 |
Token |
|
Token ID | 198 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
ities | +1.759 |
fins | +1.754 |
Advantage | +1.686 |
isite | +1.686 |
ity | +1.657 |
Neg logit contributions | |
dash | -1.237 |
hell | -1.234 |
undo | -1.227 |
ALEC | -1.184 |
boro | -1.161 |
Token | Flag |
Token ID | 34227 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
ities | +2.110 |
fins | +2.064 |
isite | +1.984 |
ity | +1.962 |
Advantage | +1.953 |
Neg logit contributions | |
hell | -2.781 |
undo | -2.773 |
dash | -2.769 |
ALEC | -2.749 |
boro | -2.672 |
Token | Reply |
Token ID | 14883 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
hell | +0.393 |
dash | +0.393 |
undo | +0.392 |
ALEC | +0.384 |
boro | +0.378 |
Neg logit contributions | |
fins | -0.303 |
ities | -0.299 |
isite | -0.294 |
iaz | -0.283 |
pta | -0.283 |
Token |
|
Token ID | 198 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
ities | +7.118 |
ity | +6.820 |
fins | +6.771 |
Advantage | +6.615 |
arily | +6.348 |
Neg logit contributions | |
undo | -7.224 |
dash | -7.193 |
hell | -7.169 |
acus | -7.144 |
FTWARE | -7.034 |
Token |
|
Token ID | 198 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ities | +2.744 |
fins | +2.713 |
Advantage | +2.613 |
isite | +2.598 |
ity | +2.592 |
Neg logit contributions | |
dash | -2.062 |
undo | -2.056 |
hell | -2.048 |
ALEC | -1.980 |
boro | -1.941 |
Token | 27 |
Token ID | 1983 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
ities | +3.008 |
fins | +2.915 |
ity | +2.850 |
Advantage | +2.832 |
isite | +2.803 |
Neg logit contributions | |
undo | -3.709 |
dash | -3.692 |
hell | -3.664 |
ALEC | -3.628 |
acus | -3.545 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
fins | +0.607 |
ities | +0.603 |
isite | +0.579 |
Advantage | +0.574 |
iaz | +0.564 |
Neg logit contributions | |
dash | -0.727 |
hell | -0.727 |
undo | -0.721 |
ALEC | -0.703 |
boro | -0.693 |
Token |
|
Token ID | 198 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
ities | +2.986 |
fins | +2.958 |
Advantage | +2.852 |
isite | +2.841 |
ity | +2.824 |
Neg logit contributions | |
dash | -2.213 |
hell | -2.203 |
undo | -2.188 |
ALEC | -2.113 |
boro | -2.069 |
Token | . |
Token ID | 13 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
dash | +0.837 |
hell | +0.834 |
undo | +0.829 |
ALEC | +0.800 |
boro | +0.784 |
Neg logit contributions | |
fins | -1.109 |
ities | -1.107 |
isite | -1.061 |
Advantage | -1.059 |
iaz | -1.040 |
Token | Flag |
Token ID | 19762 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
dash | +0.524 |
hell | +0.524 |
undo | +0.520 |
ALEC | +0.505 |
boro | +0.498 |
Neg logit contributions | |
fins | -0.499 |
ities | -0.497 |
isite | -0.477 |
Advantage | -0.475 |
iaz | -0.466 |
Token |
|
Token ID | 198 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
dash | +0.041 |
hell | +0.041 |
undo | +0.040 |
ALEC | +0.039 |
boro | +0.038 |
Neg logit contributions | |
fins | -0.057 |
ities | -0.057 |
Advantage | -0.055 |
isite | -0.055 |
iaz | -0.054 |
Token |
|
Token ID | 198 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
ities | +1.615 |
fins | +1.614 |
isite | +1.552 |
Advantage | +1.551 |
iaz | +1.525 |
Neg logit contributions | |
dash | -1.121 |
hell | -1.120 |
undo | -1.112 |
ALEC | -1.072 |
boro | -1.052 |
Token | Flag |
Token ID | 34227 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
ities | +2.105 |
fins | +2.067 |
isite | +1.986 |
Advantage | +1.962 |
ity | +1.954 |
Neg logit contributions | |
hell | -2.780 |
dash | -2.773 |
undo | -2.763 |
ALEC | -2.735 |
boro | -2.669 |
Token | Reply |
Token ID | 14883 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
undo | +1.174 |
hell | +1.172 |
dash | +1.169 |
ALEC | +1.156 |
boro | +1.130 |
Neg logit contributions | |
fins | -0.936 |
ities | -0.926 |
isite | -0.903 |
iaz | -0.874 |
Advantage | -0.868 |
Token |
|
Token ID | 198 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
ities | +7.166 |
fins | +6.940 |
Advantage | +6.879 |
ity | +6.797 |
Flames | +6.471 |
Neg logit contributions | |
hell | -7.144 |
undo | -7.132 |
dash | -7.119 |
acus | -7.014 |
FTWARE | -6.912 |
Token |
|
Token ID | 198 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
ities | +2.297 |
fins | +2.281 |
Advantage | +2.196 |
isite | +2.190 |
ity | +2.167 |
Neg logit contributions | |
dash | -1.675 |
undo | -1.668 |
hell | -1.667 |
ALEC | -1.606 |
boro | -1.574 |
Token | 55 |
Token ID | 2816 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
ities | +2.498 |
fins | +2.443 |
Advantage | +2.370 |
ity | +2.365 |
isite | +2.360 |
Neg logit contributions | |
undo | -3.111 |
dash | -3.083 |
hell | -3.079 |
ALEC | -3.036 |
boro | -2.955 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ities | +2.047 |
fins | +2.041 |
Advantage | +1.944 |
isite | +1.940 |
ity | +1.893 |
Neg logit contributions | |
dash | -2.805 |
hell | -2.788 |
undo | -2.761 |
ALEC | -2.682 |
boro | -2.658 |
Token |
|
Token ID | 198 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
ities | +3.747 |
fins | +3.681 |
Advantage | +3.555 |
ity | +3.552 |
isite | +3.535 |
Neg logit contributions | |
dash | -2.890 |
hell | -2.875 |
undo | -2.859 |
ALEC | -2.760 |
boro | -2.697 |
Token | in |
Token ID | 287 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
fins | +1.213 |
ities | +1.204 |
Advantage | +1.129 |
ity | +1.116 |
iaz | +1.116 |
Neg logit contributions | |
undo | -1.457 |
dash | -1.456 |
hell | -1.456 |
ALEC | -1.415 |
boro | -1.387 |
Token | betting |
Token ID | 22908 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
fins | +1.079 |
ities | +1.064 |
Advantage | +1.019 |
ity | +1.008 |
isite | +0.995 |
Neg logit contributions | |
undo | -1.073 |
hell | -1.071 |
dash | -1.069 |
ALEC | -1.025 |
boro | -1.020 |
Token | with |
Token ID | 351 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
dash | +3.261 |
hell | +3.259 |
undo | +3.219 |
ALEC | +3.136 |
boro | +3.076 |
Neg logit contributions | |
ities | -3.724 |
fins | -3.719 |
isite | -3.640 |
Advantage | -3.583 |
pta | -3.560 |
Token | a |
Token ID | 257 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
fins | +0.462 |
ities | +0.458 |
Advantage | +0.437 |
isite | +0.432 |
ity | +0.425 |
Neg logit contributions | |
hell | -0.527 |
dash | -0.523 |
undo | -0.521 |
ALEC | -0.503 |
boro | -0.500 |
Token | particular |
Token ID | 1948 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
fins | +1.100 |
ities | +1.094 |
isite | +1.043 |
Advantage | +1.037 |
ity | +1.020 |
Neg logit contributions | |
hell | -1.229 |
dash | -1.212 |
undo | -1.208 |
ALEC | -1.168 |
boro | -1.156 |
Token | reputation |
Token ID | 8507 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
ities | +1.974 |
fins | +1.918 |
ity | +1.855 |
Advantage | +1.814 |
isite | +1.793 |
Neg logit contributions | |
hell | -3.585 |
dash | -3.498 |
undo | -3.482 |
boro | -3.365 |
ALEC | -3.349 |
Token | as |
Token ID | 355 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
ities | +6.198 |
fins | +6.110 |
ity | +5.878 |
arily | +5.736 |
Advantage | +5.550 |
Neg logit contributions | |
dash | -7.695 |
undo | -7.650 |
hell | -7.650 |
acus | -7.494 |
FTWARE | -7.475 |
Token | in |
Token ID | 287 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
fins | +1.335 |
ities | +1.299 |
Advantage | +1.263 |
isite | +1.230 |
ity | +1.227 |
Neg logit contributions | |
undo | -1.288 |
hell | -1.286 |
dash | -1.278 |
boro | -1.222 |
ALEC | -1.214 |
Token | - |
Token ID | 12 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
fins | +1.636 |
ities | +1.609 |
Advantage | +1.549 |
isite | +1.527 |
ity | +1.521 |
Neg logit contributions | |
undo | -1.910 |
hell | -1.888 |
dash | -1.876 |
ALEC | -1.826 |
boro | -1.811 |
Token | play |
Token ID | 1759 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
undo | +0.858 |
hell | +0.847 |
ALEC | +0.838 |
dash | +0.837 |
boro | +0.798 |
Neg logit contributions | |
fins | -1.441 |
ities | -1.441 |
Advantage | -1.386 |
isite | -1.385 |
ity | -1.370 |
Token | football |
Token ID | 4346 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
dash | +0.054 |
undo | +0.054 |
hell | +0.054 |
ALEC | +0.052 |
boro | +0.051 |
Neg logit contributions | |
fins | -0.075 |
ities | -0.074 |
Advantage | -0.071 |
isite | -0.071 |
iaz | -0.070 |
Token | , |
Token ID | 11 |
Feature activation | +4.87e-03 |
Pos logit contributions | |
ities | +0.530 |
fins | +0.529 |
Advantage | +0.498 |
isite | +0.495 |
ity | +0.493 |
Neg logit contributions | |
dash | -0.503 |
hell | -0.500 |
undo | -0.498 |
ALEC | -0.481 |
boro | -0.473 |
Token | with |
Token ID | 351 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
fins | +0.014 |
ities | +0.014 |
isite | +0.013 |
Advantage | +0.013 |
ity | +0.013 |
Neg logit contributions | |
dash | -0.014 |
hell | -0.014 |
undo | -0.014 |
ALEC | -0.014 |
boro | -0.014 |
Token | this |
Token ID | 428 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
fins | +1.176 |
ities | +1.167 |
Advantage | +1.115 |
isite | +1.112 |
ity | +1.091 |
Neg logit contributions | |
hell | -1.121 |
dash | -1.119 |
undo | -1.109 |
ALEC | -1.066 |
boro | -1.053 |
Token | map |
Token ID | 3975 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
fins | +1.682 |
ities | +1.680 |
Advantage | +1.600 |
isite | +1.599 |
ity | +1.580 |
Neg logit contributions | |
hell | -1.744 |
dash | -1.740 |
undo | -1.712 |
ALEC | -1.650 |
boro | -1.650 |
Token | of |
Token ID | 286 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
dash | +1.784 |
hell | +1.779 |
undo | +1.764 |
ALEC | +1.709 |
boro | +1.683 |
Neg logit contributions | |
fins | -2.041 |
ities | -2.035 |
isite | -1.958 |
Advantage | -1.948 |
iaz | -1.913 |
Token | Brigham |
Token ID | 37434 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
ities | +1.705 |
fins | +1.689 |
Advantage | +1.618 |
isite | +1.600 |
ity | +1.585 |
Neg logit contributions | |
dash | -2.101 |
undo | -2.059 |
hell | -2.050 |
ALEC | -1.956 |
boro | -1.931 |
Token | City |
Token ID | 2254 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
ities | +5.202 |
Advantage | +4.877 |
ity | +4.839 |
fins | +4.721 |
isite | +4.510 |
Neg logit contributions | |
undo | -8.791 |
dash | -8.689 |
hell | -8.598 |
FTWARE | -8.562 |
ALEC | -8.400 |
Token | , |
Token ID | 11 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
ities | +1.134 |
fins | +1.124 |
Advantage | +1.086 |
isite | +1.078 |
ity | +1.067 |
Neg logit contributions | |
dash | -0.932 |
undo | -0.924 |
hell | -0.923 |
ALEC | -0.879 |
boro | -0.860 |
Token | Utah |
Token ID | 10202 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ities | +2.615 |
fins | +2.615 |
Advantage | +2.503 |
isite | +2.449 |
ity | +2.445 |
Neg logit contributions | |
hell | -2.621 |
dash | -2.615 |
undo | -2.579 |
boro | -2.448 |
ALEC | -2.447 |
Token | [ |
Token ID | 685 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
ities | +4.006 |
fins | +3.922 |
Advantage | +3.833 |
ity | +3.803 |
isite | +3.793 |
Neg logit contributions | |
dash | -3.605 |
undo | -3.546 |
hell | -3.518 |
ALEC | -3.361 |
FTWARE | -3.345 |
Token | g |
Token ID | 70 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
dash | +0.643 |
hell | +0.642 |
undo | +0.635 |
ALEC | +0.625 |
boro | +0.613 |
Neg logit contributions | |
fins | -0.642 |
ities | -0.641 |
isite | -0.615 |
Advantage | -0.612 |
pta | -0.601 |
Token | . |
Token ID | 13 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
ities | +2.873 |
fins | +2.815 |
Advantage | +2.691 |
ity | +2.651 |
isite | +2.597 |
Neg logit contributions | |
undo | -2.497 |
hell | -2.484 |
dash | -2.468 |
ALEC | -2.350 |
boro | -2.341 |
Token | Flag |
Token ID | 19762 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
dash | +0.189 |
hell | +0.189 |
undo | +0.188 |
ALEC | +0.181 |
boro | +0.180 |
Neg logit contributions | |
fins | -0.177 |
ities | -0.177 |
Advantage | -0.170 |
isite | -0.169 |
iaz | -0.165 |
Token |
|
Token ID | 198 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
hell | +0.362 |
dash | +0.361 |
undo | +0.359 |
ALEC | +0.347 |
boro | +0.339 |
Neg logit contributions | |
fins | -0.564 |
ities | -0.561 |
isite | -0.546 |
Advantage | -0.539 |
pta | -0.534 |
Token |
|
Token ID | 198 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
ities | +1.633 |
fins | +1.630 |
isite | +1.568 |
Advantage | +1.566 |
iaz | +1.540 |
Neg logit contributions | |
dash | -1.137 |
hell | -1.136 |
undo | -1.128 |
ALEC | -1.088 |
boro | -1.067 |
Token | Flag |
Token ID | 34227 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
ities | +2.260 |
fins | +2.199 |
isite | +2.116 |
ity | +2.104 |
Advantage | +2.083 |
Neg logit contributions | |
hell | -3.045 |
undo | -3.037 |
dash | -3.029 |
ALEC | -3.018 |
boro | -2.926 |
Token | Reply |
Token ID | 14883 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
dash | +0.824 |
hell | +0.823 |
undo | +0.820 |
ALEC | +0.806 |
boro | +0.792 |
Neg logit contributions | |
fins | -0.652 |
ities | -0.642 |
isite | -0.633 |
iaz | -0.611 |
pta | -0.609 |
Token |
|
Token ID | 198 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
ities | +6.846 |
fins | +6.548 |
ity | +6.547 |
Advantage | +6.387 |
arily | +6.124 |
Neg logit contributions | |
undo | -6.744 |
dash | -6.712 |
hell | -6.703 |
acus | -6.629 |
FTWARE | -6.552 |
Token |
|
Token ID | 198 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ities | +2.396 |
fins | +2.375 |
Advantage | +2.286 |
isite | +2.278 |
ity | +2.260 |
Neg logit contributions | |
dash | -1.760 |
undo | -1.753 |
hell | -1.751 |
ALEC | -1.688 |
boro | -1.655 |
Token | 19 |
Token ID | 1129 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
ities | +2.720 |
fins | +2.646 |
ity | +2.569 |
Advantage | +2.557 |
isite | +2.543 |
Neg logit contributions | |
undo | -3.304 |
dash | -3.288 |
hell | -3.268 |
ALEC | -3.231 |
boro | -3.146 |
Token | Recommend |
Token ID | 30361 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
hell | +1.016 |
dash | +1.013 |
undo | +1.009 |
ALEC | +0.984 |
boro | +0.970 |
Neg logit contributions | |
fins | -0.899 |
ities | -0.893 |
isite | -0.858 |
Advantage | -0.846 |
iaz | -0.842 |
Token |
|
Token ID | 198 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
ities | +2.333 |
fins | +2.321 |
Advantage | +2.234 |
isite | +2.233 |
ity | +2.200 |
Neg logit contributions | |
dash | -1.661 |
hell | -1.656 |
undo | -1.643 |
ALEC | -1.586 |
boro | -1.553 |
Token | surface |
Token ID | 4417 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
fins | +0.590 |
ities | +0.586 |
isite | +0.555 |
Advantage | +0.553 |
pta | +0.542 |
Neg logit contributions | |
dash | -0.693 |
hell | -0.692 |
undo | -0.689 |
ALEC | -0.669 |
boro | -0.664 |
Token | . |
Token ID | 13 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
dash | +0.590 |
hell | +0.589 |
undo | +0.584 |
ALEC | +0.565 |
boro | +0.556 |
Neg logit contributions | |
fins | -0.732 |
ities | -0.728 |
isite | -0.702 |
Advantage | -0.699 |
iaz | -0.687 |
Token |
|
Token ID | 198 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ities | +0.042 |
fins | +0.042 |
Advantage | +0.040 |
isite | +0.040 |
ity | +0.039 |
Neg logit contributions | |
dash | -0.032 |
hell | -0.032 |
undo | -0.032 |
ALEC | -0.030 |
boro | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
fins | +0.487 |
ities | +0.481 |
isite | +0.471 |
Advantage | +0.466 |
iaz | +0.461 |
Neg logit contributions | |
hell | -0.306 |
dash | -0.305 |
undo | -0.300 |
ALEC | -0.290 |
boro | -0.284 |
Token | Media |
Token ID | 13152 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
ities | +1.302 |
fins | +1.257 |
ity | +1.214 |
isite | +1.203 |
pta | +1.177 |
Neg logit contributions | |
ALEC | -1.484 |
dash | -1.468 |
undo | -1.467 |
hell | -1.451 |
boro | -1.439 |
Token | playback |
Token ID | 16388 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
fins | +1.132 |
ities | +1.119 |
Advantage | +1.046 |
isite | +1.020 |
ity | +0.998 |
Neg logit contributions | |
dash | -2.147 |
undo | -2.133 |
hell | -2.129 |
ALEC | -2.074 |
boro | -2.061 |
Token | is |
Token ID | 318 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
ities | +5.968 |
fins | +5.854 |
Advantage | +5.594 |
ity | +5.538 |
isite | +5.518 |
Neg logit contributions | |
undo | -7.887 |
dash | -7.857 |
hell | -7.824 |
FTWARE | -7.477 |
ALEC | -7.437 |
Token | unsupported |
Token ID | 24222 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
fins | +0.703 |
ities | +0.698 |
isite | +0.677 |
Advantage | +0.661 |
iaz | +0.654 |
Neg logit contributions | |
dash | -0.943 |
hell | -0.937 |
undo | -0.934 |
ALEC | -0.915 |
boro | -0.895 |
Token | on |
Token ID | 319 |
Feature activation | -5.50e-02 |
Pos logit contributions | |
fins | +0.810 |
ities | +0.806 |
isite | +0.777 |
Advantage | +0.772 |
iaz | +0.759 |
Neg logit contributions | |
dash | -0.759 |
hell | -0.759 |
undo | -0.751 |
ALEC | -0.730 |
boro | -0.719 |
Token | your |
Token ID | 534 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
dash | +0.106 |
hell | +0.104 |
undo | +0.103 |
ALEC | +0.099 |
boro | +0.095 |
Neg logit contributions | |
fins | -0.214 |
ities | -0.213 |
isite | -0.210 |
Advantage | -0.207 |
iaz | -0.206 |
Token | device |
Token ID | 3335 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
fins | +1.008 |
ities | +0.997 |
isite | +0.960 |
Advantage | +0.942 |
iaz | +0.928 |
Neg logit contributions | |
dash | -1.705 |
hell | -1.694 |
undo | -1.685 |
ALEC | -1.655 |
boro | -1.629 |
Token | energy |
Token ID | 2568 |
Feature activation | +8.11e-02 |
Pos logit contributions | |
fins | +0.420 |
ities | +0.419 |
Advantage | +0.401 |
isite | +0.396 |
ity | +0.394 |
Neg logit contributions | |
dash | -0.333 |
hell | -0.332 |
undo | -0.328 |
ALEC | -0.316 |
boro | -0.315 |
Token | goals |
Token ID | 4661 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
fins | +0.187 |
ities | +0.187 |
Advantage | +0.177 |
isite | +0.173 |
ity | +0.170 |
Neg logit contributions | |
hell | -0.287 |
dash | -0.285 |
undo | -0.284 |
ALEC | -0.278 |
boro | -0.275 |
Token | . |
Token ID | 13 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
ities | +1.232 |
fins | +1.221 |
Advantage | +1.168 |
isite | +1.164 |
iaz | +1.161 |
Neg logit contributions | |
dash | -0.981 |
hell | -0.972 |
undo | -0.970 |
ALEC | -0.936 |
boro | -0.934 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
ities | +0.069 |
fins | +0.069 |
Advantage | +0.067 |
isite | +0.066 |
pta | +0.065 |
Neg logit contributions | |
hell | -0.060 |
dash | -0.060 |
undo | -0.060 |
ALEC | -0.057 |
boro | -0.057 |
Token | Media |
Token ID | 13152 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
dash | +1.180 |
hell | +1.178 |
undo | +1.175 |
ALEC | +1.159 |
boro | +1.130 |
Neg logit contributions | |
ities | -1.137 |
fins | -1.129 |
isite | -1.087 |
Advantage | -1.072 |
iaz | -1.064 |
Token | playback |
Token ID | 16388 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
dash | +1.099 |
hell | +1.095 |
undo | +1.093 |
ALEC | +1.067 |
boro | +1.054 |
Neg logit contributions | |
fins | -0.634 |
ities | -0.631 |
isite | -0.594 |
Advantage | -0.592 |
iaz | -0.577 |
Token | is |
Token ID | 318 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
ities | +5.656 |
fins | +5.473 |
isite | +5.303 |
Advantage | +5.262 |
ity | +5.257 |
Neg logit contributions | |
dash | -8.165 |
undo | -8.094 |
hell | -7.991 |
FTWARE | -7.648 |
ALEC | -7.568 |
Token | unsupported |
Token ID | 24222 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
fins | +0.258 |
ities | +0.258 |
Advantage | +0.243 |
isite | +0.242 |
pta | +0.235 |
Neg logit contributions | |
dash | -0.430 |
hell | -0.430 |
undo | -0.427 |
ALEC | -0.415 |
boro | -0.413 |
Token | on |
Token ID | 319 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
fins | +0.659 |
ities | +0.654 |
isite | +0.633 |
Advantage | +0.628 |
iaz | +0.618 |
Neg logit contributions | |
hell | -0.609 |
dash | -0.609 |
undo | -0.601 |
ALEC | -0.585 |
boro | -0.576 |
Token | your |
Token ID | 534 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
dash | +0.440 |
hell | +0.429 |
undo | +0.424 |
ALEC | +0.410 |
boro | +0.389 |
Neg logit contributions | |
fins | -0.929 |
ities | -0.923 |
isite | -0.910 |
Advantage | -0.902 |
iaz | -0.896 |
Token | device |
Token ID | 3335 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
fins | +0.646 |
ities | +0.638 |
isite | +0.616 |
Advantage | +0.604 |
pta | +0.597 |
Neg logit contributions | |
dash | -1.071 |
hell | -1.061 |
undo | -1.057 |
ALEC | -1.041 |
boro | -1.023 |
Token | on |
Token ID | 319 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
hell | +1.631 |
dash | +1.631 |
undo | +1.602 |
ALEC | +1.566 |
boro | +1.540 |
Neg logit contributions | |
fins | -1.687 |
ities | -1.675 |
isite | -1.624 |
Advantage | -1.617 |
iaz | -1.592 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
fins | +0.284 |
ities | +0.283 |
Advantage | +0.265 |
isite | +0.265 |
iaz | +0.257 |
Neg logit contributions | |
hell | -0.491 |
undo | -0.491 |
dash | -0.491 |
ALEC | -0.478 |
boro | -0.474 |
Token | . |
Token ID | 13 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
ities | +1.664 |
fins | +1.647 |
Advantage | +1.569 |
isite | +1.555 |
ity | +1.543 |
Neg logit contributions | |
undo | -1.666 |
dash | -1.658 |
hell | -1.654 |
ALEC | -1.606 |
boro | -1.592 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
dash | +0.764 |
hell | +0.763 |
undo | +0.761 |
ALEC | +0.740 |
boro | +0.731 |
Neg logit contributions | |
fins | -0.514 |
ities | -0.514 |
Advantage | -0.488 |
isite | -0.486 |
iaz | -0.474 |
Token | Media |
Token ID | 13152 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
dash | +1.200 |
hell | +1.197 |
undo | +1.195 |
ALEC | +1.181 |
boro | +1.149 |
Neg logit contributions | |
ities | -1.149 |
fins | -1.141 |
isite | -1.098 |
Advantage | -1.081 |
iaz | -1.075 |
Token | playback |
Token ID | 16388 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
dash | +0.905 |
undo | +0.900 |
hell | +0.900 |
ALEC | +0.879 |
boro | +0.867 |
Neg logit contributions | |
fins | -0.511 |
ities | -0.509 |
Advantage | -0.477 |
isite | -0.476 |
iaz | -0.463 |
Token | is |
Token ID | 318 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
ities | +5.666 |
fins | +5.511 |
isite | +5.318 |
Advantage | +5.302 |
ity | +5.261 |
Neg logit contributions | |
dash | -7.917 |
undo | -7.833 |
hell | -7.792 |
FTWARE | -7.410 |
boro | -7.350 |
Token | unsupported |
Token ID | 24222 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
fins | +0.084 |
ities | +0.084 |
Advantage | +0.079 |
isite | +0.079 |
iaz | +0.077 |
Neg logit contributions | |
dash | -0.139 |
hell | -0.139 |
undo | -0.138 |
ALEC | -0.134 |
boro | -0.133 |
Token | on |
Token ID | 319 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
fins | +0.598 |
ities | +0.593 |
isite | +0.574 |
Advantage | +0.570 |
iaz | +0.561 |
Neg logit contributions | |
dash | -0.551 |
hell | -0.550 |
undo | -0.544 |
ALEC | -0.529 |
boro | -0.520 |
Token | your |
Token ID | 534 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
dash | +0.441 |
hell | +0.431 |
undo | +0.426 |
ALEC | +0.411 |
boro | +0.392 |
Neg logit contributions | |
fins | -0.913 |
ities | -0.907 |
isite | -0.892 |
Advantage | -0.884 |
iaz | -0.879 |
Token | device |
Token ID | 3335 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
fins | +0.408 |
ities | +0.401 |
isite | +0.390 |
Advantage | +0.381 |
pta | +0.379 |
Neg logit contributions | |
dash | -0.655 |
hell | -0.646 |
undo | -0.644 |
ALEC | -0.636 |
boro | -0.623 |
Token | especially |
Token ID | 2592 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
fins | +1.180 |
ities | +1.177 |
Advantage | +1.120 |
isite | +1.112 |
ity | +1.089 |
Neg logit contributions | |
dash | -1.345 |
hell | -1.335 |
undo | -1.329 |
boro | -1.293 |
ALEC | -1.282 |
Token | for |
Token ID | 329 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
fins | +0.629 |
ities | +0.628 |
Advantage | +0.597 |
isite | +0.591 |
ity | +0.585 |
Neg logit contributions | |
dash | -0.663 |
undo | -0.661 |
hell | -0.660 |
ALEC | -0.634 |
boro | -0.632 |
Token | the |
Token ID | 262 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
fins | +1.479 |
ities | +1.471 |
Advantage | +1.406 |
isite | +1.389 |
ity | +1.372 |
Neg logit contributions | |
undo | -1.522 |
dash | -1.519 |
hell | -1.517 |
boro | -1.459 |
ALEC | -1.428 |
Token | legacy |
Token ID | 10655 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
fins | +1.037 |
ities | +1.029 |
Advantage | +0.974 |
isite | +0.969 |
iaz | +0.949 |
Neg logit contributions | |
dash | -1.539 |
undo | -1.538 |
hell | -1.537 |
ALEC | -1.481 |
boro | -1.481 |
Token | and |
Token ID | 290 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
ities | +2.876 |
fins | +2.819 |
arily | +2.715 |
Advantage | +2.706 |
ity | +2.683 |
Neg logit contributions | |
undo | -3.494 |
dash | -3.491 |
hell | -3.464 |
boro | -3.389 |
acus | -3.348 |
Token | reputation |
Token ID | 8507 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
ities | +1.466 |
fins | +1.462 |
Advantage | +1.381 |
ity | +1.366 |
isite | +1.355 |
Neg logit contributions | |
dash | -1.872 |
hell | -1.863 |
undo | -1.855 |
boro | -1.789 |
ALEC | -1.774 |
Token | of |
Token ID | 286 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ities | +5.668 |
fins | +5.390 |
ity | +5.229 |
arily | +5.195 |
Advantage | +5.145 |
Neg logit contributions | |
dash | -7.923 |
undo | -7.860 |
hell | -7.602 |
boro | -7.597 |
acus | -7.584 |
Token | President |
Token ID | 1992 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
fins | +2.998 |
ities | +2.974 |
Advantage | +2.851 |
ity | +2.802 |
isite | +2.798 |
Neg logit contributions | |
hell | -3.065 |
dash | -3.055 |
undo | -3.055 |
boro | -2.957 |
FTWARE | -2.876 |
Token | Barack |
Token ID | 8732 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
dash | +0.134 |
hell | +0.134 |
undo | +0.133 |
ALEC | +0.128 |
boro | +0.127 |
Neg logit contributions | |
fins | -0.155 |
ities | -0.155 |
Advantage | -0.149 |
isite | -0.149 |
iaz | -0.146 |
Token | Obama |
Token ID | 2486 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
ities | +2.457 |
fins | +2.438 |
Advantage | +2.372 |
isite | +2.339 |
ity | +2.313 |
Neg logit contributions | |
dash | -1.840 |
hell | -1.823 |
undo | -1.815 |
ALEC | -1.730 |
boro | -1.719 |
Token | and |
Token ID | 290 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
ities | +1.719 |
fins | +1.693 |
Advantage | +1.642 |
ity | +1.623 |
iaz | +1.618 |
Neg logit contributions | |
dash | -1.485 |
hell | -1.477 |
undo | -1.466 |
ALEC | -1.418 |
boro | -1.393 |
Token | language |
Token ID | 3303 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
hell | +0.422 |
dash | +0.421 |
undo | +0.417 |
ALEC | +0.407 |
boro | +0.402 |
Neg logit contributions | |
fins | -0.295 |
ities | -0.289 |
isite | -0.285 |
Advantage | -0.279 |
pta | -0.278 |
Token | . |
Token ID | 13 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
ities | +0.873 |
fins | +0.871 |
isite | +0.842 |
Advantage | +0.839 |
iaz | +0.825 |
Neg logit contributions | |
dash | -0.788 |
hell | -0.787 |
undo | -0.777 |
ALEC | -0.747 |
boro | -0.741 |
Token | - |
Token ID | 532 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
ities | +0.652 |
fins | +0.650 |
Advantage | +0.632 |
isite | +0.620 |
pta | +0.612 |
Neg logit contributions | |
dash | -0.575 |
hell | -0.573 |
undo | -0.570 |
ALEC | -0.546 |
boro | -0.541 |
Token | Katherine |
Token ID | 32719 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
ities | +2.052 |
fins | +2.029 |
Advantage | +1.981 |
isite | +1.944 |
ity | +1.935 |
Neg logit contributions | |
dash | -1.208 |
hell | -1.208 |
undo | -1.205 |
boro | -1.135 |
ALEC | -1.134 |
Token | d |
Token ID | 288 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
hell | +0.437 |
dash | +0.436 |
undo | +0.435 |
ALEC | +0.419 |
boro | +0.417 |
Neg logit contributions | |
fins | -0.326 |
ities | -0.323 |
Advantage | -0.309 |
isite | -0.305 |
iaz | -0.301 |
Token | ' |
Token ID | 6 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
ities | +4.441 |
fins | +4.338 |
Advantage | +4.129 |
ity | +4.128 |
iaz | +4.119 |
Neg logit contributions | |
undo | -4.803 |
hell | -4.792 |
dash | -4.734 |
ALEC | -4.612 |
boro | -4.543 |
Token | Ent |
Token ID | 14539 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
ities | +4.484 |
fins | +4.160 |
ity | +4.137 |
isite | +4.065 |
Advantage | +3.989 |
Neg logit contributions | |
dash | -8.546 |
undo | -8.542 |
hell | -8.391 |
ALEC | -8.290 |
boro | -8.217 |
Token | rem |
Token ID | 2787 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
fins | +0.708 |
ities | +0.698 |
Advantage | +0.684 |
isite | +0.680 |
iaz | +0.670 |
Neg logit contributions | |
dash | -0.327 |
hell | -0.326 |
undo | -0.322 |
ALEC | -0.300 |
boro | -0.298 |
Token | ont |
Token ID | 756 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
ities | +2.679 |
fins | +2.655 |
isite | +2.599 |
pta | +2.533 |
Advantage | +2.520 |
Neg logit contributions | |
dash | -2.370 |
hell | -2.343 |
undo | -2.332 |
ALEC | -2.310 |
boro | -2.224 |
Token | , |
Token ID | 11 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
ities | +2.690 |
fins | +2.660 |
Advantage | +2.568 |
ity | +2.525 |
isite | +2.525 |
Neg logit contributions | |
dash | -2.321 |
undo | -2.321 |
hell | -2.303 |
FTWARE | -2.179 |
ALEC | -2.177 |
Token | commissioner |
Token ID | 16248 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
ities | +1.377 |
fins | +1.371 |
Advantage | +1.333 |
isite | +1.309 |
pta | +1.278 |
Neg logit contributions | |
undo | -1.444 |
dash | -1.435 |
hell | -1.432 |
boro | -1.363 |
ALEC | -1.361 |
Token |
|
Token ID | 198 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
ities | +1.662 |
fins | +1.623 |
Advantage | +1.623 |
isite | +1.583 |
ity | +1.577 |
Neg logit contributions | |
dash | -1.565 |
undo | -1.555 |
hell | -1.537 |
ALEC | -1.431 |
acus | -1.430 |
Token |
|
Token ID | 198 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
hell | +0.525 |
dash | +0.523 |
undo | +0.510 |
ALEC | +0.495 |
boro | +0.486 |
Neg logit contributions | |
fins | -0.918 |
ities | -0.898 |
isite | -0.891 |
Advantage | -0.877 |
mosqu | -0.874 |
Token | In |
Token ID | 818 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ities | +0.844 |
fins | +0.813 |
isite | +0.794 |
ity | +0.789 |
iaz | +0.774 |
Neg logit contributions | |
dash | -0.930 |
undo | -0.928 |
hell | -0.925 |
ALEC | -0.920 |
boro | -0.890 |
Token | 1973 |
Token ID | 15674 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
ities | +0.410 |
fins | +0.409 |
Advantage | +0.389 |
isite | +0.388 |
iaz | +0.379 |
Neg logit contributions | |
dash | -0.445 |
undo | -0.444 |
hell | -0.442 |
ALEC | -0.427 |
boro | -0.422 |
Token | , |
Token ID | 11 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
dash | +1.822 |
hell | +1.809 |
undo | +1.803 |
ALEC | +1.724 |
boro | +1.699 |
Neg logit contributions | |
ities | -2.233 |
fins | -2.231 |
isite | -2.151 |
Advantage | -2.142 |
pta | -2.098 |
Token | Beth |
Token ID | 19223 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
dash | +1.305 |
hell | +1.294 |
undo | +1.289 |
ALEC | +1.234 |
boro | +1.222 |
Neg logit contributions | |
fins | -1.343 |
ities | -1.340 |
isite | -1.287 |
Advantage | -1.284 |
pta | -1.254 |
Token | une |
Token ID | 1726 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
hell | +3.155 |
undo | +3.141 |
dash | +2.969 |
boro | +2.784 |
ALEC | +2.582 |
Neg logit contributions | |
fins | -11.097 |
mosqu | -10.914 |
ities | -10.725 |
inflamm | -10.700 |
isite | -10.687 |
Token | was |
Token ID | 373 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
hell | +1.762 |
dash | +1.762 |
undo | +1.743 |
ALEC | +1.688 |
boro | +1.659 |
Neg logit contributions | |
fins | -2.281 |
ities | -2.269 |
isite | -2.196 |
Advantage | -2.182 |
iaz | -2.149 |
Token | induct |
Token ID | 28948 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
dash | +1.106 |
hell | +1.090 |
undo | +1.083 |
boro | +1.032 |
ALEC | +1.032 |
Neg logit contributions | |
fins | -1.378 |
ities | -1.368 |
isite | -1.311 |
Advantage | -1.311 |
ity | -1.292 |
Token | ed |
Token ID | 276 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
ities | +0.843 |
fins | +0.840 |
isite | +0.795 |
Advantage | +0.781 |
iaz | +0.774 |
Neg logit contributions | |
hell | -1.373 |
dash | -1.370 |
undo | -1.363 |
ALEC | -1.331 |
boro | -1.321 |
Token | into |
Token ID | 656 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
dash | +0.115 |
undo | +0.114 |
hell | +0.114 |
ALEC | +0.108 |
boro | +0.108 |
Neg logit contributions | |
ities | -0.123 |
fins | -0.123 |
isite | -0.117 |
Advantage | -0.117 |
ity | -0.116 |
Token | � |
Token ID | 447 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
dash | +0.667 |
hell | +0.667 |
undo | +0.661 |
ALEC | +0.641 |
boro | +0.634 |
Neg logit contributions | |
fins | -0.661 |
ities | -0.657 |
isite | -0.631 |
Advantage | -0.628 |
iaz | -0.616 |
Token | � |
Token ID | 251 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
hell | +1.178 |
dash | +1.177 |
undo | +1.161 |
ALEC | +1.139 |
boro | +1.123 |
Neg logit contributions | |
fins | -0.973 |
ities | -0.962 |
Advantage | -0.922 |
isite | -0.918 |
iaz | -0.901 |
Token | said |
Token ID | 531 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
fins | +0.049 |
ities | +0.049 |
Advantage | +0.047 |
isite | +0.047 |
ity | +0.046 |
Neg logit contributions | |
dash | -0.052 |
hell | -0.052 |
undo | -0.052 |
ALEC | -0.051 |
boro | -0.050 |
Token | Sen |
Token ID | 2311 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
hell | +3.172 |
dash | +3.166 |
undo | +3.133 |
ALEC | +3.062 |
boro | +3.004 |
Neg logit contributions | |
fins | -3.217 |
ities | -3.193 |
isite | -3.089 |
Advantage | -3.053 |
pta | -3.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
hell | +2.698 |
dash | +2.692 |
undo | +2.666 |
ALEC | +2.573 |
boro | +2.520 |
Neg logit contributions | |
fins | -4.148 |
ities | -4.117 |
isite | -3.991 |
Advantage | -3.981 |
iaz | -3.908 |
Token | Kay |
Token ID | 17356 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
hell | +2.910 |
dash | +2.903 |
undo | +2.857 |
ALEC | +2.845 |
boro | +2.766 |
Neg logit contributions | |
fins | -3.704 |
ities | -3.662 |
isite | -3.564 |
Advantage | -3.510 |
pta | -3.486 |
Token | Bailey |
Token ID | 20330 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
undo | +6.619 |
hell | +6.564 |
dash | +6.417 |
boro | +6.407 |
ALEC | +6.373 |
Neg logit contributions | |
fins | -6.884 |
isite | -6.721 |
ities | -6.709 |
arily | -6.556 |
pta | -6.502 |
Token | Hutch |
Token ID | 30492 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
undo | +1.144 |
dash | +1.141 |
hell | +1.137 |
ALEC | +1.106 |
boro | +1.093 |
Neg logit contributions | |
fins | -0.519 |
ities | -0.517 |
Advantage | -0.484 |
isite | -0.473 |
iaz | -0.468 |
Token | ison |
Token ID | 1653 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
ities | +1.346 |
fins | +1.258 |
ity | +1.209 |
iaz | +1.207 |
isite | +1.186 |
Neg logit contributions | |
undo | -2.037 |
dash | -1.984 |
hell | -1.975 |
boro | -1.933 |
ALEC | -1.897 |
Token | ( |
Token ID | 357 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
dash | +1.323 |
hell | +1.321 |
undo | +1.312 |
ALEC | +1.265 |
boro | +1.247 |
Neg logit contributions | |
fins | -1.532 |
ities | -1.528 |
Advantage | -1.466 |
isite | -1.465 |
iaz | -1.446 |
Token | R |
Token ID | 49 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
hell | +1.242 |
dash | +1.242 |
undo | +1.239 |
ALEC | +1.204 |
boro | +1.186 |
Neg logit contributions | |
ities | -0.877 |
fins | -0.877 |
Advantage | -0.833 |
isite | -0.828 |
iaz | -0.815 |
Token | The |
Token ID | 464 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
dash | +1.154 |
hell | +1.150 |
undo | +1.148 |
ALEC | +1.127 |
boro | +1.110 |
Neg logit contributions | |
ities | -0.998 |
fins | -0.985 |
isite | -0.949 |
Advantage | -0.937 |
ity | -0.924 |
Token | FCC |
Token ID | 15915 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
hell | +0.489 |
dash | +0.489 |
undo | +0.485 |
ALEC | +0.471 |
boro | +0.466 |
Neg logit contributions | |
fins | -0.439 |
ities | -0.437 |
isite | -0.419 |
Advantage | -0.417 |
iaz | -0.408 |
Token | accused |
Token ID | 5371 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
fins | +0.091 |
ities | +0.091 |
Advantage | +0.087 |
isite | +0.087 |
ity | +0.085 |
Neg logit contributions | |
dash | -0.081 |
hell | -0.081 |
undo | -0.080 |
ALEC | -0.077 |
boro | -0.076 |
Token | California |
Token ID | 3442 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
dash | +1.974 |
hell | +1.974 |
undo | +1.953 |
ALEC | +1.901 |
boro | +1.867 |
Neg logit contributions | |
fins | -2.205 |
ities | -2.192 |
isite | -2.118 |
Advantage | -2.098 |
iaz | -2.070 |
Token | - |
Token ID | 12 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
dash | +1.708 |
hell | +1.707 |
undo | +1.690 |
ALEC | +1.640 |
boro | +1.618 |
Neg logit contributions | |
fins | -1.659 |
ities | -1.652 |
isite | -1.586 |
Advantage | -1.585 |
iaz | -1.548 |
Token | based |
Token ID | 3106 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
dash | +3.443 |
hell | +3.443 |
undo | +3.391 |
ALEC | +3.289 |
boro | +3.257 |
Neg logit contributions | |
fins | -3.764 |
ities | -3.703 |
isite | -3.579 |
Advantage | -3.550 |
iaz | -3.512 |
Token | Total |
Token ID | 7472 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
ALEC | +6.743 |
dash | +6.628 |
hell | +6.601 |
undo | +6.501 |
boro | +6.317 |
Neg logit contributions | |
fins | -6.570 |
isite | -6.520 |
ities | -6.422 |
iaz | -6.203 |
arily | -6.083 |
Token | Call |
Token ID | 4889 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
hell | +2.090 |
dash | +2.089 |
undo | +2.074 |
ALEC | +2.016 |
boro | +1.986 |
Neg logit contributions | |
fins | -1.921 |
ities | -1.905 |
isite | -1.836 |
Advantage | -1.812 |
iaz | -1.787 |
Token | Mobile |
Token ID | 12173 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
ities | +1.901 |
Advantage | +1.876 |
fins | +1.863 |
iaz | +1.779 |
isite | +1.766 |
Neg logit contributions | |
dash | -2.189 |
hell | -2.165 |
ALEC | -2.102 |
undo | -2.101 |
boro | -2.075 |
Token | of |
Token ID | 286 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
ities | +1.061 |
fins | +1.050 |
Advantage | +1.043 |
isite | +0.989 |
ity | +0.989 |
Neg logit contributions | |
dash | -1.155 |
hell | -1.136 |
undo | -1.115 |
ALEC | -1.098 |
boro | -1.087 |
Token | fraud |
Token ID | 7394 |
Feature activation | +9.10e-02 |
Pos logit contributions | |
fins | +2.364 |
ities | +2.362 |
Advantage | +2.292 |
ity | +2.185 |
isite | +2.163 |
Neg logit contributions | |
dash | -2.652 |
hell | -2.616 |
undo | -2.601 |
boro | -2.482 |
ALEC | -2.441 |
Token | slavery |
Token ID | 13503 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
fins | +0.729 |
ities | +0.728 |
Advantage | +0.692 |
ity | +0.683 |
isite | +0.682 |
Neg logit contributions | |
dash | -0.742 |
undo | -0.737 |
hell | -0.736 |
boro | -0.701 |
ALEC | -0.692 |
Token | . |
Token ID | 13 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
dash | +0.125 |
undo | +0.123 |
hell | +0.123 |
ALEC | +0.119 |
boro | +0.117 |
Neg logit contributions | |
fins | -0.142 |
ities | -0.141 |
Advantage | -0.135 |
isite | -0.134 |
ity | -0.132 |
Token | The |
Token ID | 383 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
ities | +0.106 |
fins | +0.105 |
Advantage | +0.103 |
isite | +0.100 |
ity | +0.099 |
Neg logit contributions | |
dash | -0.112 |
undo | -0.112 |
hell | -0.111 |
boro | -0.106 |
ALEC | -0.106 |
Token | 18 |
Token ID | 1248 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
ities | +1.625 |
fins | +1.601 |
Advantage | +1.527 |
isite | +1.515 |
ity | +1.491 |
Neg logit contributions | |
dash | -1.868 |
hell | -1.847 |
undo | -1.846 |
boro | -1.766 |
ALEC | -1.764 |
Token | 76 |
Token ID | 4304 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
dash | +2.121 |
hell | +2.120 |
undo | +2.102 |
ALEC | +2.042 |
boro | +2.010 |
Neg logit contributions | |
fins | -2.242 |
ities | -2.231 |
isite | -2.147 |
Advantage | -2.135 |
iaz | -2.097 |
Token | Freed |
Token ID | 38728 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
dash | +0.330 |
hell | +0.329 |
undo | +0.326 |
ALEC | +0.314 |
boro | +0.312 |
Neg logit contributions | |
ities | -0.305 |
fins | -0.302 |
Advantage | -0.289 |
isite | -0.289 |
ity | -0.282 |
Token | men |
Token ID | 3653 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
hell | +5.906 |
dash | +5.844 |
undo | +5.834 |
ALEC | +5.621 |
boro | +5.556 |
Neg logit contributions | |
fins | -7.601 |
ities | -7.355 |
isite | -7.329 |
pta | -7.193 |
Advantage | -7.104 |
Token | � |
Token ID | 447 |
Feature activation | -8.93e-02 |
Pos logit contributions | |
hell | +2.185 |
dash | +2.184 |
undo | +2.160 |
ALEC | +2.091 |
boro | +2.053 |
Neg logit contributions | |
ities | -2.486 |
fins | -2.478 |
isite | -2.392 |
Advantage | -2.387 |
iaz | -2.330 |
Token | � |
Token ID | 247 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
dash | +0.328 |
hell | +0.326 |
undo | +0.324 |
ALEC | +0.319 |
boro | +0.314 |
Neg logit contributions | |
fins | -0.192 |
ities | -0.189 |
Advantage | -0.181 |
isite | -0.180 |
iaz | -0.176 |
Token | s |
Token ID | 82 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
dash | +1.067 |
hell | +1.066 |
undo | +1.056 |
ALEC | +1.031 |
boro | +1.014 |
Neg logit contributions | |
ities | -0.970 |
fins | -0.969 |
isite | -0.928 |
Advantage | -0.922 |
iaz | -0.904 |
Token | Memorial |
Token ID | 14861 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
ities | +1.162 |
Advantage | +1.117 |
fins | +1.112 |
isite | +1.080 |
iaz | +1.078 |
Neg logit contributions | |
dash | -1.197 |
undo | -1.191 |
hell | -1.171 |
ALEC | -1.144 |
FTWARE | -1.118 |
Token | : |
Token ID | 25 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
dash | +0.308 |
hell | +0.308 |
undo | +0.305 |
ALEC | +0.296 |
boro | +0.291 |
Neg logit contributions | |
fins | -0.340 |
ities | -0.338 |
Advantage | -0.326 |
isite | -0.325 |
ity | -0.316 |
Token | The |
Token ID | 383 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
fins | +2.171 |
ities | +2.157 |
Advantage | +2.141 |
isite | +2.042 |
ity | +2.027 |
Neg logit contributions | |
dash | -2.554 |
undo | -2.510 |
hell | -2.483 |
ALEC | -2.397 |
boro | -2.380 |
Token | Ride |
Token ID | 21640 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
fins | +3.262 |
Advantage | +3.221 |
ities | +3.209 |
isite | +3.044 |
ity | +3.044 |
Neg logit contributions | |
dash | -3.919 |
hell | -3.825 |
undo | -3.808 |
ALEC | -3.720 |
boro | -3.664 |
Token | . |
Token ID | 13 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
dash | +4.530 |
hell | +4.497 |
undo | +4.442 |
ALEC | +4.278 |
boro | +4.246 |
Neg logit contributions | |
ities | -5.289 |
fins | -5.253 |
isite | -5.103 |
pta | -5.025 |
iaz | -5.009 |
Token | The |
Token ID | 383 |
Feature activation | +7.87e-03 |
Pos logit contributions | |
dash | +0.826 |
hell | +0.825 |
undo | +0.819 |
ALEC | +0.793 |
boro | +0.784 |
Neg logit contributions | |
fins | -0.782 |
ities | -0.778 |
Advantage | -0.748 |
isite | -0.748 |
pta | -0.727 |
Token | ride |
Token ID | 6594 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
fins | +0.026 |
ities | +0.025 |
Advantage | +0.024 |
isite | +0.024 |
ity | +0.024 |
Neg logit contributions | |
hell | -0.020 |
dash | -0.020 |
undo | -0.020 |
ALEC | -0.019 |
boro | -0.019 |
Token | includes |
Token ID | 3407 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
dash | +5.849 |
hell | +5.772 |
undo | +5.702 |
boro | +5.585 |
ALEC | +5.559 |
Neg logit contributions | |
ities | -6.743 |
isite | -6.731 |
fins | -6.663 |
pta | -6.646 |
iaz | -6.640 |
Token | a |
Token ID | 257 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
hell | +1.510 |
dash | +1.509 |
undo | +1.498 |
ALEC | +1.454 |
boro | +1.435 |
Neg logit contributions | |
fins | -1.463 |
ities | -1.450 |
isite | -1.392 |
Advantage | -1.384 |
iaz | -1.357 |
Token | rotating |
Token ID | 24012 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
hell | +0.957 |
dash | +0.956 |
undo | +0.949 |
ALEC | +0.923 |
boro | +0.910 |
Neg logit contributions | |
fins | -0.926 |
ities | -0.917 |
isite | -0.881 |
Advantage | -0.876 |
iaz | -0.860 |
Token | platform |
Token ID | 3859 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
dash | +3.845 |
hell | +3.828 |
undo | +3.810 |
ALEC | +3.727 |
boro | +3.642 |
Neg logit contributions | |
ities | -3.442 |
fins | -3.426 |
isite | -3.343 |
pta | -3.286 |
Advantage | -3.272 |
Token | that |
Token ID | 326 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
dash | +1.824 |
hell | +1.824 |
undo | +1.807 |
ALEC | +1.756 |
boro | +1.729 |
Neg logit contributions | |
fins | -1.906 |
ities | -1.895 |
isite | -1.826 |
Advantage | -1.814 |
iaz | -1.783 |
Token | OUNT |
Token ID | 28270 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
ities | +0.172 |
fins | +0.170 |
isite | +0.162 |
Advantage | +0.162 |
ity | +0.160 |
Neg logit contributions | |
dash | -0.143 |
hell | -0.141 |
undo | -0.140 |
ALEC | -0.136 |
boro | -0.135 |
Token | ( |
Token ID | 357 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
dash | +1.876 |
hell | +1.875 |
undo | +1.857 |
ALEC | +1.805 |
boro | +1.776 |
Neg logit contributions | |
fins | -2.014 |
ities | -2.003 |
isite | -1.932 |
Advantage | -1.919 |
iaz | -1.888 |
Token | * |
Token ID | 1635 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
fins | +0.305 |
ities | +0.302 |
isite | +0.289 |
Advantage | +0.288 |
pta | +0.280 |
Neg logit contributions | |
hell | -0.368 |
dash | -0.367 |
undo | -0.361 |
ALEC | -0.353 |
boro | -0.350 |
Token | ) |
Token ID | 1267 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
dash | +3.345 |
hell | +3.333 |
undo | +3.318 |
ALEC | +3.218 |
boro | +3.153 |
Neg logit contributions | |
fins | -4.068 |
ities | -4.054 |
isite | -3.949 |
Advantage | -3.903 |
iaz | -3.869 |
Token | AS |
Token ID | 7054 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
fins | +0.921 |
ities | +0.907 |
Advantage | +0.875 |
isite | +0.865 |
pta | +0.846 |
Neg logit contributions | |
hell | -1.016 |
dash | -1.013 |
undo | -1.002 |
boro | -0.967 |
ALEC | -0.965 |
Token | count |
Token ID | 954 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
fins | +0.409 |
ities | +0.406 |
isite | +0.389 |
Advantage | +0.388 |
ity | +0.378 |
Neg logit contributions | |
dash | -0.443 |
hell | -0.442 |
undo | -0.437 |
ALEC | -0.423 |
boro | -0.421 |
Token | FROM |
Token ID | 16034 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
dash | +5.830 |
undo | +5.819 |
hell | +5.805 |
ALEC | +5.654 |
boro | +5.461 |
Neg logit contributions | |
fins | -6.734 |
ities | -6.685 |
isite | -6.553 |
iaz | -6.474 |
Advantage | -6.445 |
Token | ( |
Token ID | 357 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
ities | +0.667 |
fins | +0.663 |
isite | +0.624 |
Advantage | +0.611 |
ity | +0.605 |
Neg logit contributions | |
undo | -1.034 |
dash | -1.033 |
hell | -1.023 |
ALEC | -0.995 |
boro | -0.993 |
Token | SELECT |
Token ID | 33493 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
hell | +0.695 |
dash | +0.693 |
undo | +0.687 |
ALEC | +0.670 |
boro | +0.663 |
Neg logit contributions | |
fins | -0.579 |
ities | -0.576 |
isite | -0.552 |
Advantage | -0.546 |
pta | -0.534 |
Token | SPL |
Token ID | 46341 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
ities | +3.305 |
fins | +3.269 |
isite | +3.165 |
Advantage | +3.113 |
ity | +3.092 |
Neg logit contributions | |
dash | -3.913 |
hell | -3.877 |
undo | -3.821 |
boro | -3.695 |
acus | -3.681 |
Token | IT |
Token ID | 2043 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
ities | +2.046 |
fins | +2.026 |
isite | +1.947 |
ity | +1.933 |
Advantage | +1.923 |
Neg logit contributions | |
dash | -2.166 |
undo | -2.118 |
hell | -2.111 |
boro | -2.094 |
ALEC | -2.060 |
Token | sell |
Token ID | 3677 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
dash | +2.438 |
hell | +2.437 |
undo | +2.412 |
ALEC | +2.363 |
boro | +2.320 |
Neg logit contributions | |
fins | -2.501 |
ities | -2.467 |
isite | -2.410 |
Advantage | -2.375 |
pta | -2.336 |
Token | its |
Token ID | 663 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
fins | +1.053 |
ities | +1.046 |
Advantage | +1.012 |
isite | +1.005 |
ity | +0.980 |
Neg logit contributions | |
hell | -1.089 |
dash | -1.081 |
undo | -1.068 |
boro | -1.023 |
ALEC | -1.020 |
Token | RF |
Token ID | 20445 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
dash | +2.142 |
hell | +2.136 |
undo | +2.125 |
ALEC | +2.081 |
boro | +2.039 |
Neg logit contributions | |
fins | -1.943 |
ities | -1.925 |
isite | -1.857 |
Advantage | -1.830 |
pta | -1.812 |
Token | ID |
Token ID | 2389 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
dash | +1.899 |
hell | +1.894 |
undo | +1.878 |
ALEC | +1.822 |
boro | +1.795 |
Neg logit contributions | |
fins | -1.929 |
ities | -1.916 |
isite | -1.848 |
Advantage | -1.830 |
iaz | -1.802 |
Token | - |
Token ID | 12 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
hell | +1.715 |
dash | +1.715 |
undo | +1.700 |
ALEC | +1.658 |
boro | +1.637 |
Neg logit contributions | |
fins | -1.360 |
ities | -1.351 |
isite | -1.294 |
Advantage | -1.285 |
iaz | -1.259 |
Token | based |
Token ID | 3106 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
dash | +2.887 |
hell | +2.877 |
undo | +2.841 |
ALEC | +2.729 |
boro | +2.710 |
Neg logit contributions | |
fins | -3.425 |
ities | -3.392 |
isite | -3.289 |
Advantage | -3.259 |
pta | -3.212 |
Token | products |
Token ID | 3186 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
dash | +6.940 |
undo | +6.807 |
ALEC | +6.773 |
hell | +6.716 |
boro | +6.484 |
Neg logit contributions | |
fins | -5.608 |
isite | -5.512 |
ities | -5.464 |
pta | -5.365 |
iaz | -5.255 |
Token | throughout |
Token ID | 3690 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
hell | +0.625 |
dash | +0.624 |
undo | +0.620 |
ALEC | +0.600 |
boro | +0.592 |
Neg logit contributions | |
fins | -0.701 |
ities | -0.699 |
Advantage | -0.671 |
isite | -0.671 |
iaz | -0.658 |
Token | its |
Token ID | 663 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
dash | +1.416 |
hell | +1.415 |
undo | +1.405 |
ALEC | +1.359 |
boro | +1.344 |
Neg logit contributions | |
fins | -1.482 |
ities | -1.475 |
isite | -1.419 |
Advantage | -1.413 |
iaz | -1.386 |
Token | global |
Token ID | 3298 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
dash | +2.991 |
hell | +2.983 |
undo | +2.937 |
ALEC | +2.918 |
boro | +2.832 |
Neg logit contributions | |
fins | -2.787 |
ities | -2.758 |
isite | -2.683 |
pta | -2.624 |
Advantage | -2.622 |
Token | customer |
Token ID | 6491 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
dash | +2.825 |
hell | +2.815 |
undo | +2.784 |
ALEC | +2.741 |
boro | +2.670 |
Neg logit contributions | |
fins | -2.938 |
ities | -2.898 |
isite | -2.834 |
pta | -2.790 |
Advantage | -2.778 |
Token | , |
Token ID | 11 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
dash | +2.896 |
hell | +2.885 |
undo | +2.860 |
ALEC | +2.788 |
boro | +2.719 |
Neg logit contributions | |
fins | -4.594 |
ities | -4.568 |
isite | -4.414 |
Advantage | -4.398 |
iaz | -4.356 |
Token | this |
Token ID | 428 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
hell | +2.496 |
dash | +2.491 |
undo | +2.466 |
ALEC | +2.438 |
boro | +2.376 |
Neg logit contributions | |
fins | -2.964 |
ities | -2.957 |
isite | -2.874 |
iaz | -2.823 |
pta | -2.819 |
Token | week |
Token ID | 1285 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
dash | +0.933 |
hell | +0.933 |
undo | +0.925 |
ALEC | +0.903 |
boro | +0.889 |
Neg logit contributions | |
fins | -0.810 |
ities | -0.805 |
isite | -0.773 |
Advantage | -0.767 |
iaz | -0.754 |
Token | Kirk |
Token ID | 13855 |
Feature activation | +8.47e-02 |
Pos logit contributions | |
dash | +2.456 |
hell | +2.451 |
undo | +2.427 |
ALEC | +2.365 |
boro | +2.319 |
Neg logit contributions | |
fins | -3.044 |
ities | -3.024 |
isite | -2.933 |
Advantage | -2.901 |
iaz | -2.873 |
Token | Herb |
Token ID | 34858 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
ities | +0.200 |
fins | +0.194 |
isite | +0.183 |
Advantage | +0.183 |
ity | +0.180 |
Neg logit contributions | |
undo | -0.297 |
dash | -0.296 |
hell | -0.293 |
boro | -0.285 |
ALEC | -0.284 |
Token | stre |
Token ID | 22853 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
hell | +0.250 |
dash | +0.248 |
undo | +0.241 |
ALEC | +0.241 |
boro | +0.233 |
Neg logit contributions | |
ities | -0.424 |
fins | -0.419 |
Advantage | -0.410 |
isite | -0.403 |
ity | -0.402 |
Token | it |
Token ID | 270 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
hell | +5.224 |
dash | +5.075 |
undo | +4.976 |
ALEC | +4.787 |
boro | +4.694 |
Neg logit contributions | |
fins | -7.773 |
ities | -7.695 |
isite | -7.537 |
Advantage | -7.528 |
pta | -7.277 |
Token | , |
Token ID | 11 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
dash | +1.359 |
hell | +1.358 |
undo | +1.345 |
ALEC | +1.305 |
boro | +1.283 |
Neg logit contributions | |
fins | -1.578 |
ities | -1.571 |
isite | -1.514 |
Advantage | -1.506 |
iaz | -1.482 |
Token | Lee |
Token ID | 5741 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
hell | +1.124 |
dash | +1.124 |
undo | +1.112 |
ALEC | +1.075 |
boro | +1.060 |
Neg logit contributions | |
fins | -1.295 |
ities | -1.287 |
isite | -1.240 |
Advantage | -1.239 |
iaz | -1.213 |
Token | Cor |
Token ID | 2744 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
ities | +0.344 |
fins | +0.336 |
Advantage | +0.327 |
isite | +0.323 |
pta | +0.319 |
Neg logit contributions | |
dash | -0.385 |
hell | -0.377 |
undo | -0.376 |
ALEC | -0.367 |
boro | -0.360 |
Token | so |
Token ID | 568 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
ities | +3.190 |
iaz | +3.061 |
ity | +3.036 |
isite | +3.017 |
fins | +3.016 |
Neg logit contributions | |
dash | -2.302 |
ALEC | -2.274 |
FTWARE | -2.227 |
undo | -2.225 |
hell | -2.224 |
Token | T |
Token ID | 309 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
fins | +0.003 |
ities | +0.003 |
Advantage | +0.003 |
isite | +0.003 |
ity | +0.003 |
Neg logit contributions | |
dash | -0.003 |
hell | -0.003 |
undo | -0.003 |
ALEC | -0.003 |
boro | -0.003 |
Token | iki |
Token ID | 5580 |
Feature activation | -9.00e-03 |
Pos logit contributions | |
dash | +2.656 |
hell | +2.656 |
undo | +2.631 |
ALEC | +2.560 |
boro | +2.522 |
Neg logit contributions | |
fins | -2.598 |
ities | -2.583 |
isite | -2.486 |
Advantage | -2.469 |
iaz | -2.426 |
Token | Tw |
Token ID | 1815 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
dash | +0.027 |
hell | +0.027 |
undo | +0.027 |
ALEC | +0.027 |
boro | +0.026 |
Neg logit contributions | |
fins | -0.025 |
ities | -0.025 |
Advantage | -0.024 |
isite | -0.024 |
ity | -0.023 |
Token | irl |
Token ID | 1901 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
ities | +0.507 |
fins | +0.495 |
isite | +0.474 |
iaz | +0.465 |
ity | +0.454 |
Neg logit contributions | |
ALEC | -1.084 |
dash | -1.080 |
hell | -1.075 |
undo | -1.063 |
FTWARE | -1.050 |
Token | thrill |
Token ID | 28576 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
hell | +0.059 |
undo | +0.059 |
dash | +0.059 |
ALEC | +0.057 |
boro | +0.056 |
Neg logit contributions | |
fins | -0.060 |
ities | -0.059 |
Advantage | -0.057 |
isite | -0.057 |
ity | -0.056 |
Token | ride |
Token ID | 6594 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
hell | +1.806 |
dash | +1.793 |
undo | +1.791 |
ALEC | +1.740 |
boro | +1.678 |
Neg logit contributions | |
fins | -3.096 |
ities | -3.055 |
isite | -2.982 |
Advantage | -2.958 |
iaz | -2.927 |
Token | at |
Token ID | 379 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
dash | +5.911 |
hell | +5.879 |
undo | +5.779 |
ALEC | +5.622 |
boro | +5.585 |
Neg logit contributions | |
ities | -6.551 |
fins | -6.445 |
isite | -6.437 |
pta | -6.402 |
iaz | -6.295 |
Token | California |
Token ID | 3442 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
dash | +0.734 |
hell | +0.727 |
undo | +0.725 |
ALEC | +0.700 |
boro | +0.692 |
Neg logit contributions | |
fins | -0.743 |
ities | -0.736 |
Advantage | -0.709 |
isite | -0.708 |
iaz | -0.688 |
Token | 's |
Token ID | 338 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
hell | +0.308 |
undo | +0.308 |
dash | +0.308 |
ALEC | +0.293 |
boro | +0.289 |
Neg logit contributions | |
fins | -0.370 |
ities | -0.369 |
Advantage | -0.356 |
isite | -0.353 |
ity | -0.347 |
Token | Great |
Token ID | 3878 |
Feature activation | -4.19e-03 |
Pos logit contributions | |
dash | +2.162 |
hell | +2.161 |
undo | +2.142 |
ALEC | +2.085 |
boro | +2.056 |
Neg logit contributions | |
fins | -1.960 |
ities | -1.948 |
isite | -1.871 |
Advantage | -1.859 |
iaz | -1.824 |
Token | America |
Token ID | 2253 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
undo | +0.013 |
dash | +0.013 |
hell | +0.013 |
FTWARE | +0.012 |
ALEC | +0.012 |
Neg logit contributions | |
ities | -0.011 |
fins | -0.011 |
isite | -0.011 |
Advantage | -0.011 |
ity | -0.011 |
Token | { |
Token ID | 1391 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
dash | +0.684 |
hell | +0.684 |
undo | +0.675 |
ALEC | +0.658 |
boro | +0.649 |
Neg logit contributions | |
fins | -0.667 |
ities | -0.664 |
Advantage | -0.637 |
isite | -0.635 |
iaz | -0.622 |
Token | Center |
Token ID | 3337 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
fins | +0.188 |
ities | +0.186 |
Advantage | +0.181 |
isite | +0.178 |
iaz | +0.176 |
Neg logit contributions | |
hell | -0.212 |
dash | -0.212 |
undo | -0.209 |
ALEC | -0.204 |
boro | -0.201 |
Token | { |
Token ID | 1391 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
hell | +0.400 |
dash | +0.399 |
undo | +0.396 |
ALEC | +0.386 |
boro | +0.378 |
Neg logit contributions | |
fins | -0.425 |
ities | -0.425 |
Advantage | -0.408 |
isite | -0.404 |
ity | -0.397 |
Token | $ |
Token ID | 720 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
fins | +1.556 |
ities | +1.547 |
Advantage | +1.500 |
isite | +1.459 |
ity | +1.442 |
Neg logit contributions | |
hell | -1.735 |
dash | -1.715 |
undo | -1.710 |
ALEC | -1.676 |
boro | -1.649 |
Token | s |
Token ID | 82 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
hell | +0.184 |
dash | +0.184 |
undo | +0.181 |
ALEC | +0.180 |
boro | +0.176 |
Neg logit contributions | |
ities | -0.197 |
fins | -0.195 |
isite | -0.189 |
Advantage | -0.186 |
iaz | -0.184 |
Token | Format |
Token ID | 26227 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
dash | +1.284 |
hell | +1.275 |
undo | +1.263 |
ALEC | +1.250 |
boro | +1.216 |
Neg logit contributions | |
ities | -1.181 |
fins | -1.166 |
isite | -1.118 |
Advantage | -1.109 |
ity | -1.094 |
Token | . |
Token ID | 13 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
hell | +5.869 |
dash | +5.789 |
undo | +5.774 |
ALEC | +5.589 |
boro | +5.473 |
Neg logit contributions | |
fins | -6.680 |
ities | -6.558 |
isite | -6.393 |
Advantage | -6.325 |
iaz | -6.287 |
Token | Al |
Token ID | 2348 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
hell | +1.454 |
dash | +1.451 |
undo | +1.439 |
ALEC | +1.412 |
boro | +1.384 |
Neg logit contributions | |
fins | -1.591 |
ities | -1.587 |
isite | -1.525 |
Advantage | -1.515 |
iaz | -1.491 |
Token | ignment |
Token ID | 16747 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
dash | +0.767 |
hell | +0.757 |
undo | +0.756 |
ALEC | +0.739 |
boro | +0.718 |
Neg logit contributions | |
ities | -0.971 |
fins | -0.958 |
isite | -0.929 |
Advantage | -0.910 |
iaz | -0.909 |
Token | = |
Token ID | 796 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
hell | +0.436 |
dash | +0.435 |
undo | +0.431 |
ALEC | +0.417 |
boro | +0.412 |
Neg logit contributions | |
ities | -0.536 |
fins | -0.535 |
Advantage | -0.514 |
isite | -0.513 |
iaz | -0.503 |
Token | [ |
Token ID | 685 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
dash | +1.896 |
hell | +1.896 |
undo | +1.878 |
ALEC | +1.827 |
boro | +1.800 |
Neg logit contributions | |
fins | -1.854 |
ities | -1.843 |
isite | -1.774 |
Advantage | -1.762 |
iaz | -1.731 |
Token |
|
Token ID | 198 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
hell | +0.729 |
dash | +0.728 |
undo | +0.712 |
ALEC | +0.691 |
boro | +0.676 |
Neg logit contributions | |
fins | -1.231 |
ities | -1.209 |
isite | -1.192 |
Advantage | -1.172 |
iaz | -1.164 |
Token | The |
Token ID | 464 |
Feature activation | -8.41e-02 |
Pos logit contributions | |
hell | +0.185 |
dash | +0.184 |
undo | +0.184 |
ALEC | +0.181 |
boro | +0.179 |
Neg logit contributions | |
ities | -0.172 |
fins | -0.168 |
isite | -0.162 |
Advantage | -0.161 |
ity | -0.160 |
Token | first |
Token ID | 717 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
dash | +0.258 |
hell | +0.257 |
undo | +0.255 |
ALEC | +0.248 |
boro | +0.246 |
Neg logit contributions | |
fins | -0.231 |
ities | -0.231 |
Advantage | -0.220 |
isite | -0.220 |
iaz | -0.215 |
Token | proposal |
Token ID | 6961 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
fins | +1.046 |
ities | +1.041 |
Advantage | +0.989 |
isite | +0.983 |
ity | +0.968 |
Neg logit contributions | |
dash | -1.271 |
hell | -1.271 |
undo | -1.266 |
boro | -1.222 |
ALEC | -1.209 |
Token | , |
Token ID | 11 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
ities | +1.318 |
fins | +1.299 |
Advantage | +1.242 |
ity | +1.230 |
isite | +1.217 |
Neg logit contributions | |
dash | -1.276 |
undo | -1.272 |
hell | -1.263 |
boro | -1.210 |
FTWARE | -1.202 |
Token | Mandatory |
Token ID | 47018 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
fins | +0.977 |
ities | +0.973 |
Advantage | +0.936 |
isite | +0.930 |
iaz | +0.910 |
Neg logit contributions | |
dash | -0.939 |
hell | -0.929 |
undo | -0.927 |
boro | -0.892 |
ALEC | -0.878 |
Token | In |
Token ID | 554 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
undo | +6.088 |
dash | +6.070 |
hell | +5.958 |
ALEC | +5.912 |
boro | +5.702 |
Neg logit contributions | |
fins | -6.201 |
ities | -6.156 |
isite | -5.995 |
iaz | -5.942 |
pta | -5.866 |
Token | clusion |
Token ID | 4717 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
ities | +1.154 |
fins | +1.095 |
Advantage | +1.066 |
isite | +1.043 |
ity | +1.042 |
Neg logit contributions | |
undo | -2.409 |
dash | -2.401 |
hell | -2.389 |
ALEC | -2.364 |
boro | -2.321 |
Token | ary |
Token ID | 560 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
ities | +0.302 |
fins | +0.295 |
Advantage | +0.291 |
isite | +0.285 |
ity | +0.281 |
Neg logit contributions | |
hell | -0.304 |
dash | -0.302 |
undo | -0.299 |
ALEC | -0.292 |
boro | -0.289 |
Token | Housing |
Token ID | 16797 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
hell | +1.321 |
dash | +1.319 |
undo | +1.308 |
ALEC | +1.269 |
boro | +1.254 |
Neg logit contributions | |
ities | -1.302 |
fins | -1.299 |
Advantage | -1.245 |
isite | -1.240 |
iaz | -1.215 |
Token | , |
Token ID | 11 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
ities | +1.438 |
Advantage | +1.434 |
fins | +1.421 |
isite | +1.370 |
ity | +1.343 |
Neg logit contributions | |
hell | -1.367 |
dash | -1.357 |
undo | -1.342 |
boro | -1.296 |
FTWARE | -1.293 |
Token | [ |
Token ID | 58 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
ities | +1.848 |
fins | +1.829 |
Advantage | +1.761 |
isite | +1.736 |
pta | +1.726 |
Neg logit contributions | |
hell | -2.304 |
ALEC | -2.301 |
dash | -2.300 |
undo | -2.291 |
boro | -2.226 |
Token | white |
Token ID | 11186 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
dash | +1.577 |
hell | +1.576 |
undo | +1.560 |
ALEC | +1.532 |
boro | +1.503 |
Neg logit contributions | |
fins | -1.554 |
ities | -1.553 |
isite | -1.492 |
Advantage | -1.480 |
pta | -1.456 |
Token | ] |
Token ID | 60 |
Feature activation | +6.05e-02 |
Pos logit contributions | |
dash | +2.375 |
hell | +2.367 |
undo | +2.337 |
ALEC | +2.238 |
boro | +2.202 |
Neg logit contributions | |
fins | -4.099 |
ities | -4.062 |
isite | -3.949 |
Advantage | -3.932 |
iaz | -3.879 |
Token | se |
Token ID | 325 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ities | +0.190 |
fins | +0.190 |
isite | +0.183 |
Advantage | +0.182 |
pta | +0.179 |
Neg logit contributions | |
hell | -0.161 |
dash | -0.160 |
undo | -0.159 |
ALEC | -0.157 |
boro | -0.153 |
Token | [ |
Token ID | 58 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
hell | +3.081 |
dash | +3.076 |
undo | +3.050 |
ALEC | +2.954 |
boro | +2.921 |
Neg logit contributions | |
fins | -3.111 |
ities | -3.080 |
isite | -2.978 |
Advantage | -2.961 |
iaz | -2.908 |
Token | t |
Token ID | 83 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
dash | +2.151 |
hell | +2.150 |
undo | +2.130 |
ALEC | +2.070 |
boro | +2.038 |
Neg logit contributions | |
fins | -2.242 |
ities | -2.229 |
isite | -2.148 |
Advantage | -2.134 |
iaz | -2.098 |
Token | ] |
Token ID | 60 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
hell | +5.731 |
dash | +5.694 |
undo | +5.687 |
boro | +5.386 |
zone | +5.269 |
Neg logit contributions | |
fins | -6.719 |
ities | -6.419 |
Advantage | -6.412 |
isite | -6.357 |
iaz | -6.156 |
Token | { |
Token ID | 1391 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
ities | +0.129 |
fins | +0.128 |
isite | +0.123 |
Advantage | +0.123 |
pta | +0.121 |
Neg logit contributions | |
hell | -0.118 |
dash | -0.118 |
ALEC | -0.117 |
undo | -0.117 |
boro | -0.113 |
Token | options |
Token ID | 25811 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
ities | +0.777 |
fins | +0.769 |
isite | +0.743 |
Advantage | +0.740 |
pta | +0.731 |
Neg logit contributions | |
hell | -0.692 |
dash | -0.688 |
ALEC | -0.687 |
undo | -0.675 |
boro | -0.669 |
Token | } |
Token ID | 92 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
dash | +2.468 |
hell | +2.468 |
undo | +2.441 |
ALEC | +2.351 |
boro | +2.311 |
Neg logit contributions | |
fins | -3.512 |
ities | -3.488 |
isite | -3.381 |
Advantage | -3.366 |
iaz | -3.319 |
Token | :[ |
Token ID | 33250 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
ities | +0.503 |
fins | +0.502 |
Advantage | +0.481 |
isite | +0.479 |
pta | +0.469 |
Neg logit contributions | |
hell | -0.555 |
dash | -0.553 |
ALEC | -0.549 |
undo | -0.548 |
boro | -0.533 |
Token | but |
Token ID | 475 |
Feature activation | +9.46e-02 |
Pos logit contributions | |
dash | +0.514 |
hell | +0.514 |
undo | +0.509 |
ALEC | +0.497 |
boro | +0.490 |
Neg logit contributions | |
fins | -0.423 |
ities | -0.421 |
isite | -0.403 |
Advantage | -0.400 |
iaz | -0.392 |
Token | if |
Token ID | 611 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
fins | +0.266 |
ities | +0.266 |
Advantage | +0.252 |
isite | +0.252 |
ity | +0.246 |
Neg logit contributions | |
dash | -0.285 |
hell | -0.284 |
undo | -0.283 |
ALEC | -0.273 |
boro | -0.271 |
Token | it |
Token ID | 340 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
undo | +0.266 |
dash | +0.266 |
hell | +0.266 |
ALEC | +0.254 |
boro | +0.252 |
Neg logit contributions | |
fins | -0.372 |
ities | -0.371 |
isite | -0.356 |
Advantage | -0.355 |
iaz | -0.350 |
Token | was |
Token ID | 373 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
dash | +2.047 |
hell | +2.046 |
undo | +2.028 |
ALEC | +1.974 |
boro | +1.945 |
Neg logit contributions | |
fins | -1.915 |
ities | -1.904 |
isite | -1.830 |
Advantage | -1.818 |
iaz | -1.785 |
Token | a |
Token ID | 257 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
hell | +2.617 |
dash | +2.610 |
undo | +2.573 |
ALEC | +2.523 |
boro | +2.467 |
Neg logit contributions | |
fins | -2.706 |
ities | -2.688 |
isite | -2.613 |
Advantage | -2.575 |
pta | -2.545 |
Token | pie |
Token ID | 2508 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
hell | +1.739 |
dash | +1.738 |
undo | +1.721 |
ALEC | +1.681 |
boro | +1.656 |
Neg logit contributions | |
fins | -1.487 |
ities | -1.475 |
isite | -1.420 |
Advantage | -1.406 |
iaz | -1.381 |
Token | [ |
Token ID | 685 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
hell | +6.300 |
dash | +6.268 |
undo | +6.127 |
ALEC | +5.968 |
boro | +5.921 |
Neg logit contributions | |
fins | -6.209 |
ities | -6.171 |
isite | -5.924 |
Advantage | -5.846 |
pta | -5.802 |
Token | chart |
Token ID | 40926 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
dash | +0.646 |
hell | +0.645 |
undo | +0.644 |
ALEC | +0.636 |
boro | +0.619 |
Neg logit contributions | |
ities | -0.676 |
fins | -0.676 |
isite | -0.649 |
Advantage | -0.643 |
iaz | -0.637 |
Token | ], |
Token ID | 4357 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
dash | +3.750 |
hell | +3.719 |
undo | +3.691 |
ALEC | +3.570 |
boro | +3.506 |
Neg logit contributions | |
fins | -4.627 |
ities | -4.618 |
isite | -4.480 |
Advantage | -4.443 |
pta | -4.387 |
Token | it |
Token ID | 340 |
Feature activation | -5.73e-02 |
Pos logit contributions | |
fins | +0.671 |
ities | +0.671 |
Advantage | +0.638 |
isite | +0.636 |
ity | +0.625 |
Neg logit contributions | |
dash | -0.657 |
undo | -0.657 |
hell | -0.653 |
ALEC | -0.632 |
boro | -0.627 |
Token | would |
Token ID | 561 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
dash | +0.170 |
hell | +0.169 |
undo | +0.169 |
ALEC | +0.165 |
boro | +0.162 |
Neg logit contributions | |
fins | -0.163 |
ities | -0.162 |
isite | -0.155 |
Advantage | -0.154 |
pta | -0.152 |
Token | for |
Token ID | 329 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
dash | +0.782 |
hell | +0.781 |
undo | +0.775 |
ALEC | +0.752 |
boro | +0.743 |
Neg logit contributions | |
fins | -0.696 |
ities | -0.695 |
Advantage | -0.663 |
isite | -0.661 |
iaz | -0.647 |
Token | def |
Token ID | 825 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
fins | +0.138 |
ities | +0.137 |
Advantage | +0.131 |
isite | +0.129 |
ity | +0.127 |
Neg logit contributions | |
hell | -0.144 |
dash | -0.143 |
undo | -0.143 |
ALEC | -0.136 |
boro | -0.136 |
Token | raud |
Token ID | 22863 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
ities | +0.977 |
fins | +0.967 |
iaz | +0.935 |
isite | +0.934 |
Advantage | +0.922 |
Neg logit contributions | |
dash | -0.923 |
hell | -0.900 |
undo | -0.892 |
ALEC | -0.889 |
FTWARE | -0.870 |
Token | ing |
Token ID | 278 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
dash | +0.616 |
hell | +0.611 |
undo | +0.608 |
ALEC | +0.591 |
boro | +0.586 |
Neg logit contributions | |
fins | -0.388 |
ities | -0.384 |
isite | -0.365 |
Advantage | -0.362 |
iaz | -0.354 |
Token | its |
Token ID | 663 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
hell | +1.447 |
dash | +1.443 |
undo | +1.437 |
ALEC | +1.386 |
boro | +1.377 |
Neg logit contributions | |
fins | -1.365 |
ities | -1.355 |
Advantage | -1.302 |
isite | -1.295 |
pta | -1.264 |
Token | Lif |
Token ID | 21073 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
dash | +2.678 |
hell | +2.670 |
undo | +2.655 |
ALEC | +2.601 |
boro | +2.542 |
Neg logit contributions | |
fins | -2.565 |
ities | -2.541 |
isite | -2.480 |
Advantage | -2.411 |
iaz | -2.405 |
Token | eline |
Token ID | 4470 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
undo | +5.078 |
hell | +4.997 |
dash | +4.936 |
boro | +4.662 |
ALEC | +4.633 |
Neg logit contributions | |
fins | -7.411 |
ities | -7.223 |
isite | -7.054 |
Advantage | -7.047 |
iaz | -6.885 |
Token | program |
Token ID | 1430 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
hell | +1.113 |
dash | +1.110 |
undo | +1.099 |
ALEC | +1.071 |
boro | +1.056 |
Neg logit contributions | |
fins | -0.966 |
ities | -0.959 |
Advantage | -0.925 |
isite | -0.917 |
iaz | -0.895 |
Token | , |
Token ID | 11 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
dash | +0.932 |
hell | +0.932 |
undo | +0.922 |
ALEC | +0.895 |
boro | +0.885 |
Neg logit contributions | |
fins | -0.986 |
ities | -0.983 |
Advantage | -0.945 |
isite | -0.942 |
iaz | -0.925 |
Token | which |
Token ID | 543 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
dash | +1.151 |
hell | +1.150 |
undo | +1.139 |
ALEC | +1.106 |
boro | +1.094 |
Neg logit contributions | |
fins | -1.063 |
ities | -1.054 |
isite | -1.012 |
Advantage | -1.011 |
iaz | -0.986 |
Token | subsid |
Token ID | 7905 |
Feature activation | -9.88e-02 |
Pos logit contributions | |
dash | +0.042 |
hell | +0.042 |
undo | +0.042 |
ALEC | +0.040 |
boro | +0.040 |
Neg logit contributions | |
fins | -0.039 |
ities | -0.038 |
Advantage | -0.037 |
isite | -0.036 |
iaz | -0.036 |
Token | writing |
Token ID | 3597 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
dash | +1.598 |
hell | +1.598 |
undo | +1.583 |
ALEC | +1.538 |
boro | +1.515 |
Neg logit contributions | |
fins | -1.676 |
ities | -1.667 |
isite | -1.606 |
Advantage | -1.596 |
iaz | -1.569 |
Token | a |
Token ID | 257 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
dash | +1.142 |
hell | +1.142 |
undo | +1.132 |
ALEC | +1.100 |
boro | +1.088 |
Neg logit contributions | |
fins | -1.174 |
ities | -1.165 |
Advantage | -1.115 |
isite | -1.115 |
pta | -1.091 |
Token | D |
Token ID | 360 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
dash | +1.420 |
hell | +1.419 |
undo | +1.406 |
ALEC | +1.369 |
boro | +1.351 |
Neg logit contributions | |
fins | -1.387 |
ities | -1.378 |
isite | -1.323 |
Advantage | -1.317 |
iaz | -1.294 |
Token | MA |
Token ID | 5673 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
ities | +0.096 |
fins | +0.096 |
isite | +0.091 |
Advantage | +0.091 |
iaz | +0.091 |
Neg logit contributions | |
hell | -0.095 |
undo | -0.094 |
dash | -0.094 |
ALEC | -0.092 |
boro | -0.090 |
Token | - |
Token ID | 12 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
dash | +0.618 |
hell | +0.617 |
undo | +0.617 |
ALEC | +0.599 |
boro | +0.595 |
Neg logit contributions | |
fins | -0.633 |
ities | -0.629 |
Advantage | -0.603 |
isite | -0.602 |
iaz | -0.591 |
Token | based |
Token ID | 3106 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
undo | +1.012 |
hell | +1.010 |
dash | +1.009 |
ALEC | +0.995 |
boro | +0.977 |
Neg logit contributions | |
ities | -1.139 |
fins | -1.137 |
isite | -1.093 |
Advantage | -1.087 |
iaz | -1.072 |
Token | USB |
Token ID | 8450 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
dash | +6.207 |
hell | +6.160 |
undo | +6.089 |
ALEC | +5.944 |
boro | +5.689 |
Neg logit contributions | |
fins | -5.839 |
isite | -5.828 |
ities | -5.774 |
pta | -5.561 |
iaz | -5.506 |
Token | stack |
Token ID | 8931 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
dash | +0.478 |
hell | +0.478 |
undo | +0.478 |
ALEC | +0.465 |
boro | +0.461 |
Neg logit contributions | |
ities | -0.430 |
fins | -0.430 |
Advantage | -0.412 |
isite | -0.407 |
iaz | -0.401 |
Token | and |
Token ID | 290 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
dash | +0.301 |
undo | +0.301 |
hell | +0.299 |
ALEC | +0.291 |
boro | +0.287 |
Neg logit contributions | |
fins | -0.347 |
ities | -0.343 |
Advantage | -0.330 |
isite | -0.329 |
iaz | -0.324 |
Token | libraries |
Token ID | 12782 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
hell | +1.323 |
dash | +1.322 |
undo | +1.311 |
ALEC | +1.275 |
boro | +1.258 |
Neg logit contributions | |
fins | -1.287 |
ities | -1.278 |
isite | -1.228 |
Advantage | -1.222 |
iaz | -1.200 |
Token | that |
Token ID | 326 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
fins | +0.118 |
ities | +0.118 |
Advantage | +0.112 |
isite | +0.112 |
ity | +0.110 |
Neg logit contributions | |
dash | -0.109 |
undo | -0.108 |
hell | -0.106 |
ALEC | -0.104 |
boro | -0.103 |
Token | reached |
Token ID | 4251 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
dash | +0.349 |
hell | +0.347 |
undo | +0.344 |
ALEC | +0.334 |
boro | +0.329 |
Neg logit contributions | |
ities | -0.368 |
fins | -0.367 |
Advantage | -0.353 |
isite | -0.351 |
ity | -0.343 |
Token | the |
Token ID | 262 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
dash | +0.840 |
hell | +0.840 |
undo | +0.833 |
ALEC | +0.806 |
boro | +0.799 |
Neg logit contributions | |
fins | -0.827 |
ities | -0.826 |
isite | -0.791 |
Advantage | -0.790 |
pta | -0.770 |
Token | original |
Token ID | 2656 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
dash | +0.558 |
hell | +0.558 |
undo | +0.553 |
ALEC | +0.538 |
boro | +0.532 |
Neg logit contributions | |
fins | -0.465 |
ities | -0.463 |
isite | -0.442 |
Advantage | -0.440 |
iaz | -0.431 |
Token | border |
Token ID | 4865 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
ities | +0.555 |
fins | +0.549 |
isite | +0.517 |
Advantage | +0.517 |
ity | +0.511 |
Neg logit contributions | |
dash | -0.774 |
hell | -0.774 |
undo | -0.770 |
ALEC | -0.747 |
boro | -0.744 |
Token | .[ |
Token ID | 3693 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
hell | +0.381 |
dash | +0.379 |
undo | +0.379 |
ALEC | +0.368 |
boro | +0.363 |
Neg logit contributions | |
ities | -0.368 |
fins | -0.366 |
isite | -0.347 |
Advantage | -0.346 |
iaz | -0.341 |
Token | 19 |
Token ID | 1129 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
dash | +1.760 |
hell | +1.759 |
undo | +1.746 |
ALEC | +1.707 |
boro | +1.675 |
Neg logit contributions | |
fins | -1.601 |
ities | -1.601 |
isite | -1.531 |
Advantage | -1.524 |
iaz | -1.495 |
Token | ] |
Token ID | 60 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
hell | +3.961 |
dash | +3.948 |
undo | +3.858 |
ALEC | +3.652 |
boro | +3.600 |
Neg logit contributions | |
fins | -8.136 |
ities | -8.040 |
isite | -7.879 |
iaz | -7.827 |
Advantage | -7.795 |
Token |
|
Token ID | 198 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
dash | +0.203 |
hell | +0.203 |
undo | +0.202 |
ALEC | +0.195 |
boro | +0.193 |
Neg logit contributions | |
ities | -0.210 |
fins | -0.210 |
Advantage | -0.202 |
isite | -0.201 |
pta | -0.196 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
hell | +0.883 |
dash | +0.876 |
undo | +0.850 |
ALEC | +0.838 |
boro | +0.815 |
Neg logit contributions | |
fins | -1.555 |
ities | -1.516 |
isite | -1.503 |
mosqu | -1.478 |
Advantage | -1.476 |
Token | At |
Token ID | 2953 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
ities | +0.282 |
fins | +0.275 |
isite | +0.267 |
ity | +0.261 |
Advantage | +0.261 |
Neg logit contributions | |
dash | -0.313 |
hell | -0.313 |
undo | -0.312 |
ALEC | -0.310 |
boro | -0.302 |
Token | that |
Token ID | 326 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
ities | +0.686 |
fins | +0.678 |
isite | +0.650 |
Advantage | +0.649 |
iaz | +0.641 |
Neg logit contributions | |
dash | -0.694 |
undo | -0.689 |
hell | -0.686 |
ALEC | -0.664 |
boro | -0.658 |
Token | former |
Token ID | 1966 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
undo | +0.544 |
dash | +0.543 |
hell | +0.543 |
ALEC | +0.519 |
boro | +0.512 |
Neg logit contributions | |
fins | -0.603 |
ities | -0.597 |
Advantage | -0.574 |
isite | -0.569 |
iaz | -0.562 |
Token | St |
Token ID | 520 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
ities | +0.518 |
fins | +0.517 |
Advantage | +0.496 |
isite | +0.487 |
ity | +0.480 |
Neg logit contributions | |
dash | -0.576 |
hell | -0.572 |
undo | -0.572 |
ALEC | -0.550 |
boro | -0.540 |
Token | . |
Token ID | 13 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
dash | +0.598 |
hell | +0.593 |
undo | +0.591 |
ALEC | +0.572 |
boro | +0.556 |
Neg logit contributions | |
ities | -0.883 |
fins | -0.878 |
isite | -0.849 |
Advantage | -0.848 |
iaz | -0.840 |
Token | Louis |
Token ID | 5593 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
fins | +0.759 |
ities | +0.758 |
Advantage | +0.736 |
isite | +0.725 |
iaz | +0.709 |
Neg logit contributions | |
dash | -0.743 |
undo | -0.739 |
hell | -0.734 |
ALEC | -0.710 |
boro | -0.694 |
Token | Rams |
Token ID | 16077 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
fins | +3.549 |
ities | +3.543 |
Advantage | +3.404 |
iaz | +3.282 |
ity | +3.279 |
Neg logit contributions | |
undo | -4.757 |
dash | -4.714 |
hell | -4.589 |
ALEC | -4.528 |
FTWARE | -4.465 |
Token | kicker |
Token ID | 38297 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
ities | +1.359 |
fins | +1.355 |
Advantage | +1.301 |
ity | +1.277 |
isite | +1.268 |
Neg logit contributions | |
dash | -1.344 |
undo | -1.328 |
hell | -1.324 |
ALEC | -1.293 |
FTWARE | -1.244 |
Token | Brett |
Token ID | 18726 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
dash | +5.328 |
hell | +5.295 |
undo | +5.195 |
ALEC | +5.160 |
boro | +5.043 |
Neg logit contributions | |
fins | -6.697 |
ities | -6.644 |
isite | -6.570 |
pta | -6.410 |
Advantage | -6.385 |
Token | Ba |
Token ID | 8999 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
hell | +2.526 |
dash | +2.525 |
undo | +2.502 |
ALEC | +2.435 |
boro | +2.402 |
Neg logit contributions | |
fins | -2.366 |
ities | -2.350 |
isite | -2.263 |
Advantage | -2.242 |
iaz | -2.204 |
Token | er |
Token ID | 263 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
ities | +0.773 |
fins | +0.750 |
ity | +0.723 |
isite | +0.722 |
iaz | +0.720 |
Neg logit contributions | |
dash | -0.889 |
undo | -0.869 |
ALEC | -0.856 |
hell | -0.855 |
boro | -0.830 |
Token | – |
Token ID | 784 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
dash | +0.758 |
hell | +0.755 |
undo | +0.754 |
ALEC | +0.735 |
boro | +0.713 |
Neg logit contributions | |
ities | -0.864 |
fins | -0.863 |
Advantage | -0.821 |
isite | -0.821 |
iaz | -0.818 |
Token | who |
Token ID | 508 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
dash | +0.926 |
hell | +0.923 |
undo | +0.917 |
ALEC | +0.893 |
boro | +0.880 |
Neg logit contributions | |
fins | -0.784 |
ities | -0.778 |
Advantage | -0.743 |
isite | -0.740 |
iaz | -0.726 |
Token | . |
Token ID | 13 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
dash | +2.325 |
hell | +2.318 |
undo | +2.297 |
ALEC | +2.231 |
boro | +2.193 |
Neg logit contributions | |
fins | -2.337 |
ities | -2.334 |
isite | -2.236 |
Advantage | -2.233 |
iaz | -2.195 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
dash | +0.641 |
hell | +0.640 |
undo | +0.638 |
boro | +0.609 |
ALEC | +0.607 |
Neg logit contributions | |
ities | -0.623 |
fins | -0.620 |
Advantage | -0.604 |
isite | -0.592 |
ity | -0.583 |
Token | The |
Token ID | 464 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
dash | +0.980 |
hell | +0.978 |
undo | +0.976 |
ALEC | +0.963 |
boro | +0.939 |
Neg logit contributions | |
ities | -0.946 |
fins | -0.939 |
isite | -0.904 |
Advantage | -0.892 |
iaz | -0.885 |
Token | Bengals |
Token ID | 24037 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
dash | +1.322 |
hell | +1.320 |
undo | +1.310 |
ALEC | +1.273 |
boro | +1.259 |
Neg logit contributions | |
fins | -1.102 |
ities | -1.095 |
isite | -1.047 |
Advantage | -1.044 |
iaz | -1.019 |
Token | signed |
Token ID | 4488 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
dash | +0.041 |
hell | +0.040 |
undo | +0.040 |
ALEC | +0.039 |
boro | +0.038 |
Neg logit contributions | |
fins | -0.039 |
ities | -0.039 |
Advantage | -0.038 |
isite | -0.036 |
ity | -0.036 |
Token | kicker |
Token ID | 38297 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
hell | +1.198 |
dash | +1.196 |
undo | +1.185 |
ALEC | +1.141 |
boro | +1.128 |
Neg logit contributions | |
fins | -1.356 |
ities | -1.351 |
Advantage | -1.300 |
isite | -1.296 |
iaz | -1.272 |
Token | Jonathan |
Token ID | 11232 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
hell | +5.294 |
dash | +5.265 |
ALEC | +5.205 |
undo | +5.175 |
boro | +5.048 |
Neg logit contributions | |
fins | -6.687 |
ities | -6.590 |
isite | -6.549 |
pta | -6.430 |
Advantage | -6.317 |
Token | Brown |
Token ID | 4373 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
dash | +1.895 |
hell | +1.892 |
undo | +1.875 |
ALEC | +1.818 |
boro | +1.791 |
Neg logit contributions | |
fins | -2.027 |
ities | -2.021 |
isite | -1.944 |
Advantage | -1.937 |
iaz | -1.902 |
Token | , |
Token ID | 11 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
fins | +1.273 |
ities | +1.263 |
Advantage | +1.215 |
iaz | +1.215 |
isite | +1.195 |
Neg logit contributions | |
dash | -1.231 |
undo | -1.211 |
hell | -1.193 |
ALEC | -1.185 |
FTWARE | -1.133 |
Token | far |
Token ID | 1290 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
dash | +1.067 |
hell | +1.067 |
undo | +1.054 |
ALEC | +1.023 |
boro | +1.011 |
Neg logit contributions | |
fins | -1.000 |
ities | -0.988 |
Advantage | -0.952 |
isite | -0.946 |
iaz | -0.926 |
Token | right |
Token ID | 826 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
ities | +1.130 |
fins | +1.120 |
Advantage | +1.069 |
iaz | +1.058 |
isite | +1.057 |
Neg logit contributions | |
dash | -1.272 |
hell | -1.267 |
undo | -1.252 |
boro | -1.209 |
ALEC | -1.208 |
Token | , |
Token ID | 11 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
dash | +0.195 |
hell | +0.194 |
undo | +0.190 |
ALEC | +0.185 |
boro | +0.181 |
Neg logit contributions | |
ities | -0.243 |
fins | -0.241 |
Advantage | -0.237 |
isite | -0.232 |
pta | -0.230 |
Token | Wells |
Token ID | 18292 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
dash | +0.457 |
hell | +0.456 |
undo | +0.453 |
ALEC | +0.438 |
boro | +0.434 |
Neg logit contributions | |
fins | -0.436 |
ities | -0.436 |
Advantage | -0.418 |
isite | -0.417 |
iaz | -0.408 |
Token | Fargo |
Token ID | 28125 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
ities | +1.997 |
fins | +1.993 |
Advantage | +1.932 |
isite | +1.902 |
iaz | +1.875 |
Neg logit contributions | |
dash | -2.128 |
undo | -2.109 |
hell | -2.102 |
ALEC | -2.035 |
boro | -1.956 |
Token | , |
Token ID | 11 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
ities | +0.149 |
fins | +0.149 |
Advantage | +0.144 |
isite | +0.143 |
iaz | +0.141 |
Neg logit contributions | |
dash | -0.113 |
hell | -0.112 |
undo | -0.111 |
ALEC | -0.107 |
boro | -0.105 |
Token | and |
Token ID | 290 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
hell | +1.961 |
dash | +1.954 |
undo | +1.934 |
ALEC | +1.900 |
boro | +1.858 |
Neg logit contributions | |
fins | -1.958 |
ities | -1.930 |
isite | -1.878 |
Advantage | -1.833 |
pta | -1.827 |
Token | Ally |
Token ID | 43039 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
dash | +1.259 |
hell | +1.259 |
undo | +1.247 |
ALEC | +1.213 |
boro | +1.193 |
Neg logit contributions | |
fins | -1.349 |
ities | -1.340 |
isite | -1.295 |
Advantage | -1.283 |
iaz | -1.263 |
Token | Bank |
Token ID | 5018 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
hell | +6.884 |
undo | +6.865 |
dash | +6.693 |
boro | +6.683 |
ALEC | +6.523 |
Neg logit contributions | |
fins | -5.177 |
ities | -5.097 |
isite | -5.002 |
pta | -4.726 |
arily | -4.688 |
Token | — |
Token ID | 960 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
hell | +1.794 |
dash | +1.784 |
undo | +1.775 |
ALEC | +1.718 |
boro | +1.694 |
Neg logit contributions | |
fins | -2.078 |
ities | -2.058 |
isite | -2.012 |
Advantage | -1.973 |
pta | -1.952 |
Token | the |
Token ID | 1169 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
hell | +1.835 |
dash | +1.831 |
undo | +1.811 |
ALEC | +1.753 |
boro | +1.728 |
Neg logit contributions | |
fins | -2.171 |
ities | -2.155 |
isite | -2.086 |
Advantage | -2.071 |
iaz | -2.038 |
Token | nation |
Token ID | 3277 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
hell | +0.797 |
dash | +0.793 |
undo | +0.787 |
ALEC | +0.773 |
boro | +0.759 |
Neg logit contributions | |
fins | -0.611 |
ities | -0.606 |
isite | -0.585 |
Advantage | -0.577 |
iaz | -0.570 |
Token | � |
Token ID | 447 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
dash | +0.298 |
hell | +0.298 |
undo | +0.295 |
ALEC | +0.285 |
boro | +0.281 |
Neg logit contributions | |
fins | -0.351 |
ities | -0.349 |
isite | -0.336 |
Advantage | -0.335 |
iaz | -0.329 |
Token | . |
Token ID | 13 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
ities | +0.871 |
fins | +0.860 |
Advantage | +0.824 |
ity | +0.818 |
isite | +0.812 |
Neg logit contributions | |
undo | -0.736 |
hell | -0.720 |
dash | -0.717 |
boro | -0.695 |
ALEC | -0.683 |
Token | # |
Token ID | 1303 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
dash | +0.633 |
hell | +0.632 |
undo | +0.628 |
ALEC | +0.608 |
boro | +0.601 |
Neg logit contributions | |
fins | -0.633 |
ities | -0.630 |
Advantage | -0.605 |
isite | -0.603 |
iaz | -0.590 |
Token | atl |
Token ID | 25864 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
ities | +0.551 |
fins | +0.542 |
isite | +0.522 |
Advantage | +0.517 |
iaz | +0.517 |
Neg logit contributions | |
dash | -0.509 |
hell | -0.506 |
undo | -0.506 |
ALEC | -0.504 |
boro | -0.487 |
Token | weather |
Token ID | 23563 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
ities | +1.692 |
fins | +1.670 |
isite | +1.592 |
Advantage | +1.580 |
pta | +1.575 |
Neg logit contributions | |
hell | -1.507 |
ALEC | -1.501 |
dash | -1.497 |
undo | -1.492 |
FTWARE | -1.437 |
Token | # |
Token ID | 1303 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
dash | +1.878 |
hell | +1.876 |
undo | +1.865 |
ALEC | +1.821 |
boro | +1.794 |
Neg logit contributions | |
fins | -1.525 |
ities | -1.519 |
isite | -1.449 |
Advantage | -1.443 |
iaz | -1.413 |
Token | Snow |
Token ID | 28974 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
ities | +0.654 |
fins | +0.642 |
isite | +0.622 |
iaz | +0.615 |
pta | +0.614 |
Neg logit contributions | |
dash | -0.575 |
ALEC | -0.574 |
undo | -0.573 |
hell | -0.570 |
boro | -0.553 |
Token | ed |
Token ID | 276 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
hell | +6.333 |
dash | +6.333 |
undo | +6.164 |
boro | +5.999 |
ALEC | +5.887 |
Neg logit contributions | |
fins | -5.759 |
ities | -5.582 |
isite | -5.537 |
Advantage | -5.452 |
pta | -5.420 |
Token | Out |
Token ID | 7975 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
hell | +2.393 |
dash | +2.393 |
undo | +2.369 |
ALEC | +2.303 |
boro | +2.272 |
Neg logit contributions | |
fins | -2.321 |
ities | -2.304 |
isite | -2.221 |
Advantage | -2.205 |
iaz | -2.166 |
Token | Atlanta |
Token ID | 43482 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
dash | +2.795 |
hell | +2.795 |
undo | +2.773 |
ALEC | +2.707 |
boro | +2.673 |
Neg logit contributions | |
fins | -2.007 |
ities | -1.994 |
isite | -1.905 |
Advantage | -1.890 |
iaz | -1.850 |
Token | pic |
Token ID | 8301 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
dash | +1.565 |
hell | +1.561 |
undo | +1.556 |
ALEC | +1.517 |
boro | +1.497 |
Neg logit contributions | |
fins | -1.062 |
ities | -1.061 |
isite | -1.003 |
Advantage | -1.002 |
iaz | -0.977 |
Token | . |
Token ID | 13 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
dash | +0.776 |
hell | +0.775 |
undo | +0.760 |
ALEC | +0.734 |
boro | +0.715 |
Neg logit contributions | |
fins | -1.411 |
ities | -1.392 |
isite | -1.375 |
Advantage | -1.355 |
pta | -1.339 |
Token | people |
Token ID | 661 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
fins | +2.630 |
ities | +2.594 |
iaz | +2.393 |
Advantage | +2.388 |
ity | +2.383 |
Neg logit contributions | |
hell | -3.331 |
dash | -3.303 |
undo | -3.299 |
boro | -3.245 |
ALEC | -3.206 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
ities | +0.990 |
fins | +0.979 |
Advantage | +0.934 |
ity | +0.933 |
iaz | +0.927 |
Neg logit contributions | |
dash | -0.828 |
undo | -0.821 |
hell | -0.812 |
ALEC | -0.789 |
boro | -0.783 |
Token | Its |
Token ID | 6363 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
dash | +0.442 |
hell | +0.442 |
undo | +0.440 |
ALEC | +0.425 |
boro | +0.421 |
Neg logit contributions | |
fins | -0.411 |
ities | -0.409 |
Advantage | -0.394 |
isite | -0.392 |
iaz | -0.383 |
Token | exports |
Token ID | 15319 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
dash | +0.444 |
hell | +0.444 |
undo | +0.441 |
ALEC | +0.428 |
boro | +0.422 |
Neg logit contributions | |
fins | -0.423 |
ities | -0.420 |
isite | -0.403 |
Advantage | -0.402 |
iaz | -0.394 |
Token | to |
Token ID | 284 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
fins | +2.419 |
ities | +2.413 |
Advantage | +2.268 |
ity | +2.233 |
iaz | +2.226 |
Neg logit contributions | |
dash | -2.684 |
undo | -2.668 |
hell | -2.643 |
ALEC | -2.575 |
boro | -2.557 |
Token | Saudi |
Token ID | 7420 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
fins | +1.051 |
ities | +1.042 |
Advantage | +0.990 |
isite | +0.979 |
ity | +0.978 |
Neg logit contributions | |
dash | -1.260 |
undo | -1.257 |
hell | -1.237 |
boro | -1.210 |
ALEC | -1.184 |
Token | Arabia |
Token ID | 9671 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
fins | +1.902 |
ities | +1.842 |
iaz | +1.631 |
ity | +1.618 |
Advantage | +1.553 |
Neg logit contributions | |
undo | -7.809 |
dash | -7.678 |
hell | -7.643 |
boro | -7.494 |
ALEC | -7.490 |
Token | total |
Token ID | 2472 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
ities | +2.542 |
fins | +2.521 |
Advantage | +2.373 |
ity | +2.353 |
isite | +2.329 |
Neg logit contributions | |
dash | -2.917 |
undo | -2.906 |
hell | -2.885 |
ALEC | -2.802 |
boro | -2.765 |
Token | $ |
Token ID | 720 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
fins | +0.205 |
ities | +0.204 |
Advantage | +0.194 |
isite | +0.194 |
iaz | +0.190 |
Neg logit contributions | |
dash | -0.214 |
hell | -0.213 |
undo | -0.212 |
ALEC | -0.205 |
boro | -0.204 |
Token | 1 |
Token ID | 16 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
dash | +0.069 |
hell | +0.069 |
undo | +0.069 |
ALEC | +0.067 |
boro | +0.066 |
Neg logit contributions | |
ities | -0.065 |
fins | -0.065 |
isite | -0.062 |
Advantage | -0.062 |
iaz | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
undo | +1.076 |
dash | +1.074 |
hell | +1.070 |
ALEC | +1.026 |
boro | +1.005 |
Neg logit contributions | |
fins | -1.584 |
ities | -1.571 |
isite | -1.523 |
Advantage | -1.515 |
iaz | -1.501 |
Token | 2016 |
Token ID | 1584 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
ities | +1.958 |
fins | +1.946 |
Advantage | +1.890 |
isite | +1.848 |
ity | +1.821 |
Neg logit contributions | |
dash | -1.931 |
undo | -1.907 |
hell | -1.895 |
ALEC | -1.815 |
boro | -1.800 |
Token | ( |
Token ID | 357 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
dash | +1.842 |
hell | +1.840 |
undo | +1.819 |
ALEC | +1.755 |
boro | +1.723 |
Neg logit contributions | |
fins | -2.654 |
ities | -2.643 |
isite | -2.559 |
Advantage | -2.546 |
iaz | -2.507 |
Token | Photo |
Token ID | 6191 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ities | +1.090 |
fins | +1.062 |
Advantage | +1.036 |
isite | +1.033 |
pta | +1.016 |
Neg logit contributions | |
dash | -1.146 |
ALEC | -1.142 |
hell | -1.140 |
undo | -1.131 |
boro | -1.107 |
Token | : |
Token ID | 25 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
hell | +0.506 |
dash | +0.505 |
undo | +0.495 |
ALEC | +0.481 |
boro | +0.475 |
Neg logit contributions | |
fins | -0.832 |
ities | -0.822 |
isite | -0.812 |
Advantage | -0.792 |
iaz | -0.790 |
Token | Wayne |
Token ID | 13329 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
ities | +2.104 |
fins | +2.079 |
Advantage | +2.068 |
isite | +1.996 |
ity | +1.972 |
Neg logit contributions | |
dash | -1.787 |
hell | -1.766 |
undo | -1.744 |
boro | -1.680 |
acus | -1.662 |
Token | McG |
Token ID | 11130 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
hell | +1.789 |
dash | +1.786 |
undo | +1.765 |
ALEC | +1.725 |
boro | +1.699 |
Neg logit contributions | |
fins | -1.674 |
ities | -1.658 |
isite | -1.600 |
Advantage | -1.584 |
iaz | -1.562 |
Token | a |
Token ID | 64 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
ities | +5.082 |
ity | +4.789 |
isite | +4.784 |
iaz | +4.640 |
fins | +4.639 |
Neg logit contributions | |
dash | -4.999 |
ALEC | -4.996 |
FTWARE | -4.882 |
undo | -4.675 |
hell | -4.637 |
Token | hee |
Token ID | 21067 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
ities | +0.186 |
fins | +0.185 |
isite | +0.179 |
Advantage | +0.178 |
ity | +0.176 |
Neg logit contributions | |
dash | -0.114 |
undo | -0.112 |
hell | -0.112 |
ALEC | -0.110 |
boro | -0.106 |
Token | III |
Token ID | 6711 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
hell | +1.043 |
dash | +1.041 |
undo | +1.032 |
ALEC | +0.997 |
boro | +0.983 |
Neg logit contributions | |
ities | -1.316 |
fins | -1.314 |
Advantage | -1.269 |
isite | -1.268 |
iaz | -1.246 |
Token | / |
Token ID | 14 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ities | +0.164 |
fins | +0.164 |
Advantage | +0.160 |
isite | +0.157 |
iaz | +0.155 |
Neg logit contributions | |
hell | -0.145 |
dash | -0.144 |
undo | -0.143 |
ALEC | -0.139 |
boro | -0.137 |
Token | Dem |
Token ID | 11522 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
dash | +0.588 |
hell | +0.588 |
undo | +0.582 |
ALEC | +0.572 |
boro | +0.563 |
Neg logit contributions | |
ities | -0.539 |
fins | -0.538 |
isite | -0.516 |
Advantage | -0.515 |
iaz | -0.501 |
Token | for |
Token ID | 1640 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
fins | +0.706 |
ities | +0.703 |
isite | +0.679 |
Advantage | +0.675 |
iaz | +0.665 |
Neg logit contributions | |
dash | -0.561 |
hell | -0.561 |
undo | -0.555 |
ALEC | -0.538 |
boro | -0.528 |
Token | his |
Token ID | 465 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
ities | +0.577 |
fins | +0.576 |
Advantage | +0.559 |
isite | +0.549 |
pta | +0.541 |
Neg logit contributions | |
dash | -0.522 |
hell | -0.512 |
undo | -0.508 |
ALEC | -0.487 |
boro | -0.479 |
Token | fourth |
Token ID | 5544 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
fins | +0.126 |
ities | +0.125 |
Advantage | +0.120 |
isite | +0.119 |
ity | +0.117 |
Neg logit contributions | |
dash | -0.109 |
hell | -0.108 |
undo | -0.107 |
ALEC | -0.102 |
boro | -0.102 |
Token | ACC |
Token ID | 15859 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
fins | +1.159 |
ities | +1.156 |
Advantage | +1.116 |
isite | +1.102 |
ity | +1.081 |
Neg logit contributions | |
dash | -1.253 |
hell | -1.232 |
undo | -1.221 |
ALEC | -1.169 |
boro | -1.159 |
Token | Rookie |
Token ID | 36595 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
ities | +2.130 |
fins | +2.125 |
Advantage | +2.079 |
ity | +1.971 |
isite | +1.935 |
Neg logit contributions | |
dash | -3.279 |
hell | -3.233 |
undo | -3.193 |
FTWARE | -3.114 |
ALEC | -3.105 |
Token | of |
Token ID | 286 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
dash | +1.250 |
hell | +1.246 |
undo | +1.233 |
ALEC | +1.196 |
boro | +1.182 |
Neg logit contributions | |
fins | -1.157 |
ities | -1.157 |
Advantage | -1.111 |
isite | -1.110 |
iaz | -1.082 |
Token | the |
Token ID | 262 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ities | +4.915 |
fins | +4.773 |
Advantage | +4.744 |
ity | +4.681 |
isite | +4.554 |
Neg logit contributions | |
undo | -4.677 |
dash | -4.665 |
hell | -4.574 |
boro | -4.369 |
ALEC | -4.362 |
Token | Week |
Token ID | 6119 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
ities | +2.751 |
Advantage | +2.733 |
ity | +2.636 |
fins | +2.617 |
isite | +2.523 |
Neg logit contributions | |
dash | -4.794 |
hell | -4.773 |
undo | -4.750 |
FTWARE | -4.607 |
acus | -4.525 |
Token | Award |
Token ID | 11289 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
dash | +0.665 |
hell | +0.664 |
undo | +0.655 |
ALEC | +0.637 |
boro | +0.630 |
Neg logit contributions | |
fins | -0.632 |
ities | -0.628 |
isite | -0.603 |
Advantage | -0.601 |
iaz | -0.589 |
Token | and |
Token ID | 290 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
ities | +2.606 |
fins | +2.603 |
Advantage | +2.506 |
ity | +2.468 |
isite | +2.463 |
Neg logit contributions | |
dash | -2.997 |
hell | -2.948 |
undo | -2.899 |
ALEC | -2.800 |
boro | -2.799 |
Token | first |
Token ID | 717 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
fins | +0.652 |
ities | +0.648 |
Advantage | +0.627 |
isite | +0.612 |
ity | +0.609 |
Neg logit contributions | |
dash | -0.609 |
hell | -0.607 |
undo | -0.601 |
boro | -0.568 |
ALEC | -0.567 |
Token | a |
Token ID | 257 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
ities | +1.839 |
fins | +1.839 |
ity | +1.727 |
Advantage | +1.716 |
arily | +1.701 |
Neg logit contributions | |
dash | -1.568 |
undo | -1.559 |
hell | -1.556 |
ALEC | -1.508 |
boro | -1.496 |
Token | block |
Token ID | 2512 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
fins | +0.273 |
ities | +0.272 |
Advantage | +0.257 |
isite | +0.257 |
iaz | +0.252 |
Neg logit contributions | |
dash | -0.339 |
hell | -0.338 |
undo | -0.334 |
ALEC | -0.329 |
boro | -0.324 |
Token | be |
Token ID | 307 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
hell | +1.365 |
dash | +1.365 |
undo | +1.353 |
ALEC | +1.316 |
boro | +1.298 |
Neg logit contributions | |
fins | -1.277 |
ities | -1.270 |
isite | -1.222 |
Advantage | -1.213 |
iaz | -1.191 |
Token | a |
Token ID | 257 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
dash | +1.096 |
hell | +1.096 |
undo | +1.086 |
ALEC | +1.056 |
boro | +1.040 |
Neg logit contributions | |
fins | -1.116 |
ities | -1.109 |
isite | -1.067 |
Advantage | -1.062 |
iaz | -1.043 |
Token | first |
Token ID | 717 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
fins | +0.868 |
ities | +0.861 |
Advantage | +0.822 |
isite | +0.816 |
pta | +0.804 |
Neg logit contributions | |
hell | -0.971 |
dash | -0.959 |
undo | -0.953 |
ALEC | -0.934 |
boro | -0.928 |
Token | class |
Token ID | 1398 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
fins | +0.964 |
ities | +0.960 |
Advantage | +0.919 |
isite | +0.915 |
ity | +0.897 |
Neg logit contributions | |
hell | -1.213 |
dash | -1.209 |
undo | -1.208 |
ALEC | -1.175 |
boro | -1.158 |
Token | parameter |
Token ID | 11507 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
ities | +3.876 |
fins | +3.830 |
Advantage | +3.785 |
ity | +3.699 |
isite | +3.692 |
Neg logit contributions | |
dash | -5.222 |
hell | -5.179 |
undo | -5.147 |
boro | -5.025 |
FTWARE | -4.927 |
Token | and |
Token ID | 290 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
dash | +0.107 |
hell | +0.107 |
undo | +0.106 |
ALEC | +0.103 |
boro | +0.102 |
Neg logit contributions | |
ities | -0.109 |
fins | -0.108 |
isite | -0.104 |
Advantage | -0.103 |
iaz | -0.101 |
Token | can |
Token ID | 460 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
dash | +0.830 |
hell | +0.829 |
undo | +0.822 |
ALEC | +0.799 |
boro | +0.788 |
Neg logit contributions | |
fins | -0.829 |
ities | -0.823 |
isite | -0.790 |
Advantage | -0.787 |
iaz | -0.772 |
Token | you |
Token ID | 345 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
fins | +1.617 |
ities | +1.611 |
Advantage | +1.510 |
ity | +1.509 |
isite | +1.509 |
Neg logit contributions | |
dash | -1.426 |
undo | -1.420 |
hell | -1.413 |
ALEC | -1.373 |
boro | -1.355 |
Token | pass |
Token ID | 1208 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
fins | +2.566 |
ities | +2.531 |
ity | +2.344 |
Advantage | +2.329 |
pta | +2.329 |
Neg logit contributions | |
dash | -3.161 |
hell | -3.125 |
undo | -3.071 |
ALEC | -3.045 |
boro | -3.036 |
Token | / |
Token ID | 14 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
ities | +3.227 |
fins | +3.131 |
ity | +3.066 |
Advantage | +3.017 |
isite | +2.992 |
Neg logit contributions | |
undo | -2.147 |
dash | -2.100 |
hell | -2.082 |
ALEC | -2.037 |
acus | -1.972 |
Token | W |
Token ID | 54 |
Feature activation | +8.35e-01 |
Pos logit contributions | |
ities | +2.514 |
fins | +2.467 |
iaz | +2.397 |
pta | +2.386 |
isite | +2.381 |
Neg logit contributions | |
ALEC | -2.474 |
dash | -2.444 |
undo | -2.437 |
hell | -2.430 |
boro | -2.365 |
Token | 8 |
Token ID | 23 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ities | +2.481 |
fins | +2.425 |
iaz | +2.365 |
isite | +2.361 |
pta | +2.350 |
Neg logit contributions | |
ALEC | -2.315 |
dash | -2.286 |
hell | -2.279 |
undo | -2.278 |
boro | -2.200 |
Token | v |
Token ID | 85 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
ities | +3.289 |
fins | +3.212 |
iaz | +3.131 |
pta | +3.121 |
ity | +3.115 |
Neg logit contributions | |
ALEC | -3.079 |
dash | -3.043 |
undo | -3.023 |
hell | -3.002 |
boro | -2.920 |
Token | X |
Token ID | 55 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
ities | +2.800 |
fins | +2.740 |
iaz | +2.680 |
pta | +2.668 |
isite | +2.666 |
Neg logit contributions | |
ALEC | -2.723 |
dash | -2.692 |
undo | -2.680 |
hell | -2.666 |
boro | -2.582 |
Token | Ds |
Token ID | 30832 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
ities | +5.534 |
iaz | +5.346 |
fins | +5.337 |
pta | +5.309 |
ity | +5.305 |
Neg logit contributions | |
ALEC | -5.273 |
undo | -5.041 |
dash | -5.013 |
hell | -4.977 |
FTWARE | -4.896 |
Token | 4 |
Token ID | 19 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ities | +5.051 |
iaz | +4.911 |
fins | +4.871 |
pta | +4.825 |
ity | +4.823 |
Neg logit contributions | |
ALEC | -4.734 |
undo | -4.543 |
dash | -4.528 |
hell | -4.485 |
FTWARE | -4.394 |
Token | j |
Token ID | 73 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ities | +3.211 |
fins | +3.141 |
iaz | +3.062 |
pta | +3.055 |
ity | +3.045 |
Neg logit contributions | |
ALEC | -2.998 |
dash | -2.960 |
undo | -2.944 |
hell | -2.921 |
boro | -2.852 |
Token | 0 |
Token ID | 15 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ities | +3.699 |
fins | +3.612 |
iaz | +3.568 |
pta | +3.538 |
ity | +3.516 |
Neg logit contributions | |
ALEC | -3.578 |
undo | -3.481 |
dash | -3.477 |
hell | -3.468 |
boro | -3.361 |
Token | o |
Token ID | 78 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
ities | +3.057 |
fins | +3.001 |
iaz | +2.916 |
pta | +2.906 |
ity | +2.895 |
Neg logit contributions | |
ALEC | -2.939 |
dash | -2.920 |
undo | -2.900 |
hell | -2.884 |
boro | -2.812 |
Token | — |
Token ID | 851 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
ities | +2.259 |
fins | +2.256 |
Advantage | +2.171 |
iaz | +2.156 |
ity | +2.129 |
Neg logit contributions | |
dash | -3.053 |
undo | -3.019 |
hell | -2.981 |
ALEC | -2.953 |
boro | -2.913 |
Token | ( |
Token ID | 357 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
fins | +0.301 |
ities | +0.300 |
Advantage | +0.287 |
isite | +0.286 |
ity | +0.281 |
Neg logit contributions | |
dash | -0.279 |
hell | -0.277 |
undo | -0.277 |
boro | -0.266 |
ALEC | -0.265 |
Token | W |
Token ID | 54 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
dash | +0.484 |
hell | +0.480 |
undo | +0.479 |
ALEC | +0.470 |
boro | +0.460 |
Neg logit contributions | |
fins | -0.409 |
ities | -0.407 |
isite | -0.389 |
Advantage | -0.386 |
pta | -0.379 |
Token | CR |
Token ID | 9419 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
hell | +1.187 |
dash | +1.187 |
undo | +1.176 |
ALEC | +1.143 |
boro | +1.120 |
Neg logit contributions | |
fins | -1.518 |
ities | -1.511 |
isite | -1.462 |
Advantage | -1.447 |
pta | -1.433 |
Token | P |
Token ID | 47 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
dash | +1.576 |
hell | +1.575 |
undo | +1.561 |
ALEC | +1.512 |
boro | +1.494 |
Neg logit contributions | |
fins | -1.643 |
ities | -1.635 |
isite | -1.575 |
Advantage | -1.565 |
iaz | -1.541 |
Token | ), |
Token ID | 828 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
dash | +2.169 |
hell | +2.164 |
undo | +2.134 |
ALEC | +2.054 |
boro | +2.010 |
Neg logit contributions | |
fins | -3.726 |
ities | -3.705 |
isite | -3.594 |
Advantage | -3.576 |
iaz | -3.529 |
Token | European |
Token ID | 3427 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
dash | +1.249 |
hell | +1.247 |
undo | +1.238 |
ALEC | +1.200 |
boro | +1.185 |
Neg logit contributions | |
fins | -1.254 |
ities | -1.247 |
isite | -1.199 |
Advantage | -1.193 |
iaz | -1.171 |
Token | Commission |
Token ID | 4513 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
fins | +0.909 |
ities | +0.907 |
Advantage | +0.865 |
isite | +0.842 |
ity | +0.839 |
Neg logit contributions | |
dash | -1.118 |
undo | -1.118 |
hell | -1.104 |
ALEC | -1.070 |
boro | -1.062 |
Token | Joint |
Token ID | 16798 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
dash | +0.881 |
hell | +0.877 |
undo | +0.872 |
ALEC | +0.843 |
boro | +0.833 |
Neg logit contributions | |
fins | -0.990 |
ities | -0.986 |
isite | -0.947 |
Advantage | -0.944 |
iaz | -0.927 |
Token | Research |
Token ID | 4992 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
hell | +2.662 |
dash | +2.662 |
undo | +2.607 |
ALEC | +2.583 |
boro | +2.530 |
Neg logit contributions | |
fins | -2.230 |
ities | -2.182 |
isite | -2.121 |
pta | -2.105 |
Advantage | -2.095 |
Token | Centre |
Token ID | 9072 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
ities | +0.780 |
fins | +0.777 |
Advantage | +0.740 |
isite | +0.736 |
ity | +0.711 |
Neg logit contributions | |
dash | -1.119 |
undo | -1.118 |
hell | -1.113 |
ALEC | -1.077 |
boro | -1.067 |
Token | ( |
Token ID | 357 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
fins | +0.132 |
ities | +0.132 |
isite | +0.126 |
Advantage | +0.126 |
iaz | +0.123 |
Neg logit contributions | |
hell | -0.122 |
dash | -0.122 |
undo | -0.121 |
ALEC | -0.116 |
boro | -0.116 |
Token | Another |
Token ID | 6023 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
dash | +0.096 |
hell | +0.095 |
undo | +0.095 |
ALEC | +0.091 |
boro | +0.090 |
Neg logit contributions | |
fins | -0.120 |
ities | -0.120 |
Advantage | -0.116 |
isite | -0.115 |
pta | -0.113 |
Token | common |
Token ID | 2219 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
fins | +1.737 |
ities | +1.714 |
isite | +1.630 |
Advantage | +1.619 |
ity | +1.599 |
Neg logit contributions | |
dash | -2.171 |
hell | -2.139 |
undo | -2.119 |
ALEC | -2.064 |
boro | -2.041 |
Token | name |
Token ID | 1438 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ities | +1.429 |
fins | +1.402 |
isite | +1.321 |
ity | +1.317 |
Advantage | +1.295 |
Neg logit contributions | |
dash | -2.153 |
undo | -2.127 |
hell | -2.124 |
ALEC | -2.054 |
boro | -2.036 |
Token | suggested |
Token ID | 5220 |
Feature activation | +9.12e-02 |
Pos logit contributions | |
ities | +3.901 |
fins | +3.821 |
ity | +3.697 |
arily | +3.596 |
Advantage | +3.529 |
Neg logit contributions | |
dash | -4.408 |
hell | -4.320 |
undo | -4.320 |
ALEC | -4.163 |
FTWARE | -4.137 |
Token | for |
Token ID | 329 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
fins | +0.265 |
ities | +0.263 |
isite | +0.249 |
Advantage | +0.248 |
ity | +0.245 |
Neg logit contributions | |
dash | -0.271 |
undo | -0.268 |
hell | -0.266 |
ALEC | -0.258 |
boro | -0.254 |
Token | Pet |
Token ID | 4767 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
fins | +2.682 |
ities | +2.628 |
Advantage | +2.519 |
arily | +2.503 |
ity | +2.502 |
Neg logit contributions | |
dash | -2.747 |
hell | -2.676 |
undo | -2.649 |
ALEC | -2.566 |
boro | -2.520 |
Token | rog |
Token ID | 3828 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
fins | +1.337 |
ities | +1.336 |
isite | +1.298 |
Advantage | +1.292 |
iaz | +1.279 |
Neg logit contributions | |
dash | -0.511 |
hell | -0.506 |
undo | -0.499 |
ALEC | -0.479 |
boro | -0.458 |
Token | ale |
Token ID | 1000 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
ities | +2.236 |
fins | +2.228 |
isite | +2.158 |
Advantage | +2.140 |
iaz | +2.121 |
Neg logit contributions | |
dash | -1.605 |
hell | -1.595 |
undo | -1.582 |
ALEC | -1.536 |
boro | -1.501 |
Token | wil |
Token ID | 39716 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
fins | +1.735 |
ities | +1.700 |
isite | +1.607 |
ity | +1.592 |
Advantage | +1.591 |
Neg logit contributions | |
dash | -2.015 |
hell | -1.996 |
undo | -1.989 |
ALEC | -1.919 |
boro | -1.869 |
Token | kins |
Token ID | 5331 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ities | +5.173 |
fins | +5.131 |
isite | +4.883 |
ity | +4.883 |
pta | +4.875 |
Neg logit contributions | |
ALEC | -2.679 |
undo | -2.677 |
dash | -2.661 |
hell | -2.629 |
FTWARE | -2.433 |
Token | i |
Token ID | 72 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
ities | +2.842 |
fins | +2.834 |
ity | +2.650 |
iaz | +2.602 |
isite | +2.594 |
Neg logit contributions | |
undo | -4.881 |
dash | -4.873 |
hell | -4.805 |
ALEC | -4.789 |
FTWARE | -4.666 |
Token | Exception |
Token ID | 16922 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
ities | +0.457 |
fins | +0.449 |
isite | +0.438 |
Advantage | +0.435 |
ity | +0.428 |
Neg logit contributions | |
dash | -0.413 |
hell | -0.409 |
undo | -0.409 |
ALEC | -0.405 |
boro | -0.395 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
hell | +0.898 |
dash | +0.894 |
undo | +0.874 |
ALEC | +0.843 |
boro | +0.827 |
Neg logit contributions | |
fins | -1.663 |
ities | -1.626 |
isite | -1.591 |
Advantage | -1.576 |
pta | -1.565 |
Token | Message |
Token ID | 12837 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
ities | +0.039 |
fins | +0.038 |
isite | +0.037 |
Advantage | +0.037 |
ity | +0.036 |
Neg logit contributions | |
dash | -0.034 |
undo | -0.034 |
hell | -0.033 |
ALEC | -0.033 |
boro | -0.032 |
Token | )" |
Token ID | 16725 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
hell | +2.016 |
dash | +2.016 |
undo | +1.996 |
ALEC | +1.937 |
boro | +1.907 |
Neg logit contributions | |
fins | -2.255 |
ities | -2.243 |
isite | -2.164 |
Advantage | -2.150 |
iaz | -2.115 |
Token | break |
Token ID | 2270 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
fins | +0.669 |
ities | +0.666 |
isite | +0.650 |
Advantage | +0.639 |
iaz | +0.634 |
Neg logit contributions | |
hell | -0.567 |
dash | -0.565 |
undo | -0.563 |
ALEC | -0.546 |
boro | -0.535 |
Token | } |
Token ID | 1782 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
hell | +1.569 |
dash | +1.557 |
undo | +1.551 |
ALEC | +1.527 |
boro | +1.496 |
Neg logit contributions | |
fins | -1.077 |
ities | -1.069 |
isite | -1.047 |
iaz | -1.016 |
Advantage | -1.000 |
Token | } |
Token ID | 1782 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
fins | +0.788 |
ities | +0.774 |
Advantage | +0.735 |
isite | +0.714 |
pta | +0.696 |
Neg logit contributions | |
dash | -1.602 |
hell | -1.590 |
undo | -1.588 |
ALEC | -1.549 |
boro | -1.545 |
Token | End |
Token ID | 5268 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
fins | +1.418 |
ities | +1.386 |
Advantage | +1.337 |
isite | +1.274 |
pta | +1.257 |
Neg logit contributions | |
dash | -2.287 |
undo | -2.262 |
hell | -2.261 |
ALEC | -2.201 |
boro | -2.198 |
Token | { |
Token ID | 1391 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
fins | +1.055 |
ities | +1.054 |
Advantage | +1.011 |
isite | +1.005 |
iaz | +0.983 |
Neg logit contributions | |
dash | -1.164 |
undo | -1.155 |
hell | -1.145 |
ALEC | -1.124 |
boro | -1.099 |
Token | Try |
Token ID | 9993 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
fins | +0.661 |
ities | +0.653 |
Advantage | +0.629 |
isite | +0.619 |
iaz | +0.603 |
Neg logit contributions | |
dash | -0.853 |
hell | -0.846 |
undo | -0.844 |
ALEC | -0.821 |
boro | -0.818 |
Token | { |
Token ID | 1391 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
dash | +0.779 |
hell | +0.773 |
undo | +0.771 |
ALEC | +0.747 |
boro | +0.740 |
Neg logit contributions | |
fins | -0.712 |
ities | -0.712 |
Advantage | -0.681 |
isite | -0.680 |
iaz | -0.662 |
Token | s |
Token ID | 82 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
hell | +0.180 |
dash | +0.180 |
undo | +0.179 |
ALEC | +0.176 |
boro | +0.174 |
Neg logit contributions | |
ities | -0.114 |
fins | -0.114 |
isite | -0.107 |
Advantage | -0.106 |
ity | -0.104 |
Token | something |
Token ID | 1223 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
fins | +0.152 |
ities | +0.151 |
Advantage | +0.145 |
isite | +0.144 |
iaz | +0.142 |
Neg logit contributions | |
dash | -0.150 |
hell | -0.149 |
undo | -0.149 |
ALEC | -0.143 |
boro | -0.142 |
Token | you |
Token ID | 345 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
dash | +1.228 |
undo | +1.227 |
hell | +1.223 |
ALEC | +1.174 |
boro | +1.160 |
Neg logit contributions | |
fins | -1.421 |
ities | -1.420 |
Advantage | -1.358 |
isite | -1.352 |
iaz | -1.334 |
Token | don |
Token ID | 836 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
fins | +1.810 |
ities | +1.780 |
Advantage | +1.686 |
isite | +1.668 |
iaz | +1.661 |
Neg logit contributions | |
hell | -2.057 |
dash | -2.057 |
undo | -2.040 |
ALEC | -1.980 |
boro | -1.951 |
Token | � |
Token ID | 447 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ities | +2.608 |
fins | +2.527 |
ity | +2.405 |
Advantage | +2.351 |
iaz | +2.334 |
Neg logit contributions | |
undo | -4.513 |
hell | -4.498 |
dash | -4.478 |
ALEC | -4.400 |
boro | -4.323 |
Token | � |
Token ID | 247 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
fins | +0.401 |
ities | +0.399 |
isite | +0.383 |
Advantage | +0.381 |
iaz | +0.373 |
Neg logit contributions | |
hell | -0.449 |
dash | -0.449 |
undo | -0.445 |
ALEC | -0.434 |
boro | -0.427 |
Token | t |
Token ID | 83 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
fins | +0.827 |
ities | +0.826 |
isite | +0.792 |
Advantage | +0.788 |
ity | +0.782 |
Neg logit contributions | |
hell | -0.564 |
dash | -0.560 |
undo | -0.556 |
ALEC | -0.547 |
boro | -0.532 |
Token | want |
Token ID | 765 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
dash | +0.282 |
hell | +0.282 |
undo | +0.280 |
ALEC | +0.273 |
boro | +0.269 |
Neg logit contributions | |
fins | -0.228 |
ities | -0.226 |
isite | -0.216 |
Advantage | -0.215 |
iaz | -0.211 |
Token | to |
Token ID | 284 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
ities | +1.132 |
fins | +1.132 |
isite | +1.066 |
ity | +1.065 |
Advantage | +1.065 |
Neg logit contributions | |
hell | -1.014 |
undo | -1.009 |
dash | -1.005 |
ALEC | -0.976 |
boro | -0.963 |
Token | happen |
Token ID | 1645 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
dash | +0.483 |
hell | +0.483 |
undo | +0.478 |
ALEC | +0.466 |
boro | +0.459 |
Neg logit contributions | |
fins | -0.448 |
ities | -0.446 |
isite | -0.429 |
Advantage | -0.426 |
iaz | -0.418 |
Token | . |
Token ID | 13 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
dash | +0.345 |
undo | +0.343 |
hell | +0.343 |
ALEC | +0.332 |
boro | +0.324 |
Neg logit contributions | |
ities | -0.391 |
fins | -0.389 |
isite | -0.371 |
Advantage | -0.370 |
ity | -0.366 |
Token | Forum |
Token ID | 14867 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
fins | +0.732 |
ities | +0.722 |
Advantage | +0.688 |
isite | +0.686 |
iaz | +0.663 |
Neg logit contributions | |
hell | -1.276 |
dash | -1.272 |
undo | -1.267 |
ALEC | -1.233 |
boro | -1.220 |
Token | , |
Token ID | 11 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
fins | +1.948 |
ities | +1.938 |
Advantage | +1.836 |
isite | +1.821 |
ity | +1.797 |
Neg logit contributions | |
dash | -2.052 |
hell | -2.052 |
undo | -2.040 |
boro | -1.938 |
ALEC | -1.937 |
Token | which |
Token ID | 543 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
fins | +1.074 |
ities | +1.057 |
Advantage | +1.013 |
isite | +1.001 |
iaz | +0.985 |
Neg logit contributions | |
dash | -1.500 |
undo | -1.494 |
hell | -1.494 |
boro | -1.434 |
ALEC | -1.423 |
Token | will |
Token ID | 481 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
fins | +1.998 |
ities | +1.988 |
Advantage | +1.894 |
isite | +1.850 |
iaz | +1.849 |
Neg logit contributions | |
undo | -1.998 |
hell | -1.988 |
dash | -1.985 |
boro | -1.857 |
ALEC | -1.856 |
Token | meet |
Token ID | 1826 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
fins | +1.076 |
ities | +1.061 |
isite | +1.010 |
Advantage | +1.000 |
iaz | +0.996 |
Neg logit contributions | |
dash | -1.208 |
hell | -1.207 |
undo | -1.188 |
ALEC | -1.160 |
boro | -1.147 |
Token | on |
Token ID | 319 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
dash | +0.123 |
hell | +0.123 |
undo | +0.122 |
ALEC | +0.118 |
boro | +0.117 |
Neg logit contributions | |
fins | -0.127 |
ities | -0.127 |
isite | -0.122 |
Advantage | -0.121 |
iaz | -0.119 |
Token | a |
Token ID | 257 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
fins | +1.939 |
ities | +1.925 |
Advantage | +1.852 |
isite | +1.828 |
ity | +1.792 |
Neg logit contributions | |
undo | -2.187 |
dash | -2.175 |
hell | -2.172 |
ALEC | -2.072 |
acus | -2.050 |
Token | quarterly |
Token ID | 27868 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
fins | +0.559 |
ities | +0.558 |
isite | +0.539 |
Advantage | +0.534 |
iaz | +0.525 |
Neg logit contributions | |
dash | -0.498 |
hell | -0.497 |
undo | -0.493 |
ALEC | -0.477 |
boro | -0.469 |
Token | basis |
Token ID | 4308 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
ities | +0.239 |
fins | +0.239 |
isite | +0.222 |
Advantage | +0.222 |
ity | +0.218 |
Neg logit contributions | |
dash | -0.412 |
hell | -0.409 |
undo | -0.409 |
ALEC | -0.394 |
boro | -0.393 |
Token | from |
Token ID | 422 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
dash | +0.203 |
hell | +0.201 |
undo | +0.201 |
ALEC | +0.194 |
boro | +0.191 |
Neg logit contributions | |
fins | -0.221 |
ities | -0.220 |
isite | -0.211 |
Advantage | -0.210 |
iaz | -0.207 |
Token | September |
Token ID | 2693 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
hell | +1.899 |
dash | +1.886 |
undo | +1.872 |
ALEC | +1.845 |
boro | +1.802 |
Neg logit contributions | |
fins | -1.938 |
ities | -1.926 |
isite | -1.885 |
Advantage | -1.841 |
pta | -1.831 |
Token | first |
Token ID | 717 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
fins | +1.248 |
ities | +1.224 |
Advantage | +1.166 |
isite | +1.146 |
ity | +1.130 |
Neg logit contributions | |
hell | -1.461 |
dash | -1.456 |
undo | -1.443 |
ALEC | -1.401 |
boro | -1.378 |
Token | by |
Token ID | 416 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
ities | +2.720 |
fins | +2.687 |
ity | +2.548 |
Advantage | +2.539 |
arily | +2.538 |
Neg logit contributions | |
dash | -3.184 |
undo | -3.145 |
hell | -3.138 |
ALEC | -3.039 |
boro | -3.011 |
Token | a |
Token ID | 257 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
fins | +1.671 |
ities | +1.649 |
Advantage | +1.559 |
isite | +1.538 |
ity | +1.538 |
Neg logit contributions | |
dash | -1.702 |
hell | -1.685 |
undo | -1.680 |
boro | -1.623 |
ALEC | -1.619 |
Token | hydra |
Token ID | 25039 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
fins | +1.057 |
ities | +1.045 |
isite | +0.988 |
Advantage | +0.985 |
ity | +0.967 |
Neg logit contributions | |
dash | -1.342 |
hell | -1.341 |
undo | -1.327 |
ALEC | -1.294 |
boro | -1.284 |
Token | ul |
Token ID | 377 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
fins | +0.599 |
ities | +0.585 |
isite | +0.571 |
iaz | +0.563 |
Advantage | +0.561 |
Neg logit contributions | |
dash | -0.373 |
hell | -0.369 |
undo | -0.365 |
ALEC | -0.362 |
boro | -0.348 |
Token | ics |
Token ID | 873 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
ities | +0.621 |
fins | +0.620 |
isite | +0.586 |
Advantage | +0.573 |
ity | +0.572 |
Neg logit contributions | |
dash | -0.906 |
hell | -0.895 |
undo | -0.895 |
ALEC | -0.887 |
boro | -0.870 |
Token | issue |
Token ID | 2071 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
fins | +0.059 |
ities | +0.058 |
isite | +0.054 |
Advantage | +0.054 |
iaz | +0.052 |
Neg logit contributions | |
dash | -0.125 |
hell | -0.124 |
undo | -0.124 |
ALEC | -0.121 |
boro | -0.120 |
Token | with |
Token ID | 351 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
ities | +2.433 |
fins | +2.406 |
ity | +2.280 |
Advantage | +2.270 |
arily | +2.233 |
Neg logit contributions | |
dash | -2.684 |
undo | -2.644 |
hell | -2.622 |
ALEC | -2.585 |
boro | -2.544 |
Token | the |
Token ID | 262 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
fins | +1.928 |
ities | +1.852 |
Advantage | +1.775 |
isite | +1.771 |
ity | +1.742 |
Neg logit contributions | |
dash | -1.773 |
hell | -1.760 |
undo | -1.757 |
boro | -1.686 |
ALEC | -1.681 |
Token | rocket |
Token ID | 10701 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
fins | +1.791 |
ities | +1.737 |
Advantage | +1.663 |
isite | +1.652 |
iaz | +1.616 |
Neg logit contributions | |
dash | -1.980 |
hell | -1.962 |
undo | -1.949 |
ALEC | -1.904 |
boro | -1.886 |
Token | � |
Token ID | 447 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
fins | +0.905 |
ities | +0.888 |
isite | +0.847 |
Advantage | +0.846 |
iaz | +0.832 |
Neg logit contributions | |
dash | -0.877 |
undo | -0.873 |
hell | -0.872 |
ALEC | -0.845 |
boro | -0.834 |
Token | who |
Token ID | 508 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
fins | +0.111 |
ities | +0.109 |
Advantage | +0.105 |
isite | +0.103 |
iaz | +0.102 |
Neg logit contributions | |
dash | -0.122 |
hell | -0.122 |
undo | -0.122 |
ALEC | -0.117 |
boro | -0.116 |
Token | could |
Token ID | 714 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
dash | +0.787 |
hell | +0.784 |
undo | +0.782 |
ALEC | +0.755 |
boro | +0.744 |
Neg logit contributions | |
fins | -0.738 |
ities | -0.735 |
isite | -0.698 |
Advantage | -0.697 |
iaz | -0.684 |
Token | land |
Token ID | 1956 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
fins | +0.668 |
ities | +0.663 |
isite | +0.622 |
Advantage | +0.621 |
ity | +0.612 |
Neg logit contributions | |
dash | -0.814 |
hell | -0.813 |
undo | -0.801 |
ALEC | -0.787 |
boro | -0.775 |
Token | a |
Token ID | 257 |
Feature activation | +9.28e-02 |
Pos logit contributions | |
dash | +1.547 |
hell | +1.543 |
undo | +1.534 |
ALEC | +1.484 |
boro | +1.466 |
Neg logit contributions | |
fins | -1.672 |
ities | -1.662 |
isite | -1.597 |
Advantage | -1.592 |
iaz | -1.561 |
Token | Supporting |
Token ID | 44188 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
fins | +0.264 |
ities | +0.262 |
Advantage | +0.250 |
isite | +0.249 |
ity | +0.245 |
Neg logit contributions | |
dash | -0.278 |
hell | -0.275 |
undo | -0.274 |
ALEC | -0.265 |
boro | -0.264 |
Token | Actor |
Token ID | 27274 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
hell | +2.777 |
dash | +2.773 |
undo | +2.751 |
ALEC | +2.678 |
boro | +2.636 |
Neg logit contributions | |
fins | -2.831 |
ities | -2.814 |
isite | -2.713 |
Advantage | -2.681 |
pta | -2.645 |
Token | nomination |
Token ID | 11872 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
ities | +0.268 |
fins | +0.267 |
Advantage | +0.257 |
isite | +0.255 |
ity | +0.253 |
Neg logit contributions | |
dash | -0.284 |
hell | -0.281 |
undo | -0.277 |
ALEC | -0.270 |
boro | -0.267 |
Token | for |
Token ID | 329 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
ities | +1.228 |
fins | +1.224 |
Advantage | +1.167 |
ity | +1.154 |
isite | +1.153 |
Neg logit contributions | |
dash | -1.220 |
hell | -1.201 |
undo | -1.200 |
ALEC | -1.165 |
boro | -1.146 |
Token | Joe |
Token ID | 5689 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
fins | +1.070 |
ities | +1.058 |
Advantage | +1.034 |
isite | +1.005 |
ity | +1.000 |
Neg logit contributions | |
dash | -1.012 |
undo | -0.997 |
hell | -0.990 |
ALEC | -0.948 |
boro | -0.938 |
Token | Wright |
Token ID | 12206 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
dash | +1.082 |
hell | +1.078 |
undo | +1.069 |
ALEC | +1.040 |
boro | +1.024 |
Neg logit contributions | |
fins | -0.820 |
ities | -0.814 |
Advantage | -0.783 |
isite | -0.781 |
iaz | -0.760 |
Token | � |
Token ID | 447 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
fins | +0.406 |
ities | +0.400 |
Advantage | +0.390 |
isite | +0.383 |
iaz | +0.380 |
Neg logit contributions | |
dash | -0.387 |
undo | -0.384 |
hell | -0.384 |
ALEC | -0.374 |
boro | -0.362 |
Token | ading |
Token ID | 4980 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
ities | +0.105 |
fins | +0.103 |
isite | +0.099 |
iaz | +0.098 |
ity | +0.097 |
Neg logit contributions | |
hell | -0.113 |
dash | -0.112 |
undo | -0.112 |
ALEC | -0.111 |
boro | -0.107 |
Token | framework |
Token ID | 9355 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
fins | +1.846 |
ities | +1.801 |
Advantage | +1.727 |
ity | +1.672 |
isite | +1.659 |
Neg logit contributions | |
undo | -2.167 |
hell | -2.137 |
dash | -2.128 |
boro | -2.048 |
ALEC | -2.035 |
Token | needed |
Token ID | 2622 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
ities | +0.361 |
fins | +0.361 |
Advantage | +0.344 |
isite | +0.341 |
ity | +0.337 |
Neg logit contributions | |
dash | -0.326 |
undo | -0.323 |
hell | -0.322 |
boro | -0.309 |
ALEC | -0.306 |
Token | for |
Token ID | 329 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
dash | +1.150 |
hell | +1.149 |
undo | +1.141 |
ALEC | +1.097 |
boro | +1.086 |
Neg logit contributions | |
fins | -1.367 |
ities | -1.361 |
isite | -1.311 |
Advantage | -1.300 |
pta | -1.280 |
Token | the |
Token ID | 262 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
hell | +0.055 |
dash | +0.055 |
undo | +0.054 |
boro | +0.052 |
ALEC | +0.052 |
Neg logit contributions | |
fins | -0.056 |
ities | -0.056 |
Advantage | -0.053 |
isite | -0.053 |
ity | -0.052 |
Token | regional |
Token ID | 7915 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
fins | +0.813 |
ities | +0.803 |
Advantage | +0.769 |
isite | +0.762 |
iaz | +0.748 |
Neg logit contributions | |
undo | -0.878 |
hell | -0.878 |
dash | -0.878 |
boro | -0.840 |
ALEC | -0.835 |
Token | system |
Token ID | 1080 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
dash | +0.827 |
hell | +0.827 |
undo | +0.824 |
ALEC | +0.793 |
boro | +0.785 |
Neg logit contributions | |
fins | -0.890 |
ities | -0.889 |
Advantage | -0.847 |
isite | -0.846 |
iaz | -0.829 |
Token | to |
Token ID | 284 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
ities | +0.753 |
fins | +0.748 |
Advantage | +0.716 |
isite | +0.712 |
ity | +0.707 |
Neg logit contributions | |
dash | -0.650 |
undo | -0.647 |
hell | -0.644 |
ALEC | -0.618 |
boro | -0.618 |
Token | work |
Token ID | 670 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
fins | +0.076 |
ities | +0.075 |
isite | +0.071 |
Advantage | +0.071 |
iaz | +0.070 |
Neg logit contributions | |
dash | -0.088 |
hell | -0.088 |
undo | -0.087 |
ALEC | -0.085 |
boro | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
ities | +1.231 |
fins | +1.223 |
isite | +1.160 |
Advantage | +1.159 |
ity | +1.152 |
Neg logit contributions | |
dash | -1.084 |
undo | -1.082 |
hell | -1.064 |
ALEC | -1.026 |
boro | -1.022 |
Token |
|
Token ID | 198 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
dash | +0.561 |
hell | +0.561 |
undo | +0.558 |
ALEC | +0.534 |
boro | +0.532 |
Neg logit contributions | |
ities | -0.612 |
fins | -0.612 |
Advantage | -0.591 |
isite | -0.587 |
pta | -0.574 |
Token | 's |
Token ID | 338 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
fins | +0.425 |
ities | +0.424 |
Advantage | +0.402 |
isite | +0.400 |
arily | +0.393 |
Neg logit contributions | |
dash | -0.401 |
hell | -0.397 |
undo | -0.395 |
ALEC | -0.383 |
boro | -0.377 |
Token | war |
Token ID | 1175 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
dash | +1.040 |
hell | +1.040 |
undo | +1.030 |
ALEC | +1.002 |
boro | +0.987 |
Neg logit contributions | |
fins | -1.037 |
ities | -1.031 |
isite | -0.994 |
Advantage | -0.986 |
iaz | -0.970 |
Token | chest |
Token ID | 7721 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
dash | +1.084 |
undo | +1.081 |
hell | +1.071 |
ALEC | +1.039 |
boro | +0.999 |
Neg logit contributions | |
fins | -1.812 |
ities | -1.803 |
Advantage | -1.724 |
isite | -1.723 |
iaz | -1.698 |
Token | is |
Token ID | 318 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
fins | +1.939 |
ities | +1.929 |
Advantage | +1.817 |
ity | +1.786 |
isite | +1.776 |
Neg logit contributions | |
dash | -2.012 |
undo | -1.988 |
hell | -1.982 |
ALEC | -1.914 |
boro | -1.903 |
Token | significantly |
Token ID | 5566 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
fins | +0.637 |
ities | +0.630 |
Advantage | +0.604 |
isite | +0.600 |
iaz | +0.587 |
Neg logit contributions | |
dash | -0.687 |
hell | -0.674 |
undo | -0.673 |
ALEC | -0.649 |
boro | -0.643 |
Token | bigger |
Token ID | 5749 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
dash | +1.260 |
hell | +1.259 |
undo | +1.248 |
ALEC | +1.214 |
boro | +1.197 |
Neg logit contributions | |
fins | -1.184 |
ities | -1.177 |
isite | -1.131 |
Advantage | -1.124 |
iaz | -1.103 |
Token | now |
Token ID | 783 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
dash | +1.502 |
hell | +1.502 |
undo | +1.485 |
ALEC | +1.438 |
boro | +1.414 |
Neg logit contributions | |
fins | -1.957 |
ities | -1.948 |
isite | -1.879 |
Advantage | -1.872 |
iaz | -1.842 |
Token | . |
Token ID | 13 |
Feature activation | +9.90e-03 |
Pos logit contributions | |
ities | +0.998 |
fins | +0.989 |
Advantage | +0.951 |
arily | +0.937 |
isite | +0.934 |
Neg logit contributions | |
dash | -0.852 |
undo | -0.846 |
hell | -0.844 |
ALEC | -0.814 |
boro | -0.809 |
Token | Mozilla |
Token ID | 29258 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
fins | +0.032 |
ities | +0.032 |
Advantage | +0.031 |
isite | +0.030 |
pta | +0.030 |
Neg logit contributions | |
dash | -0.026 |
hell | -0.026 |
undo | -0.026 |
ALEC | -0.024 |
boro | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
hell | +2.076 |
dash | +2.073 |
undo | +2.053 |
ALEC | +2.002 |
boro | +1.962 |
Neg logit contributions | |
fins | -2.290 |
ities | -2.270 |
isite | -2.219 |
Advantage | -2.176 |
iaz | -2.163 |
Token | which |
Token ID | 543 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
dash | +0.973 |
hell | +0.972 |
undo | +0.964 |
ALEC | +0.939 |
boro | +0.927 |
Neg logit contributions | |
fins | -0.832 |
ities | -0.827 |
isite | -0.793 |
Advantage | -0.788 |
iaz | -0.773 |
Token | timed |
Token ID | 28805 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
dash | +1.314 |
hell | +1.312 |
undo | +1.304 |
ALEC | +1.270 |
boro | +1.255 |
Neg logit contributions | |
fins | -1.061 |
ities | -1.056 |
isite | -1.009 |
Advantage | -1.004 |
iaz | -0.983 |
Token | 45 |
Token ID | 4153 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
hell | +3.723 |
dash | +3.709 |
undo | +3.689 |
ALEC | +3.578 |
boro | +3.524 |
Neg logit contributions | |
fins | -3.112 |
ities | -3.063 |
isite | -2.959 |
Advantage | -2.927 |
pta | -2.888 |
Token | - |
Token ID | 12 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
hell | +1.051 |
dash | +1.050 |
undo | +1.041 |
ALEC | +1.018 |
boro | +1.005 |
Neg logit contributions | |
fins | -0.763 |
ities | -0.759 |
isite | -0.724 |
Advantage | -0.720 |
pta | -0.702 |
Token | minute |
Token ID | 11374 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
ities | +0.367 |
fins | +0.365 |
isite | +0.351 |
Advantage | +0.350 |
pta | +0.345 |
Neg logit contributions | |
hell | -0.331 |
dash | -0.330 |
undo | -0.328 |
ALEC | -0.326 |
boro | -0.316 |
Token | programming |
Token ID | 8300 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
dash | +0.984 |
hell | +0.982 |
undo | +0.974 |
ALEC | +0.948 |
boro | +0.937 |
Neg logit contributions | |
fins | -0.853 |
ities | -0.849 |
isite | -0.813 |
Advantage | -0.809 |
iaz | -0.792 |
Token | challenge |
Token ID | 4427 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
dash | +0.803 |
hell | +0.797 |
undo | +0.796 |
ALEC | +0.772 |
boro | +0.765 |
Neg logit contributions | |
fins | -0.671 |
ities | -0.668 |
isite | -0.636 |
Advantage | -0.635 |
iaz | -0.619 |
Token | on |
Token ID | 319 |
Feature activation | -6.25e-02 |
Pos logit contributions | |
dash | +1.732 |
hell | +1.728 |
undo | +1.717 |
ALEC | +1.660 |
boro | +1.632 |
Neg logit contributions | |
fins | -2.273 |
ities | -2.266 |
isite | -2.184 |
Advantage | -2.176 |
iaz | -2.141 |
Token | Interview |
Token ID | 19371 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
dash | +0.166 |
undo | +0.166 |
hell | +0.166 |
ALEC | +0.159 |
boro | +0.157 |
Neg logit contributions | |
fins | -0.197 |
ities | -0.196 |
Advantage | -0.189 |
isite | -0.189 |
iaz | -0.184 |
Token | Street |
Token ID | 34356 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
dash | +0.623 |
hell | +0.622 |
undo | +0.615 |
ALEC | +0.603 |
boro | +0.592 |
Neg logit contributions | |
ities | -0.547 |
fins | -0.547 |
isite | -0.525 |
Advantage | -0.524 |
pta | -0.509 |
Token | as |
Token ID | 355 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
hell | +1.340 |
dash | +1.339 |
undo | +1.333 |
ALEC | +1.290 |
boro | +1.266 |
Neg logit contributions | |
fins | -1.760 |
ities | -1.758 |
isite | -1.697 |
Advantage | -1.696 |
iaz | -1.662 |
Token | a |
Token ID | 257 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
dash | +1.970 |
hell | +1.965 |
undo | +1.952 |
ALEC | +1.893 |
boro | +1.863 |
Neg logit contributions | |
fins | -2.280 |
ities | -2.269 |
Advantage | -2.189 |
isite | -2.187 |
iaz | -2.143 |
Token | the |
Token ID | 262 |
Feature activation | -9.80e-02 |
Pos logit contributions | |
hell | +1.317 |
dash | +1.317 |
undo | +1.303 |
ALEC | +1.264 |
boro | +1.246 |
Neg logit contributions | |
fins | -1.494 |
ities | -1.488 |
isite | -1.433 |
Advantage | -1.429 |
iaz | -1.400 |
Token | same |
Token ID | 976 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
hell | +0.365 |
dash | +0.364 |
undo | +0.361 |
ALEC | +0.352 |
boro | +0.350 |
Neg logit contributions | |
fins | -0.206 |
ities | -0.205 |
Advantage | -0.194 |
isite | -0.194 |
iaz | -0.186 |
Token | thing |
Token ID | 1517 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
ities | +1.898 |
fins | +1.852 |
Advantage | +1.767 |
ity | +1.751 |
isite | +1.739 |
Neg logit contributions | |
hell | -2.438 |
dash | -2.407 |
undo | -2.376 |
boro | -2.315 |
ALEC | -2.287 |
Token | . |
Token ID | 13 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
ities | +0.553 |
fins | +0.549 |
Advantage | +0.530 |
isite | +0.528 |
ity | +0.520 |
Neg logit contributions | |
dash | -0.438 |
hell | -0.437 |
undo | -0.437 |
ALEC | -0.418 |
boro | -0.416 |
Token | The |
Token ID | 383 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
hell | +0.991 |
dash | +0.991 |
undo | +0.982 |
ALEC | +0.951 |
boro | +0.938 |
Neg logit contributions | |
fins | -1.076 |
ities | -1.072 |
isite | -1.033 |
Advantage | -1.030 |
iaz | -1.009 |
Token | news |
Token ID | 1705 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
fins | +0.265 |
ities | +0.263 |
Advantage | +0.251 |
isite | +0.251 |
iaz | +0.244 |
Neg logit contributions | |
hell | -0.325 |
dash | -0.325 |
undo | -0.323 |
ALEC | -0.313 |
boro | -0.311 |
Token | feed |
Token ID | 12363 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
hell | +5.145 |
dash | +5.108 |
undo | +5.067 |
ALEC | +4.939 |
boro | +4.892 |
Neg logit contributions | |
fins | -4.243 |
ities | -4.171 |
isite | -4.042 |
Advantage | -3.988 |
pta | -3.973 |
Token | , |
Token ID | 11 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
dash | +3.047 |
hell | +3.036 |
undo | +3.008 |
ALEC | +2.931 |
boro | +2.877 |
Neg logit contributions | |
fins | -2.975 |
ities | -2.942 |
isite | -2.858 |
Advantage | -2.811 |
pta | -2.796 |
Token | a |
Token ID | 257 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
dash | +1.168 |
hell | +1.167 |
undo | +1.156 |
ALEC | +1.126 |
boro | +1.108 |
Neg logit contributions | |
fins | -1.079 |
ities | -1.073 |
isite | -1.032 |
Advantage | -1.022 |
iaz | -1.007 |
Token | staple |
Token ID | 25629 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
fins | +0.109 |
ities | +0.108 |
isite | +0.104 |
Advantage | +0.103 |
ity | +0.101 |
Neg logit contributions | |
hell | -0.118 |
dash | -0.117 |
undo | -0.117 |
ALEC | -0.113 |
boro | -0.113 |
Token | of |
Token ID | 286 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
hell | +1.064 |
dash | +1.064 |
undo | +1.054 |
ALEC | +1.025 |
boro | +1.011 |
Neg logit contributions | |
fins | -1.034 |
ities | -1.028 |
isite | -0.989 |
Advantage | -0.983 |
iaz | -0.965 |
Token | factor |
Token ID | 5766 |
Feature activation | +6.89e-02 |
Pos logit contributions | |
fins | +0.691 |
ities | +0.678 |
isite | +0.621 |
Advantage | +0.620 |
ity | +0.620 |
Neg logit contributions | |
hell | -1.572 |
dash | -1.566 |
undo | -1.553 |
ALEC | -1.544 |
boro | -1.519 |
Token | " |
Token ID | 1 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
fins | +0.196 |
ities | +0.196 |
Advantage | +0.187 |
isite | +0.186 |
iaz | +0.183 |
Neg logit contributions | |
hell | -0.205 |
dash | -0.204 |
undo | -0.203 |
ALEC | -0.198 |
boro | -0.196 |
Token | number |
Token ID | 1271 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
fins | +0.381 |
ities | +0.380 |
Advantage | +0.363 |
isite | +0.361 |
iaz | +0.354 |
Neg logit contributions | |
hell | -0.444 |
dash | -0.443 |
undo | -0.438 |
ALEC | -0.428 |
boro | -0.424 |
Token | that |
Token ID | 326 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
hell | +1.012 |
dash | +1.011 |
undo | +1.004 |
ALEC | +0.973 |
boro | +0.957 |
Neg logit contributions | |
fins | -1.156 |
ities | -1.151 |
isite | -1.107 |
Advantage | -1.103 |
iaz | -1.084 |
Token | is |
Token ID | 318 |
Feature activation | -7.16e-02 |
Pos logit contributions | |
dash | +1.072 |
hell | +1.072 |
undo | +1.064 |
ALEC | +1.032 |
boro | +1.017 |
Neg logit contributions | |
fins | -1.057 |
ities | -1.051 |
Advantage | -1.004 |
isite | -1.004 |
iaz | -0.983 |
Token | greater |
Token ID | 3744 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
dash | +0.211 |
hell | +0.210 |
undo | +0.209 |
ALEC | +0.202 |
boro | +0.200 |
Neg logit contributions | |
fins | -0.206 |
ities | -0.205 |
Advantage | -0.197 |
isite | -0.195 |
iaz | -0.192 |
Token | than |
Token ID | 621 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
dash | +2.886 |
hell | +2.874 |
undo | +2.838 |
ALEC | +2.735 |
boro | +2.689 |
Neg logit contributions | |
fins | -3.973 |
ities | -3.938 |
isite | -3.847 |
Advantage | -3.792 |
pta | -3.770 |
Token | 0 |
Token ID | 657 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
hell | +1.994 |
dash | +1.993 |
undo | +1.977 |
ALEC | +1.924 |
boro | +1.897 |
Neg logit contributions | |
fins | -1.794 |
ities | -1.784 |
isite | -1.708 |
Advantage | -1.705 |
iaz | -1.667 |
Token | , |
Token ID | 11 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
dash | +1.920 |
hell | +1.919 |
undo | +1.898 |
ALEC | +1.836 |
boro | +1.804 |
Neg logit contributions | |
fins | -2.607 |
ities | -2.594 |
isite | -2.510 |
Advantage | -2.496 |
iaz | -2.458 |
Token | and |
Token ID | 290 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
fins | +0.636 |
ities | +0.632 |
Advantage | +0.608 |
isite | +0.596 |
iaz | +0.588 |
Neg logit contributions | |
dash | -0.731 |
hell | -0.730 |
undo | -0.728 |
ALEC | -0.710 |
boro | -0.692 |
Token | then |
Token ID | 788 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
fins | +2.240 |
ities | +2.231 |
Advantage | +2.149 |
ity | +2.055 |
isite | +2.051 |
Neg logit contributions | |
dash | -2.468 |
undo | -2.451 |
hell | -2.449 |
ALEC | -2.375 |
boro | -2.346 |
Token | was |
Token ID | 373 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
fins | +0.851 |
ities | +0.848 |
Advantage | +0.803 |
isite | +0.794 |
ity | +0.789 |
Neg logit contributions | |
hell | -0.855 |
dash | -0.854 |
undo | -0.854 |
ALEC | -0.818 |
boro | -0.804 |
Token | once |
Token ID | 1752 |
Feature activation | +9.48e-01 |
Pos logit contributions | |
fins | +0.371 |
ities | +0.366 |
Advantage | +0.349 |
arily | +0.346 |
ity | +0.345 |
Neg logit contributions | |
dash | -0.374 |
undo | -0.369 |
hell | -0.368 |
ALEC | -0.354 |
boro | -0.352 |
Token | seemed |
Token ID | 3947 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
fins | +2.746 |
ities | +2.703 |
Advantage | +2.602 |
ity | +2.586 |
arily | +2.578 |
Neg logit contributions | |
dash | -2.728 |
hell | -2.689 |
undo | -2.678 |
acus | -2.586 |
boro | -2.568 |
Token | like |
Token ID | 588 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
ities | +2.664 |
fins | +2.647 |
isite | +2.517 |
ity | +2.508 |
arily | +2.505 |
Neg logit contributions | |
dash | -2.769 |
undo | -2.737 |
hell | -2.697 |
ALEC | -2.661 |
FTWARE | -2.650 |
Token | a |
Token ID | 257 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
fins | +0.678 |
ities | +0.668 |
Advantage | +0.644 |
isite | +0.635 |
ity | +0.634 |
Neg logit contributions | |
undo | -0.627 |
hell | -0.621 |
dash | -0.616 |
ALEC | -0.600 |
FTWARE | -0.592 |
Token | summer |
Token ID | 3931 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
dash | +0.044 |
hell | +0.044 |
undo | +0.044 |
ALEC | +0.042 |
boro | +0.042 |
Neg logit contributions | |
fins | -0.043 |
ities | -0.042 |
isite | -0.040 |
Advantage | -0.040 |
ity | -0.040 |
Token | memory |
Token ID | 4088 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
dash | +3.303 |
hell | +3.301 |
undo | +3.267 |
ALEC | +3.176 |
boro | +3.136 |
Neg logit contributions | |
fins | -3.394 |
ities | -3.375 |
isite | -3.256 |
Advantage | -3.232 |
pta | -3.179 |
Token | from |
Token ID | 422 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
fins | +0.430 |
ities | +0.427 |
Advantage | +0.411 |
isite | +0.409 |
arily | +0.405 |
Neg logit contributions | |
dash | -0.343 |
hell | -0.341 |
undo | -0.341 |
ALEC | -0.328 |
boro | -0.321 |
Token | the |
Token ID | 262 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
dash | +1.238 |
hell | +1.236 |
undo | +1.225 |
ALEC | +1.189 |
boro | +1.170 |
Neg logit contributions | |
fins | -1.349 |
ities | -1.342 |
isite | -1.290 |
Advantage | -1.287 |
iaz | -1.261 |
Token | ancient |
Token ID | 6156 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
fins | +0.410 |
ities | +0.408 |
Advantage | +0.388 |
isite | +0.386 |
iaz | +0.378 |
Neg logit contributions | |
dash | -0.464 |
hell | -0.461 |
undo | -0.457 |
ALEC | -0.446 |
boro | -0.441 |
Token | past |
Token ID | 1613 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
ities | +1.735 |
fins | +1.685 |
ity | +1.582 |
Advantage | +1.580 |
isite | +1.537 |
Neg logit contributions | |
dash | -2.183 |
undo | -2.155 |
hell | -2.142 |
ALEC | -2.082 |
boro | -2.049 |
Token | ] |
Token ID | 60 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
hell | +1.316 |
dash | +1.316 |
undo | +1.304 |
ALEC | +1.264 |
boro | +1.236 |
Neg logit contributions | |
fins | -1.914 |
ities | -1.912 |
isite | -1.848 |
Advantage | -1.837 |
iaz | -1.809 |
Token | optional |
Token ID | 11902 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
ities | +0.835 |
fins | +0.831 |
Advantage | +0.797 |
isite | +0.790 |
pta | +0.782 |
Neg logit contributions | |
hell | -0.812 |
dash | -0.811 |
ALEC | -0.805 |
undo | -0.802 |
boro | -0.780 |
Token | white |
Token ID | 2330 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
dash | +3.850 |
undo | +3.818 |
hell | +3.812 |
ALEC | +3.655 |
boro | +3.613 |
Neg logit contributions | |
fins | -3.419 |
ities | -3.352 |
isite | -3.286 |
iaz | -3.230 |
Advantage | -3.217 |
Token | space |
Token ID | 2272 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
ities | +0.237 |
fins | +0.235 |
Advantage | +0.225 |
isite | +0.224 |
ity | +0.220 |
Neg logit contributions | |
hell | -0.272 |
dash | -0.270 |
undo | -0.267 |
ALEC | -0.266 |
boro | -0.261 |
Token | { |
Token ID | 1391 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
hell | +0.998 |
dash | +0.995 |
undo | +0.987 |
ALEC | +0.964 |
boro | +0.950 |
Neg logit contributions | |
fins | -0.954 |
ities | -0.951 |
Advantage | -0.910 |
isite | -0.909 |
iaz | -0.885 |
Token | options |
Token ID | 25811 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
hell | +0.899 |
dash | +0.896 |
undo | +0.885 |
ALEC | +0.883 |
boro | +0.863 |
Neg logit contributions | |
fins | -0.739 |
ities | -0.737 |
isite | -0.705 |
Advantage | -0.702 |
pta | -0.691 |
Token | } |
Token ID | 92 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
hell | +2.794 |
dash | +2.792 |
undo | +2.763 |
ALEC | +2.653 |
boro | +2.613 |
Neg logit contributions | |
fins | -3.933 |
ities | -3.907 |
isite | -3.787 |
Advantage | -3.768 |
iaz | -3.720 |
Token | a |
Token ID | 257 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
dash | +0.363 |
hell | +0.363 |
undo | +0.360 |
ALEC | +0.352 |
boro | +0.347 |
Neg logit contributions | |
fins | -0.344 |
ities | -0.342 |
Advantage | -0.328 |
isite | -0.328 |
pta | -0.320 |
Token | list |
Token ID | 1351 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
hell | +1.321 |
dash | +1.316 |
undo | +1.303 |
ALEC | +1.285 |
boro | +1.260 |
Neg logit contributions | |
fins | -1.141 |
ities | -1.141 |
isite | -1.089 |
Advantage | -1.083 |
pta | -1.065 |
Token | of |
Token ID | 286 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
dash | +3.198 |
hell | +3.192 |
undo | +3.175 |
ALEC | +3.071 |
boro | +3.026 |
Neg logit contributions | |
fins | -3.309 |
ities | -3.283 |
isite | -3.168 |
Advantage | -3.145 |
iaz | -3.093 |
Token | option |
Token ID | 3038 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
hell | +0.498 |
dash | +0.495 |
undo | +0.490 |
ALEC | +0.481 |
boro | +0.475 |
Neg logit contributions | |
fins | -0.446 |
ities | -0.444 |
Advantage | -0.422 |
isite | -0.421 |
pta | -0.412 |
Token | F |
Token ID | 376 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
fins | +0.393 |
ities | +0.393 |
Advantage | +0.373 |
isite | +0.370 |
ity | +0.365 |
Neg logit contributions | |
dash | -0.488 |
undo | -0.488 |
hell | -0.485 |
ALEC | -0.469 |
boro | -0.464 |
Token | - |
Token ID | 12 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
dash | +0.494 |
hell | +0.494 |
undo | +0.488 |
ALEC | +0.474 |
boro | +0.468 |
Neg logit contributions | |
fins | -0.498 |
ities | -0.493 |
isite | -0.477 |
Advantage | -0.474 |
pta | -0.465 |
Token | 150 |
Token ID | 8628 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
ities | +0.830 |
fins | +0.813 |
Advantage | +0.774 |
isite | +0.768 |
ity | +0.760 |
Neg logit contributions | |
hell | -1.058 |
undo | -1.054 |
dash | -1.042 |
ALEC | -1.041 |
boro | -1.005 |
Token | Eco |
Token ID | 38719 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
fins | +1.246 |
ities | +1.240 |
Advantage | +1.192 |
isite | +1.166 |
ity | +1.157 |
Neg logit contributions | |
undo | -1.339 |
dash | -1.329 |
hell | -1.319 |
ALEC | -1.287 |
boro | -1.258 |
Token | Boost |
Token ID | 45686 |
Feature activation | +9.47e-02 |
Pos logit contributions | |
hell | +2.133 |
dash | +2.131 |
undo | +2.111 |
ALEC | +2.043 |
boro | +2.002 |
Neg logit contributions | |
fins | -2.970 |
ities | -2.953 |
isite | -2.858 |
Advantage | -2.848 |
iaz | -2.801 |
Token | Tort |
Token ID | 28467 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
fins | +0.273 |
ities | +0.272 |
Advantage | +0.262 |
isite | +0.259 |
iaz | +0.256 |
Neg logit contributions | |
dash | -0.277 |
undo | -0.277 |
hell | -0.276 |
ALEC | -0.268 |
boro | -0.263 |
Token | ure |
Token ID | 495 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
hell | +4.452 |
dash | +4.450 |
undo | +4.412 |
ALEC | +4.299 |
boro | +4.242 |
Neg logit contributions | |
fins | -3.711 |
ities | -3.689 |
isite | -3.538 |
Advantage | -3.512 |
iaz | -3.444 |
Token | Test |
Token ID | 6208 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
fins | +0.303 |
ities | +0.296 |
Advantage | +0.291 |
isite | +0.284 |
iaz | +0.279 |
Neg logit contributions | |
undo | -0.310 |
dash | -0.308 |
hell | -0.304 |
ALEC | -0.301 |
FTWARE | -0.294 |
Token | truck |
Token ID | 7779 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
ities | +2.034 |
fins | +2.025 |
Advantage | +1.967 |
isite | +1.918 |
iaz | +1.902 |
Neg logit contributions | |
undo | -2.109 |
dash | -2.090 |
hell | -2.089 |
ALEC | -2.059 |
boro | -1.992 |
Token | in |
Token ID | 287 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
undo | +0.106 |
dash | +0.105 |
hell | +0.105 |
ALEC | +0.102 |
boro | +0.100 |
Neg logit contributions | |
fins | -0.107 |
ities | -0.106 |
Advantage | -0.101 |
isite | -0.101 |
iaz | -0.099 |
Token | the |
Token ID | 262 |
Feature activation | +9.45e-02 |
Pos logit contributions | |
fins | +1.068 |
ities | +1.054 |
Advantage | +1.009 |
isite | +0.998 |
ity | +0.985 |
Neg logit contributions | |
hell | -1.083 |
undo | -1.080 |
dash | -1.078 |
ALEC | -1.028 |
boro | -1.027 |