Token | x |
Token ID | 2124 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
ellar | +4.231 |
yrinth | +4.020 |
Priv | +3.615 |
Balloon | +3.382 |
drag | +3.337 |
Neg logit contributions | |
�士 | -9.794 |
UCS | -9.631 |
UTF | -9.505 |
osph | -9.421 |
py | -9.004 |
Token | . |
Token ID | 13 |
Feature activation | +9.20e+00 |
Pos logit contributions | |
ellar | +3.364 |
yrinth | +3.140 |
Priv | +2.815 |
--------- | +2.776 |
[_ | +2.753 |
Neg logit contributions | |
�士 | -4.161 |
UCS | -3.970 |
UTF | -3.806 |
osph | -3.722 |
py | -3.540 |
Token | x |
Token ID | 87 |
Feature activation | +8.69e+00 |
Pos logit contributions | |
ellar | +4.477 |
yrinth | +3.990 |
[_ | +3.494 |
--------- | +3.436 |
BW | +3.392 |
Neg logit contributions | |
�士 | -9.148 |
UCS | -8.450 |
UTF | -8.039 |
osph | -7.846 |
senal | -7.506 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
ellar | +4.993 |
yrinth | +4.405 |
Priv | +4.182 |
--------- | +4.173 |
[_ | +4.165 |
Neg logit contributions | |
�士 | -7.837 |
UCS | -7.014 |
UTF | -6.767 |
osph | -6.700 |
senal | -6.549 |
Token | x |
Token ID | 87 |
Feature activation | +1.25e+01 |
Pos logit contributions | |
ellar | +5.294 |
yrinth | +4.684 |
[_ | +4.256 |
night | +4.029 |
--------- | +4.016 |
Neg logit contributions | |
�士 | -12.218 |
UCS | -11.223 |
UTF | -10.627 |
osph | -10.417 |
senal | -10.271 |
Token | . |
Token ID | 13 |
Feature activation | +1.57e+01 |
Pos logit contributions | |
ellar | +6.489 |
[_ | +5.700 |
yrinth | +5.609 |
--------- | +5.509 |
Priv | +5.370 |
Neg logit contributions | |
�士 | -11.585 |
UCS | -10.342 |
senal | -10.001 |
UTF | -9.915 |
osph | -9.872 |
Token | 83 |
Token ID | 5999 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ellar | +5.433 |
yrinth | +5.214 |
[_ | +4.046 |
--------- | +3.705 |
LG | +3.612 |
Neg logit contributions | |
UCS | -15.696 |
�士 | -14.879 |
UTF | -14.670 |
osph | -14.345 |
pu | -13.578 |
Token | 10 |
Token ID | 838 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ellar | +1.057 |
yrinth | +1.042 |
Priv | +0.898 |
Balloon | +0.877 |
--------- | +0.871 |
Neg logit contributions | |
UCS | -1.107 |
�士 | -1.079 |
UTF | -1.066 |
osph | -1.027 |
py | -0.999 |
Token | 92 |
Token ID | 5892 |
Feature activation | +9.93e+00 |
Pos logit contributions | |
ellar | +0.854 |
yrinth | +0.826 |
Priv | +0.722 |
Balloon | +0.709 |
--------- | +0.707 |
Neg logit contributions | |
UCS | -0.769 |
�士 | -0.746 |
UTF | -0.733 |
osph | -0.709 |
py | -0.681 |
Token | 135 |
Token ID | 17059 |
Feature activation | +9.04e+00 |
Pos logit contributions | |
ellar | +6.114 |
yrinth | +5.620 |
Priv | +5.085 |
--------- | +5.041 |
Balloon | +4.951 |
Neg logit contributions | |
UCS | -7.658 |
�士 | -7.581 |
osph | -7.177 |
UTF | -7.125 |
amera | -6.697 |
Token | x |
Token ID | 2124 |
Feature activation | +5.26e+00 |
Pos logit contributions | |
ellar | +3.964 |
yrinth | +3.620 |
Priv | +3.414 |
Balloon | +3.249 |
drag | +3.172 |
Neg logit contributions | |
�士 | -8.907 |
UCS | -8.280 |
UTF | -8.216 |
osph | -8.025 |
py | -7.665 |
Token | x |
Token ID | 2124 |
Feature activation | +5.01e+00 |
Pos logit contributions | |
ellar | +3.405 |
yrinth | +3.248 |
Priv | +2.841 |
Balloon | +2.693 |
drag | +2.645 |
Neg logit contributions | |
�士 | -6.833 |
UCS | -6.736 |
UTF | -6.665 |
osph | -6.497 |
py | -6.313 |
Token | . |
Token ID | 13 |
Feature activation | +9.05e+00 |
Pos logit contributions | |
ellar | +3.280 |
yrinth | +3.063 |
Priv | +2.738 |
--------- | +2.708 |
[_ | +2.679 |
Neg logit contributions | |
�士 | -4.040 |
UCS | -3.862 |
UTF | -3.701 |
osph | -3.619 |
py | -3.431 |
Token | x |
Token ID | 87 |
Feature activation | +9.46e+00 |
Pos logit contributions | |
ellar | +4.402 |
yrinth | +3.917 |
[_ | +3.427 |
--------- | +3.375 |
BW | +3.317 |
Neg logit contributions | |
�士 | -9.027 |
UCS | -8.329 |
UTF | -7.930 |
osph | -7.742 |
senal | -7.404 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
ellar | +5.264 |
yrinth | +4.554 |
[_ | +4.427 |
--------- | +4.417 |
Priv | +4.387 |
Neg logit contributions | |
�士 | -8.727 |
UCS | -7.706 |
UTF | -7.439 |
senal | -7.409 |
osph | -7.398 |
Token | x |
Token ID | 87 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
ellar | +4.754 |
yrinth | +4.199 |
[_ | +3.715 |
--------- | +3.598 |
night | +3.583 |
Neg logit contributions | |
�士 | -10.356 |
UCS | -9.517 |
UTF | -9.055 |
osph | -8.835 |
senal | -8.601 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
ellar | +6.885 |
[_ | +6.174 |
--------- | +5.865 |
yrinth | +5.678 |
Priv | +5.652 |
Neg logit contributions | |
�士 | -13.332 |
UCS | -11.891 |
senal | -11.712 |
UTF | -11.320 |
osph | -11.317 |
Token | 82 |
Token ID | 6469 |
Feature activation | +6.24e+00 |
Pos logit contributions | |
ellar | +6.453 |
yrinth | +6.009 |
[_ | +5.060 |
ever | +4.651 |
Balloon | +4.642 |
Neg logit contributions | |
UCS | -13.809 |
UTF | -13.085 |
�士 | -12.661 |
osph | -12.321 |
� | -11.610 |
Token | 11 |
Token ID | 1367 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
ellar | +3.998 |
yrinth | +3.972 |
Priv | +3.509 |
--------- | +3.388 |
Balloon | +3.384 |
Neg logit contributions | |
�士 | -4.772 |
UCS | -4.684 |
UTF | -4.593 |
osph | -4.532 |
py | -4.282 |
Token | 66 |
Token ID | 2791 |
Feature activation | +8.50e+00 |
Pos logit contributions | |
ellar | +1.875 |
yrinth | +1.794 |
Priv | +1.592 |
--------- | +1.572 |
Balloon | +1.568 |
Neg logit contributions | |
UCS | -1.734 |
�士 | -1.698 |
UTF | -1.657 |
osph | -1.624 |
py | -1.546 |
Token | 756 |
Token ID | 38219 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
ellar | +5.695 |
yrinth | +5.270 |
--------- | +4.933 |
Priv | +4.764 |
BW | +4.760 |
Neg logit contributions | |
UCS | -6.110 |
�士 | -6.002 |
UTF | -5.751 |
osph | -5.727 |
py | -5.305 |
Token | x |
Token ID | 2124 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
ellar | +4.231 |
yrinth | +4.020 |
Priv | +3.615 |
Balloon | +3.382 |
drag | +3.337 |
Neg logit contributions | |
�士 | -9.794 |
UCS | -9.631 |
UTF | -9.505 |
osph | -9.421 |
py | -9.004 |
Token | direction |
Token ID | 4571 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
UCS | +2.337 |
UTF | +2.238 |
�士 | +2.218 |
osph | +2.125 |
py | +2.115 |
Neg logit contributions | |
ellar | -1.995 |
yrinth | -1.958 |
Priv | -1.637 |
Klux | -1.614 |
Balloon | -1.600 |
Token | to |
Token ID | 284 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
UCS | +0.044 |
�士 | +0.042 |
UTF | +0.042 |
osph | +0.040 |
py | +0.039 |
Neg logit contributions | |
ellar | -0.041 |
yrinth | -0.041 |
Priv | -0.034 |
Balloon | -0.034 |
Klux | -0.034 |
Token | reach |
Token ID | 3151 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
ellar | +1.767 |
yrinth | +1.735 |
Priv | +1.480 |
Balloon | +1.466 |
drag | +1.463 |
Neg logit contributions | |
UCS | -1.855 |
�士 | -1.819 |
UTF | -1.817 |
osph | -1.701 |
py | -1.666 |
Token | a |
Token ID | 257 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ellar | +2.006 |
yrinth | +1.969 |
Balloon | +1.625 |
Priv | +1.618 |
drag | +1.588 |
Neg logit contributions | |
UCS | -2.680 |
�士 | -2.650 |
UTF | -2.635 |
osph | -2.489 |
py | -2.438 |
Token | water |
Token ID | 1660 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
ellar | +1.057 |
yrinth | +1.044 |
Priv | +0.874 |
Balloon | +0.872 |
drag | +0.860 |
Neg logit contributions | |
UCS | -1.212 |
�士 | -1.192 |
UTF | -1.186 |
osph | -1.119 |
py | -1.101 |
Token | sy |
Token ID | 827 |
Feature activation | +1.46e+01 |
Pos logit contributions | |
ellar | +2.682 |
yrinth | +2.648 |
Balloon | +2.229 |
drag | +2.224 |
Priv | +2.192 |
Neg logit contributions | |
UCS | -3.088 |
�士 | -3.059 |
UTF | -3.030 |
osph | -2.823 |
py | -2.769 |
Token | ringe |
Token ID | 38229 |
Feature activation | +5.40e+00 |
Pos logit contributions | |
ellar | +5.801 |
yrinth | +5.336 |
apor | +3.774 |
sted | +3.764 |
Balloon | +3.687 |
Neg logit contributions | |
�士 | -14.789 |
UTF | -14.379 |
UCS | -14.350 |
� | -12.984 |
osph | -12.481 |
Token | held |
Token ID | 2714 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
ellar | +3.462 |
yrinth | +3.378 |
drag | +2.892 |
Balloon | +2.883 |
Priv | +2.865 |
Neg logit contributions | |
�士 | -4.299 |
UCS | -4.190 |
UTF | -4.155 |
osph | -3.883 |
pu | -3.733 |
Token | by |
Token ID | 416 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
ellar | +1.185 |
yrinth | +1.164 |
Priv | +0.981 |
Balloon | +0.975 |
drag | +0.954 |
Neg logit contributions | |
UCS | -1.476 |
�士 | -1.453 |
UTF | -1.428 |
osph | -1.365 |
py | -1.327 |
Token | an |
Token ID | 281 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
UCS | +0.406 |
�士 | +0.395 |
UTF | +0.395 |
osph | +0.377 |
py | +0.368 |
Neg logit contributions | |
ellar | -0.338 |
yrinth | -0.331 |
Priv | -0.278 |
Balloon | -0.275 |
drag | -0.269 |
Token | experiment |
Token ID | 6306 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
ellar | +1.601 |
yrinth | +1.554 |
Balloon | +1.316 |
Priv | +1.312 |
drag | +1.297 |
Neg logit contributions | |
UCS | -1.775 |
�士 | -1.754 |
UTF | -1.726 |
osph | -1.660 |
py | -1.631 |
Token |
|
Token ID | 198 |
Feature activation | +7.50e-02 |
Pos logit contributions | |
UCS | +0.617 |
UTF | +0.596 |
�士 | +0.595 |
osph | +0.568 |
py | +0.557 |
Neg logit contributions | |
ellar | -0.534 |
yrinth | -0.525 |
Priv | -0.443 |
Balloon | -0.434 |
Klux | -0.428 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ellar | +0.053 |
yrinth | +0.052 |
Priv | +0.043 |
Klux | +0.043 |
Balloon | +0.043 |
Neg logit contributions | |
UCS | -0.057 |
UTF | -0.054 |
�士 | -0.053 |
osph | -0.051 |
py | -0.051 |
Token | The |
Token ID | 464 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
UCS | +0.103 |
�士 | +0.099 |
UTF | +0.098 |
osph | +0.094 |
py | +0.092 |
Neg logit contributions | |
ellar | -0.097 |
yrinth | -0.096 |
Priv | -0.081 |
Balloon | -0.079 |
BW | -0.079 |
Token | two |
Token ID | 734 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
UCS | +0.909 |
UTF | +0.873 |
�士 | +0.870 |
osph | +0.830 |
py | +0.818 |
Neg logit contributions | |
ellar | -0.857 |
yrinth | -0.843 |
Priv | -0.710 |
Balloon | -0.700 |
Klux | -0.697 |
Token | L |
Token ID | 406 |
Feature activation | +5.66e+00 |
Pos logit contributions | |
ellar | +2.417 |
yrinth | +2.378 |
Priv | +2.055 |
drag | +2.015 |
Balloon | +1.999 |
Neg logit contributions | |
UCS | -2.693 |
�士 | -2.676 |
UTF | -2.656 |
osph | -2.519 |
py | -2.458 |
Token | ig |
Token ID | 328 |
Feature activation | +1.46e+01 |
Pos logit contributions | |
ellar | +1.656 |
yrinth | +1.541 |
Priv | +0.864 |
drag | +0.849 |
BW | +0.840 |
Neg logit contributions | |
UCS | -6.571 |
�士 | -6.422 |
UTF | -6.317 |
py | -6.089 |
osph | -6.086 |
Token | ier |
Token ID | 959 |
Feature activation | +6.76e+00 |
Pos logit contributions | |
yrinth | +7.870 |
ellar | +7.827 |
Priv | +6.428 |
drag | +6.211 |
Klux | +6.148 |
Neg logit contributions | |
�士 | -12.240 |
UTF | -11.468 |
UCS | -11.389 |
osph | -10.355 |
py | -10.303 |
Token | JS |
Token ID | 26755 |
Feature activation | +5.29e+00 |
Pos logit contributions | |
ellar | +4.418 |
yrinth | +4.378 |
Priv | +3.881 |
drag | +3.846 |
Doodle | +3.687 |
Neg logit contributions | |
�士 | -4.915 |
UCS | -4.907 |
UTF | -4.897 |
osph | -4.701 |
py | -4.544 |
Token | P |
Token ID | 350 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
ellar | +3.734 |
yrinth | +3.660 |
Priv | +3.251 |
drag | +3.182 |
Balloon | +3.098 |
Neg logit contributions | |
UCS | -3.731 |
UTF | -3.678 |
�士 | -3.661 |
osph | -3.477 |
py | -3.391 |
Token | 3 |
Token ID | 18 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
ellar | +0.301 |
yrinth | +0.296 |
Priv | +0.260 |
Klux | +0.257 |
Balloon | +0.256 |
Neg logit contributions | |
UCS | -0.191 |
UTF | -0.180 |
�士 | -0.180 |
osph | -0.167 |
py | -0.165 |
Token | N |
Token ID | 399 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
ellar | +2.220 |
yrinth | +2.193 |
Priv | +1.878 |
drag | +1.830 |
Balloon | +1.822 |
Neg logit contributions | |
UCS | -2.360 |
UTF | -2.306 |
�士 | -2.282 |
osph | -2.182 |
py | -2.129 |
Token | are |
Token ID | 389 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
UCS | +6.807 |
UTF | +6.617 |
py | +6.122 |
�士 | +6.102 |
osph | +6.096 |
Neg logit contributions | |
ellar | -9.386 |
yrinth | -8.957 |
Klux | -8.061 |
Doodle | -7.804 |
Priv | -7.721 |
Token | enabled |
Token ID | 9343 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
UCS | +2.140 |
UTF | +2.047 |
�士 | +2.029 |
osph | +1.949 |
py | +1.925 |
Neg logit contributions | |
ellar | -1.846 |
yrinth | -1.811 |
Priv | -1.496 |
Klux | -1.483 |
Balloon | -1.481 |
Token | . |
Token ID | 13 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
UCS | +1.973 |
UTF | +1.888 |
�士 | +1.865 |
osph | +1.790 |
py | +1.767 |
Neg logit contributions | |
ellar | -2.036 |
yrinth | -1.999 |
Priv | -1.687 |
Balloon | -1.669 |
Klux | -1.668 |
Token | Now |
Token ID | 2735 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
UCS | +1.403 |
UTF | +1.346 |
�士 | +1.337 |
osph | +1.278 |
py | +1.266 |
Neg logit contributions | |
ellar | -1.291 |
yrinth | -1.270 |
Priv | -1.060 |
Klux | -1.047 |
Balloon | -1.046 |
Token | go |
Token ID | 467 |
Feature activation | +8.65e+00 |
Pos logit contributions | |
UCS | +0.905 |
UTF | +0.871 |
�士 | +0.869 |
osph | +0.829 |
py | +0.818 |
Neg logit contributions | |
ellar | -0.799 |
yrinth | -0.786 |
Priv | -0.658 |
Balloon | -0.648 |
Klux | -0.645 |
Token | back |
Token ID | 736 |
Feature activation | +1.45e+01 |
Pos logit contributions | |
yrinth | +4.968 |
ellar | +4.768 |
drag | +4.241 |
Priv | +4.052 |
Balloon | +4.026 |
Neg logit contributions | |
�士 | -6.908 |
UTF | -6.859 |
UCS | -6.810 |
osph | -6.413 |
pu | -6.230 |
Token | to |
Token ID | 284 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
yrinth | +7.203 |
ellar | +6.577 |
drag | +5.887 |
Priv | +5.773 |
--------- | +5.759 |
Neg logit contributions | |
�士 | -11.749 |
UCS | -11.556 |
UTF | -11.501 |
osph | -10.847 |
pu | -10.439 |
Token | the |
Token ID | 262 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
ellar | +1.550 |
yrinth | +1.547 |
Priv | +1.317 |
Balloon | +1.278 |
drag | +1.259 |
Neg logit contributions | |
UCS | -1.843 |
UTF | -1.837 |
�士 | -1.828 |
osph | -1.738 |
py | -1.691 |
Token | Kodi |
Token ID | 44129 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
UCS | +1.280 |
UTF | +1.232 |
�士 | +1.229 |
osph | +1.175 |
py | +1.158 |
Neg logit contributions | |
ellar | -1.078 |
yrinth | -1.060 |
Priv | -0.882 |
Balloon | -0.869 |
Klux | -0.864 |
Token | homes |
Token ID | 5682 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
ellar | +2.453 |
yrinth | +2.449 |
Priv | +2.105 |
drag | +2.044 |
Balloon | +2.043 |
Neg logit contributions | |
UCS | -2.659 |
�士 | -2.636 |
UTF | -2.629 |
osph | -2.525 |
py | -2.418 |
Token | creen |
Token ID | 32060 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
ellar | +2.532 |
yrinth | +2.507 |
Priv | +2.108 |
drag | +2.085 |
Klux | +2.070 |
Neg logit contributions | |
UCS | -2.392 |
UTF | -2.298 |
�士 | -2.295 |
osph | -2.180 |
pu | -2.041 |
Token | $ |
Token ID | 720 |
Feature activation | +7.63e+00 |
Pos logit contributions | |
ellar | +0.362 |
yrinth | +0.354 |
Priv | +0.306 |
Balloon | +0.300 |
Klux | +0.295 |
Neg logit contributions | |
UCS | -0.345 |
�士 | -0.332 |
UTF | -0.331 |
osph | -0.316 |
py | -0.309 |
Token | image |
Token ID | 9060 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
ellar | +4.300 |
yrinth | +4.067 |
BW | +3.319 |
Balloon | +3.309 |
[_ | +3.219 |
Neg logit contributions | |
UCS | -6.558 |
�士 | -6.547 |
UTF | -6.099 |
osph | -5.960 |
� | -5.829 |
Token | . |
Token ID | 13 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
ellar | +2.987 |
yrinth | +2.867 |
[_ | +2.454 |
BW | +2.442 |
Priv | +2.428 |
Neg logit contributions | |
UCS | -3.579 |
�士 | -3.492 |
UTF | -3.357 |
osph | -3.289 |
py | -3.160 |
Token | Draw |
Token ID | 25302 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ellar | +1.035 |
yrinth | +1.008 |
BW | +0.777 |
Priv | +0.759 |
Balloon | +0.751 |
Neg logit contributions | |
UCS | -2.121 |
�士 | -2.072 |
UTF | -2.010 |
osph | -1.976 |
py | -1.921 |
Token | String |
Token ID | 10100 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ellar | +0.935 |
yrinth | +0.920 |
Priv | +0.805 |
Balloon | +0.801 |
BW | +0.797 |
Neg logit contributions | |
UCS | -0.627 |
�士 | -0.604 |
UTF | -0.577 |
osph | -0.565 |
py | -0.541 |
Token | ($ |
Token ID | 16763 |
Feature activation | +1.44e+01 |
Pos logit contributions | |
ellar | +1.104 |
yrinth | +1.073 |
Priv | +0.933 |
Balloon | +0.914 |
BW | +0.901 |
Neg logit contributions | |
UCS | -1.074 |
�士 | -1.048 |
UTF | -1.015 |
osph | -0.982 |
py | -0.955 |
Token | art |
Token ID | 433 |
Feature activation | +7.76e+00 |
Pos logit contributions | |
ellar | +6.540 |
yrinth | +5.378 |
night | +4.774 |
[_ | +4.698 |
BW | +4.579 |
Neg logit contributions | |
�士 | -14.441 |
UCS | -13.346 |
UTF | -12.434 |
senal | -11.972 |
osph | -11.967 |
Token | ext |
Token ID | 2302 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ellar | +3.551 |
yrinth | +3.187 |
[_ | +2.499 |
night | +2.479 |
--------- | +2.451 |
Neg logit contributions | |
�士 | -8.205 |
UCS | -7.668 |
UTF | -7.327 |
osph | -7.009 |
� | -6.877 |
Token | [ |
Token ID | 58 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
ellar | +0.835 |
yrinth | +0.819 |
Priv | +0.694 |
Balloon | +0.684 |
Klux | +0.680 |
Neg logit contributions | |
UCS | -0.863 |
�士 | -0.831 |
UTF | -0.827 |
osph | -0.788 |
py | -0.774 |
Token | $ |
Token ID | 3 |
Feature activation | +6.19e+00 |
Pos logit contributions | |
UCS | +0.402 |
UTF | +0.386 |
�士 | +0.361 |
py | +0.353 |
osph | +0.350 |
Neg logit contributions | |
yrinth | -0.715 |
ellar | -0.714 |
Priv | -0.621 |
Balloon | -0.617 |
Klux | -0.616 |
Token | i |
Token ID | 72 |
Feature activation | +8.48e+00 |
Pos logit contributions | |
ellar | +3.571 |
yrinth | +3.367 |
[_ | +2.741 |
Priv | +2.725 |
Balloon | +2.672 |
Neg logit contributions | |
�士 | -5.590 |
UCS | -5.402 |
UTF | -5.056 |
osph | -4.890 |
� | -4.721 |
Token | performance |
Token ID | 2854 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
UCS | +0.828 |
�士 | +0.800 |
UTF | +0.798 |
osph | +0.760 |
py | +0.749 |
Neg logit contributions | |
ellar | -0.719 |
yrinth | -0.708 |
Priv | -0.594 |
Balloon | -0.584 |
Klux | -0.578 |
Token | . |
Token ID | 13 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
ellar | +1.599 |
yrinth | +1.569 |
Priv | +1.342 |
Balloon | +1.322 |
--------- | +1.299 |
Neg logit contributions | |
UCS | -1.799 |
�士 | -1.781 |
UTF | -1.731 |
osph | -1.645 |
py | -1.610 |
Token |
|
Token ID | 198 |
Feature activation | -9.24e-01 |
Pos logit contributions | |
ellar | +0.219 |
yrinth | +0.214 |
Priv | +0.183 |
Balloon | +0.179 |
Doodle | +0.176 |
Neg logit contributions | |
UCS | -0.252 |
�士 | -0.246 |
UTF | -0.245 |
osph | -0.234 |
py | -0.229 |
Token |
|
Token ID | 198 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
UCS | +0.680 |
UTF | +0.651 |
�士 | +0.617 |
py | +0.615 |
osph | +0.612 |
Neg logit contributions | |
yrinth | -0.673 |
ellar | -0.669 |
Klux | -0.553 |
Priv | -0.551 |
Balloon | -0.550 |
Token | Going |
Token ID | 27404 |
Feature activation | +6.14e+00 |
Pos logit contributions | |
ellar | +0.267 |
yrinth | +0.263 |
Priv | +0.224 |
Balloon | +0.220 |
BW | +0.220 |
Neg logit contributions | |
UCS | -0.262 |
�士 | -0.254 |
UTF | -0.249 |
osph | -0.239 |
py | -0.233 |
Token | back |
Token ID | 736 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
yrinth | +4.047 |
ellar | +4.037 |
Priv | +3.601 |
Balloon | +3.544 |
Klux | +3.411 |
Neg logit contributions | |
�士 | -4.637 |
UTF | -4.456 |
UCS | -4.416 |
osph | -4.172 |
py | -4.099 |
Token | to |
Token ID | 284 |
Feature activation | +4.96e+00 |
Pos logit contributions | |
yrinth | +7.098 |
ellar | +6.985 |
--------- | +5.701 |
drag | +5.665 |
Priv | +5.588 |
Neg logit contributions | |
�士 | -11.476 |
UCS | -11.336 |
UTF | -10.997 |
� | -10.208 |
py | -10.175 |
Token | our |
Token ID | 674 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
ellar | +3.424 |
yrinth | +3.420 |
Priv | +2.994 |
Balloon | +2.937 |
drag | +2.882 |
Neg logit contributions | |
�士 | -3.578 |
UTF | -3.542 |
UCS | -3.490 |
osph | -3.319 |
py | -3.220 |
Token | ideal |
Token ID | 7306 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
ellar | +3.088 |
yrinth | +3.042 |
Priv | +2.643 |
Balloon | +2.582 |
Doodle | +2.535 |
Neg logit contributions | |
�士 | -3.570 |
UCS | -3.505 |
UTF | -3.494 |
osph | -3.321 |
py | -3.242 |
Token | world |
Token ID | 995 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ellar | +1.391 |
yrinth | +1.377 |
Priv | +1.161 |
Balloon | +1.133 |
Klux | +1.112 |
Neg logit contributions | |
UCS | -1.606 |
�士 | -1.591 |
UTF | -1.573 |
osph | -1.492 |
py | -1.473 |
Token | , |
Token ID | 11 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ellar | +1.304 |
yrinth | +1.274 |
Priv | +1.077 |
Balloon | +1.062 |
drag | +1.039 |
Neg logit contributions | |
UCS | -1.463 |
�士 | -1.441 |
UTF | -1.424 |
osph | -1.347 |
py | -1.320 |
Token | rejected |
Token ID | 8606 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
ellar | +1.628 |
yrinth | +1.599 |
Priv | +1.358 |
Balloon | +1.345 |
Doodle | +1.311 |
Neg logit contributions | |
UCS | -1.938 |
�士 | -1.888 |
UTF | -1.886 |
osph | -1.796 |
py | -1.762 |
Token | the |
Token ID | 262 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
ellar | +1.795 |
yrinth | +1.751 |
Priv | +1.524 |
Balloon | +1.508 |
drag | +1.432 |
Neg logit contributions | |
UCS | -2.286 |
�士 | -2.268 |
UTF | -2.254 |
osph | -2.165 |
py | -2.087 |
Token | Per |
Token ID | 2448 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
ellar | +2.266 |
yrinth | +2.167 |
Priv | +1.839 |
Balloon | +1.833 |
drag | +1.733 |
Neg logit contributions | |
�士 | -4.289 |
UTF | -4.217 |
UCS | -4.202 |
osph | -4.035 |
pu | -3.913 |
Token | kin |
Token ID | 5116 |
Feature activation | +6.73e+00 |
Pos logit contributions | |
UCS | +2.138 |
UTF | +2.037 |
osph | +1.971 |
py | +1.944 |
pu | +1.885 |
Neg logit contributions | |
yrinth | -2.929 |
ellar | -2.897 |
Priv | -2.530 |
Doodle | -2.500 |
Balloon | -2.477 |
Token | - |
Token ID | 12 |
Feature activation | +1.34e+01 |
Pos logit contributions | |
ellar | +4.150 |
yrinth | +4.011 |
Balloon | +3.433 |
Priv | +3.407 |
--------- | +3.267 |
Neg logit contributions | |
UCS | -5.329 |
�士 | -5.301 |
UTF | -5.224 |
osph | -5.006 |
py | -4.811 |
Token | El |
Token ID | 9527 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
ellar | +7.110 |
yrinth | +6.425 |
--------- | +5.793 |
BW | +5.621 |
LG | +5.607 |
Neg logit contributions | |
�士 | -11.910 |
UCS | -10.879 |
osph | -10.621 |
UTF | -10.095 |
pu | -9.854 |
Token | mer |
Token ID | 647 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
ellar | +5.743 |
yrinth | +5.163 |
night | +4.623 |
Klux | +4.300 |
Priv | +4.145 |
Neg logit contributions | |
�士 | -15.158 |
UTF | -13.476 |
UCS | -13.285 |
osph | -12.459 |
� | -12.194 |
Token | proposal |
Token ID | 6961 |
Feature activation | -1.62e-04 |
Pos logit contributions | |
ellar | +2.914 |
yrinth | +2.784 |
Balloon | +2.396 |
Priv | +2.384 |
Doodle | +2.281 |
Neg logit contributions | |
�士 | -5.204 |
UCS | -5.078 |
UTF | -5.074 |
osph | -4.820 |
pu | -4.681 |
Token | . |
Token ID | 13 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
UCS | +0.000 |
�士 | +0.000 |
UTF | +0.000 |
osph | +0.000 |
py | +0.000 |
Neg logit contributions | |
ellar | -0.000 |
yrinth | -0.000 |
Priv | -0.000 |
Balloon | -0.000 |
Klux | -0.000 |
Token | The |
Token ID | 383 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
UCS | +1.049 |
UTF | +1.005 |
�士 | +1.003 |
osph | +0.953 |
py | +0.937 |
Neg logit contributions | |
ellar | -1.124 |
yrinth | -1.106 |
Priv | -0.945 |
Balloon | -0.932 |
Klux | -0.927 |
Token | H |
Token ID | 367 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
ellar | +1.653 |
yrinth | +1.626 |
Priv | +1.399 |
Balloon | +1.385 |
Doodle | +1.332 |
Neg logit contributions | |
UCS | -1.941 |
�士 | -1.930 |
UTF | -1.914 |
osph | -1.820 |
py | -1.769 |
Token | 2 |
Token ID | 17 |
Feature activation | +4.94e+00 |
Pos logit contributions | |
ellar | +1.530 |
yrinth | +1.482 |
Priv | +1.311 |
Balloon | +1.292 |
BW | +1.287 |
Neg logit contributions | |
UCS | -1.167 |
�士 | -1.131 |
UTF | -1.092 |
osph | -1.058 |
py | -1.018 |
Token | + |
Token ID | 1343 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ellar | +3.146 |
yrinth | +2.983 |
Balloon | +2.578 |
)-- | +2.566 |
[_ | +2.565 |
Neg logit contributions | |
UCS | -3.881 |
�士 | -3.855 |
UTF | -3.662 |
osph | -3.591 |
py | -3.448 |
Token | $ |
Token ID | 720 |
Feature activation | +7.73e+00 |
Pos logit contributions | |
ellar | +0.869 |
yrinth | +0.848 |
Priv | +0.737 |
Balloon | +0.726 |
BW | +0.711 |
Neg logit contributions | |
UCS | -0.828 |
�士 | -0.804 |
UTF | -0.796 |
osph | -0.765 |
py | -0.747 |
Token | s |
Token ID | 82 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ellar | +4.246 |
yrinth | +3.882 |
BW | +3.404 |
Balloon | +3.243 |
Priv | +3.232 |
Neg logit contributions | |
UCS | -6.716 |
�士 | -6.713 |
UTF | -6.255 |
osph | -6.153 |
py | -5.980 |
Token | z |
Token ID | 89 |
Feature activation | +8.80e+00 |
Pos logit contributions | |
ellar | +0.914 |
yrinth | +0.891 |
Priv | +0.755 |
BW | +0.751 |
Balloon | +0.741 |
Neg logit contributions | |
UCS | -0.942 |
�士 | -0.919 |
UTF | -0.879 |
osph | -0.843 |
py | -0.822 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
ellar | +5.107 |
yrinth | +4.805 |
[_ | +4.254 |
BW | +4.239 |
Priv | +4.165 |
Neg logit contributions | |
UCS | -7.080 |
�士 | -6.980 |
UTF | -6.585 |
osph | -6.419 |
pu | -6.158 |
Token | . |
Token ID | 13 |
Feature activation | +7.93e+00 |
Pos logit contributions | |
ellar | +7.012 |
yrinth | +6.260 |
[_ | +6.231 |
)-- | +6.170 |
--------- | +5.800 |
Neg logit contributions | |
�士 | -11.600 |
UCS | -11.218 |
osph | -10.533 |
UTF | -10.381 |
pu | -10.085 |
Token | Height |
Token ID | 23106 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
ellar | +3.245 |
yrinth | +2.963 |
BW | +2.628 |
Balloon | +2.463 |
--------- | +2.434 |
Neg logit contributions | |
�士 | -7.812 |
UCS | -7.772 |
osph | -7.415 |
UTF | -7.194 |
ansen | -7.016 |
Token | ), |
Token ID | 828 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
ellar | +3.299 |
yrinth | +3.108 |
)-- | +2.686 |
Priv | +2.676 |
Balloon | +2.651 |
Neg logit contributions | |
�士 | -4.816 |
UCS | -4.797 |
UTF | -4.573 |
osph | -4.450 |
py | -4.308 |
Token | $ |
Token ID | 3 |
Feature activation | +9.02e+00 |
Pos logit contributions | |
ellar | +1.779 |
yrinth | +1.737 |
Priv | +1.538 |
Balloon | +1.502 |
BW | +1.493 |
Neg logit contributions | |
UCS | -1.230 |
�士 | -1.176 |
UTF | -1.148 |
osph | -1.105 |
py | -1.060 |
Token | SR |
Token ID | 12562 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
ellar | +5.239 |
yrinth | +4.856 |
BW | +4.303 |
Priv | +4.118 |
LG | +4.093 |
Neg logit contributions | |
�士 | -7.322 |
UCS | -7.281 |
UTF | -6.827 |
osph | -6.795 |
py | -6.533 |
Token | 75 |
Token ID | 2425 |
Feature activation | +7.43e+00 |
Pos logit contributions | |
ellar | +3.107 |
yrinth | +2.916 |
Priv | +2.640 |
Balloon | +2.591 |
--------- | +2.587 |
Neg logit contributions | |
�士 | -3.074 |
UCS | -3.058 |
UTF | -2.944 |
osph | -2.888 |
py | -2.717 |
Token | x |
Token ID | 2124 |
Feature activation | +5.01e+00 |
Pos logit contributions | |
ellar | +3.405 |
yrinth | +3.248 |
Priv | +2.841 |
Balloon | +2.693 |
drag | +2.645 |
Neg logit contributions | |
�士 | -6.833 |
UCS | -6.736 |
UTF | -6.665 |
osph | -6.497 |
py | -6.313 |
Token | . |
Token ID | 13 |
Feature activation | +9.05e+00 |
Pos logit contributions | |
ellar | +3.280 |
yrinth | +3.063 |
Priv | +2.738 |
--------- | +2.708 |
[_ | +2.679 |
Neg logit contributions | |
�士 | -4.040 |
UCS | -3.862 |
UTF | -3.701 |
osph | -3.619 |
py | -3.431 |
Token | x |
Token ID | 87 |
Feature activation | +9.46e+00 |
Pos logit contributions | |
ellar | +4.402 |
yrinth | +3.917 |
[_ | +3.427 |
--------- | +3.375 |
BW | +3.317 |
Neg logit contributions | |
�士 | -9.027 |
UCS | -8.329 |
UTF | -7.930 |
osph | -7.742 |
senal | -7.404 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
ellar | +5.264 |
yrinth | +4.554 |
[_ | +4.427 |
--------- | +4.417 |
Priv | +4.387 |
Neg logit contributions | |
�士 | -8.727 |
UCS | -7.706 |
UTF | -7.439 |
senal | -7.409 |
osph | -7.398 |
Token | x |
Token ID | 87 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
ellar | +4.754 |
yrinth | +4.199 |
[_ | +3.715 |
--------- | +3.598 |
night | +3.583 |
Neg logit contributions | |
�士 | -10.356 |
UCS | -9.517 |
UTF | -9.055 |
osph | -8.835 |
senal | -8.601 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
ellar | +6.885 |
[_ | +6.174 |
--------- | +5.865 |
yrinth | +5.678 |
Priv | +5.652 |
Neg logit contributions | |
�士 | -13.332 |
UCS | -11.891 |
senal | -11.712 |
UTF | -11.320 |
osph | -11.317 |
Token | 82 |
Token ID | 6469 |
Feature activation | +6.24e+00 |
Pos logit contributions | |
ellar | +6.453 |
yrinth | +6.009 |
[_ | +5.060 |
ever | +4.651 |
Balloon | +4.642 |
Neg logit contributions | |
UCS | -13.809 |
UTF | -13.085 |
�士 | -12.661 |
osph | -12.321 |
� | -11.610 |
Token | 11 |
Token ID | 1367 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
ellar | +3.998 |
yrinth | +3.972 |
Priv | +3.509 |
--------- | +3.388 |
Balloon | +3.384 |
Neg logit contributions | |
�士 | -4.772 |
UCS | -4.684 |
UTF | -4.593 |
osph | -4.532 |
py | -4.282 |
Token | 66 |
Token ID | 2791 |
Feature activation | +8.50e+00 |
Pos logit contributions | |
ellar | +1.875 |
yrinth | +1.794 |
Priv | +1.592 |
--------- | +1.572 |
Balloon | +1.568 |
Neg logit contributions | |
UCS | -1.734 |
�士 | -1.698 |
UTF | -1.657 |
osph | -1.624 |
py | -1.546 |
Token | 756 |
Token ID | 38219 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
ellar | +5.695 |
yrinth | +5.270 |
--------- | +4.933 |
Priv | +4.764 |
BW | +4.760 |
Neg logit contributions | |
UCS | -6.110 |
�士 | -6.002 |
UTF | -5.751 |
osph | -5.727 |
py | -5.305 |
Token | ] |
Token ID | 60 |
Feature activation | +6.05e+00 |
Pos logit contributions | |
ellar | +3.097 |
yrinth | +2.940 |
Priv | +2.525 |
--------- | +2.521 |
[_ | +2.491 |
Neg logit contributions | |
�士 | -3.769 |
UCS | -3.680 |
UTF | -3.519 |
osph | -3.390 |
py | -3.251 |
Token | Mega |
Token ID | 43471 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
ellar | +4.145 |
yrinth | +4.103 |
BW | +3.603 |
Balloon | +3.506 |
--------- | +3.498 |
Neg logit contributions | |
UCS | -4.362 |
�士 | -4.293 |
UTF | -4.030 |
osph | -4.014 |
py | -3.757 |
Token | Pony |
Token ID | 30377 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
ellar | +1.969 |
yrinth | +1.937 |
Priv | +1.638 |
Balloon | +1.616 |
Doodle | +1.601 |
Neg logit contributions | |
UCS | -2.734 |
�士 | -2.689 |
UTF | -2.670 |
osph | -2.575 |
py | -2.498 |
Token | [/ |
Token ID | 13412 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
UCS | +3.709 |
UTF | +3.459 |
�士 | +3.438 |
py | +3.318 |
osph | +3.318 |
Neg logit contributions | |
ellar | -4.203 |
yrinth | -4.114 |
Klux | -3.446 |
Priv | -3.430 |
--------- | -3.361 |
Token | b |
Token ID | 65 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
ellar | +1.989 |
yrinth | +1.919 |
Priv | +1.614 |
BW | +1.601 |
Balloon | +1.588 |
Neg logit contributions | |
UCS | -2.438 |
�士 | -2.419 |
UTF | -2.329 |
osph | -2.224 |
py | -2.161 |
Token | ][/ |
Token ID | 44926 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
ellar | +1.461 |
yrinth | +1.424 |
Priv | +1.219 |
Balloon | +1.203 |
Klux | +1.191 |
Neg logit contributions | |
UCS | -1.443 |
�士 | -1.416 |
UTF | -1.377 |
osph | -1.315 |
py | -1.285 |
Token | color |
Token ID | 8043 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
ellar | +2.867 |
yrinth | +1.746 |
BW | +1.527 |
night | +1.358 |
--------- | +1.274 |
Neg logit contributions | |
�士 | -18.569 |
UCS | -16.496 |
senal | -15.836 |
UTF | -15.606 |
� | -15.291 |
Token | ] |
Token ID | 60 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
ellar | +0.640 |
yrinth | +0.627 |
Priv | +0.532 |
Balloon | +0.524 |
Klux | +0.520 |
Neg logit contributions | |
UCS | -0.660 |
�士 | -0.642 |
UTF | -0.634 |
osph | -0.604 |
py | -0.591 |
Token | - |
Token ID | 532 |
Feature activation | +5.89e+00 |
Pos logit contributions | |
ellar | +2.059 |
yrinth | +2.056 |
Balloon | +1.667 |
Priv | +1.664 |
--------- | +1.605 |
Neg logit contributions | |
UCS | -3.127 |
�士 | -3.042 |
UTF | -3.004 |
osph | -2.932 |
py | -2.822 |
Token | 20 |
Token ID | 1160 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
yrinth | +3.259 |
ellar | +3.200 |
Balloon | +2.735 |
Priv | +2.661 |
drag | +2.549 |
Neg logit contributions | |
UCS | -5.028 |
�士 | -5.020 |
UTF | -4.960 |
osph | -4.811 |
py | -4.572 |
Token | % |
Token ID | 4 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
ellar | +1.517 |
yrinth | +1.486 |
Balloon | +1.230 |
Priv | +1.223 |
BW | +1.195 |
Neg logit contributions | |
UCS | -2.118 |
�士 | -2.060 |
UTF | -2.044 |
osph | -1.955 |
py | -1.888 |
Token | A |
Token ID | 317 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
ellar | +1.944 |
yrinth | +1.926 |
Priv | +1.709 |
Balloon | +1.635 |
Doodle | +1.606 |
Neg logit contributions | |
UCS | -2.186 |
�士 | -2.151 |
UTF | -2.134 |
osph | -2.049 |
py | -2.000 |
Token | Novel |
Token ID | 24467 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ellar | +1.972 |
yrinth | +1.952 |
Priv | +1.703 |
Balloon | +1.647 |
Doodle | +1.613 |
Neg logit contributions | |
UCS | -2.218 |
�士 | -2.186 |
UTF | -2.179 |
osph | -2.082 |
py | -2.019 |
Token | ( |
Token ID | 357 |
Feature activation | +7.46e+00 |
Pos logit contributions | |
UCS | +1.328 |
UTF | +1.274 |
�士 | +1.270 |
osph | +1.214 |
py | +1.199 |
Neg logit contributions | |
ellar | -1.178 |
yrinth | -1.157 |
Priv | -0.966 |
Balloon | -0.953 |
Klux | -0.952 |
Token | New |
Token ID | 3791 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
ellar | +4.827 |
yrinth | +4.715 |
Priv | +4.067 |
BW | +4.061 |
--------- | +4.031 |
Neg logit contributions | |
�士 | -5.456 |
UCS | -5.456 |
UTF | -5.165 |
osph | -5.159 |
py | -4.901 |
Token | York |
Token ID | 1971 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
ellar | +2.532 |
yrinth | +2.505 |
Priv | +2.111 |
Balloon | +2.012 |
Klux | +1.934 |
Neg logit contributions | |
UCS | -3.690 |
UTF | -3.662 |
�士 | -3.623 |
osph | -3.465 |
py | -3.383 |
Token | : |
Token ID | 25 |
Feature activation | +1.40e+01 |
Pos logit contributions | |
ellar | +2.697 |
yrinth | +2.609 |
Priv | +2.238 |
Balloon | +2.185 |
Doodle | +2.127 |
Neg logit contributions | |
UCS | -3.226 |
�士 | -3.181 |
UTF | -3.127 |
osph | -3.009 |
py | -2.986 |
Token | St |
Token ID | 520 |
Feature activation | +6.11e+00 |
Pos logit contributions | |
ellar | +8.046 |
Priv | +8.015 |
yrinth | +7.435 |
Balloon | +7.377 |
Band | +7.222 |
Neg logit contributions | |
osph | -9.812 |
�士 | -9.803 |
UTF | -9.562 |
amera | -9.422 |
UCS | -9.302 |
Token | . |
Token ID | 13 |
Feature activation | +7.66e+00 |
Pos logit contributions | |
ellar | +4.164 |
yrinth | +3.833 |
Priv | +3.296 |
Klux | +3.165 |
--------- | +3.163 |
Neg logit contributions | |
UCS | -4.757 |
�士 | -4.641 |
UTF | -4.547 |
py | -4.264 |
� | -4.175 |
Token | Martin |
Token ID | 5780 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
ellar | +3.256 |
yrinth | +2.838 |
Priv | +2.536 |
Balloon | +2.266 |
Doodle | +2.193 |
Neg logit contributions | |
UCS | -7.528 |
�士 | -7.475 |
UTF | -7.342 |
osph | -6.993 |
py | -6.988 |
Token | � |
Token ID | 447 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
ellar | +5.976 |
yrinth | +5.567 |
Priv | +4.962 |
)-- | +4.866 |
Balloon | +4.761 |
Neg logit contributions | |
�士 | -9.539 |
UTF | -9.456 |
UCS | -9.378 |
amera | -8.968 |
py | -8.909 |
Token | � |
Token ID | 247 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
ellar | +0.501 |
yrinth | +0.491 |
Priv | +0.415 |
Balloon | +0.408 |
Klux | +0.405 |
Neg logit contributions | |
UCS | -0.548 |
UTF | -0.522 |
�士 | -0.507 |
osph | -0.493 |
py | -0.489 |
Token | but |
Token ID | 475 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
ellar | +2.233 |
yrinth | +2.173 |
Priv | +1.859 |
Balloon | +1.831 |
drag | +1.799 |
Neg logit contributions | |
UCS | -2.638 |
�士 | -2.588 |
UTF | -2.564 |
osph | -2.434 |
py | -2.386 |
Token | typically |
Token ID | 6032 |
Feature activation | +9.46e+00 |
Pos logit contributions | |
ellar | +2.086 |
yrinth | +2.016 |
Priv | +1.722 |
Balloon | +1.710 |
Klux | +1.668 |
Neg logit contributions | |
UCS | -2.562 |
�士 | -2.502 |
UTF | -2.481 |
osph | -2.373 |
py | -2.335 |
Token | got |
Token ID | 1392 |
Feature activation | +9.85e+00 |
Pos logit contributions | |
ellar | +5.548 |
yrinth | +5.182 |
drag | +4.715 |
Balloon | +4.668 |
Priv | +4.645 |
Neg logit contributions | |
�士 | -7.365 |
UCS | -7.297 |
UTF | -7.257 |
osph | -6.941 |
py | -6.699 |
Token | his |
Token ID | 465 |
Feature activation | +8.85e+00 |
Pos logit contributions | |
ellar | +5.770 |
yrinth | +5.513 |
drag | +4.899 |
Priv | +4.820 |
Balloon | +4.765 |
Neg logit contributions | |
�士 | -7.662 |
UTF | -7.641 |
UCS | -7.587 |
osph | -7.323 |
py | -6.980 |
Token | best |
Token ID | 1266 |
Feature activation | +9.84e+00 |
Pos logit contributions | |
ellar | +5.007 |
yrinth | +4.591 |
drag | +4.212 |
Balloon | +4.145 |
Priv | +4.137 |
Neg logit contributions | |
�士 | -7.404 |
UCS | -7.127 |
UTF | -7.104 |
osph | -6.916 |
py | -6.492 |
Token | results |
Token ID | 2482 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
ellar | +5.510 |
yrinth | +4.965 |
drag | +4.606 |
Priv | +4.494 |
night | +4.395 |
Neg logit contributions | |
�士 | -8.112 |
UCS | -7.916 |
UTF | -7.870 |
osph | -7.653 |
py | -7.321 |
Token | at |
Token ID | 379 |
Feature activation | +6.78e+00 |
Pos logit contributions | |
ellar | +6.882 |
yrinth | +6.259 |
night | +5.820 |
drag | +5.797 |
Balloon | +5.670 |
Neg logit contributions | |
�士 | -12.042 |
UCS | -11.237 |
UTF | -11.033 |
osph | -10.501 |
pu | -10.074 |
Token | night |
Token ID | 1755 |
Feature activation | +8.64e+00 |
Pos logit contributions | |
ellar | +3.674 |
yrinth | +3.540 |
Balloon | +3.072 |
Priv | +3.049 |
drag | +2.963 |
Neg logit contributions | |
UTF | -5.803 |
�士 | -5.798 |
UCS | -5.648 |
osph | -5.515 |
py | -5.334 |
Token | when |
Token ID | 618 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
ellar | +5.067 |
yrinth | +4.886 |
Balloon | +4.244 |
[_ | +4.208 |
drag | +4.181 |
Neg logit contributions | |
�士 | -6.943 |
UCS | -6.855 |
UTF | -6.684 |
osph | -6.236 |
pu | -6.108 |
Token | the |
Token ID | 262 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
ellar | +2.304 |
yrinth | +2.202 |
Priv | +1.875 |
Balloon | +1.866 |
drag | +1.829 |
Neg logit contributions | |
UCS | -2.999 |
�士 | -2.967 |
UTF | -2.919 |
osph | -2.798 |
py | -2.767 |
Token | airport |
Token ID | 9003 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
ellar | +2.691 |
yrinth | +2.619 |
Priv | +2.293 |
Balloon | +2.292 |
drag | +2.268 |
Neg logit contributions | |
UCS | -2.493 |
�士 | -2.483 |
UTF | -2.408 |
osph | -2.289 |
py | -2.251 |
Token | we |
Token ID | 356 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
UCS | +2.127 |
UTF | +2.030 |
�士 | +2.020 |
osph | +1.935 |
py | +1.913 |
Neg logit contributions | |
ellar | -1.900 |
yrinth | -1.861 |
Priv | -1.550 |
Balloon | -1.532 |
Klux | -1.527 |
Token | must |
Token ID | 1276 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
UCS | +0.241 |
�士 | +0.232 |
UTF | +0.232 |
osph | +0.217 |
py | +0.213 |
Neg logit contributions | |
ellar | -0.295 |
yrinth | -0.291 |
Priv | -0.252 |
Balloon | -0.248 |
Klux | -0.247 |
Token | place |
Token ID | 1295 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ellar | +0.920 |
yrinth | +0.904 |
Priv | +0.763 |
drag | +0.747 |
Balloon | +0.747 |
Neg logit contributions | |
UCS | -1.061 |
�士 | -1.042 |
UTF | -1.033 |
osph | -0.967 |
py | -0.959 |
Token | it |
Token ID | 340 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
ellar | +0.825 |
yrinth | +0.815 |
Priv | +0.692 |
Balloon | +0.670 |
Klux | +0.669 |
Neg logit contributions | |
UCS | -0.989 |
�士 | -0.971 |
UTF | -0.967 |
osph | -0.922 |
py | -0.902 |
Token | front |
Token ID | 2166 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
yrinth | +2.655 |
ellar | +2.655 |
Priv | +2.247 |
drag | +2.220 |
Klux | +2.172 |
Neg logit contributions | |
UCS | -3.499 |
�士 | -3.464 |
UTF | -3.436 |
osph | -3.233 |
py | -3.143 |
Token | and |
Token ID | 290 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
ellar | +1.872 |
yrinth | +1.822 |
Priv | +1.502 |
drag | +1.489 |
Klux | +1.467 |
Neg logit contributions | |
UCS | -2.229 |
�士 | -2.169 |
UTF | -2.159 |
osph | -2.029 |
py | -1.975 |
Token | center |
Token ID | 3641 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ellar | +2.334 |
drag | +1.464 |
yrinth | +1.028 |
wing | +0.876 |
queens | +0.833 |
Neg logit contributions | |
�士 | -16.803 |
UTF | -16.367 |
UCS | -16.363 |
osph | -15.807 |
� | -15.421 |
Token | . |
Token ID | 13 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
UCS | +0.839 |
UTF | +0.806 |
�士 | +0.805 |
osph | +0.766 |
py | +0.755 |
Neg logit contributions | |
ellar | -0.786 |
yrinth | -0.773 |
Priv | -0.652 |
Balloon | -0.642 |
Klux | -0.639 |
Token | Dec |
Token ID | 4280 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
UCS | +1.910 |
UTF | +1.815 |
�士 | +1.799 |
osph | +1.714 |
py | +1.705 |
Neg logit contributions | |
ellar | -1.845 |
yrinth | -1.814 |
Klux | -1.499 |
Priv | -1.493 |
Balloon | -1.482 |
Token | ades |
Token ID | 2367 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
ellar | +0.943 |
yrinth | +0.916 |
Priv | +0.753 |
Klux | +0.738 |
Balloon | +0.732 |
Neg logit contributions | |
UCS | -1.245 |
�士 | -1.219 |
UTF | -1.211 |
osph | -1.134 |
py | -1.121 |
Token | ago |
Token ID | 2084 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
UCS | +0.693 |
�士 | +0.669 |
UTF | +0.668 |
osph | +0.636 |
py | +0.625 |
Neg logit contributions | |
ellar | -0.589 |
yrinth | -0.579 |
Priv | -0.485 |
Balloon | -0.477 |
Klux | -0.475 |
Token | a |
Token ID | 257 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
yrinth | +3.019 |
ellar | +2.999 |
Priv | +2.573 |
Balloon | +2.499 |
Klux | +2.468 |
Neg logit contributions | |
�士 | -4.285 |
UTF | -4.258 |
UCS | -4.256 |
osph | -4.064 |
py | -3.936 |
Token | lawsuit |
Token ID | 8087 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
ellar | +2.482 |
yrinth | +2.455 |
Priv | +2.143 |
Balloon | +2.072 |
Doodle | +2.035 |
Neg logit contributions | |
�士 | -3.199 |
UTF | -3.179 |
UCS | -3.174 |
osph | -3.015 |
py | -2.912 |
Token | against |
Token ID | 1028 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
ellar | +2.874 |
yrinth | +2.844 |
Priv | +2.478 |
Balloon | +2.405 |
drag | +2.377 |
Neg logit contributions | |
�士 | -3.166 |
UCS | -3.153 |
UTF | -3.122 |
osph | -2.932 |
py | -2.865 |
Token | New |
Token ID | 968 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
ellar | +2.189 |
yrinth | +2.149 |
Priv | +1.878 |
Balloon | +1.802 |
drag | +1.780 |
Neg logit contributions | |
UCS | -2.649 |
�士 | -2.642 |
UTF | -2.642 |
osph | -2.520 |
py | -2.435 |
Token | York |
Token ID | 1971 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
ellar | +2.002 |
yrinth | +1.941 |
Priv | +1.643 |
Balloon | +1.572 |
Klux | +1.560 |
Neg logit contributions | |
UCS | -2.704 |
UTF | -2.639 |
�士 | -2.620 |
osph | -2.507 |
py | -2.440 |
Token | Governor |
Token ID | 10807 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
ellar | +0.698 |
yrinth | +0.683 |
Priv | +0.599 |
Balloon | +0.587 |
Klux | +0.585 |
Neg logit contributions | |
UCS | -0.600 |
UTF | -0.583 |
�士 | -0.576 |
osph | -0.546 |
py | -0.532 |
Token | Andrew |
Token ID | 6858 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
ellar | +8.384 |
Priv | +7.282 |
yrinth | +7.120 |
[_ | +6.808 |
Balloon | +6.785 |
Neg logit contributions | |
UCS | -10.511 |
UTF | -10.359 |
�士 | -10.293 |
osph | -9.523 |
pu | -9.503 |
Token | Cuomo |
Token ID | 32496 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
ellar | +2.686 |
yrinth | +2.518 |
Priv | +2.219 |
Balloon | +2.149 |
Klux | +2.087 |
Neg logit contributions | |
UCS | -3.767 |
�士 | -3.647 |
UTF | -3.632 |
osph | -3.487 |
py | -3.392 |
Token | ; |
Token ID | 26 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
ellar | +1.771 |
yrinth | +1.739 |
Priv | +1.511 |
Balloon | +1.471 |
Klux | +1.451 |
Neg logit contributions | |
UCS | -1.837 |
�士 | -1.791 |
UTF | -1.775 |
osph | -1.673 |
py | -1.649 |
Token | Janet |
Token ID | 28111 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
ellar | +1.657 |
yrinth | +1.623 |
Priv | +1.405 |
Balloon | +1.362 |
Klux | +1.340 |
Neg logit contributions | |
UCS | -1.857 |
UTF | -1.839 |
�士 | -1.827 |
osph | -1.743 |
py | -1.699 |
Token | Di |
Token ID | 6031 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
UCS | +2.971 |
UTF | +2.834 |
�士 | +2.827 |
osph | +2.709 |
py | +2.680 |
Neg logit contributions | |
ellar | -2.697 |
yrinth | -2.664 |
Priv | -2.202 |
Klux | -2.175 |
Balloon | -2.173 |
Token | laws |
Token ID | 3657 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
ellar | +2.814 |
yrinth | +2.740 |
Priv | +2.369 |
drag | +2.286 |
Klux | +2.284 |
Neg logit contributions | |
�士 | -3.115 |
UCS | -3.105 |
UTF | -3.072 |
osph | -2.932 |
py | -2.832 |
Token | prohibiting |
Token ID | 30363 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ellar | +1.970 |
yrinth | +1.935 |
Priv | +1.664 |
drag | +1.620 |
Balloon | +1.611 |
Neg logit contributions | |
UCS | -2.244 |
�士 | -2.222 |
UTF | -2.188 |
osph | -2.050 |
py | -2.017 |
Token | needle |
Token ID | 17598 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
UCS | +1.535 |
UTF | +1.475 |
�士 | +1.469 |
osph | +1.406 |
py | +1.388 |
Neg logit contributions | |
ellar | -1.299 |
yrinth | -1.278 |
Priv | -1.061 |
Balloon | -1.047 |
Klux | -1.041 |
Token | exchanges |
Token ID | 14525 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
ellar | +2.974 |
yrinth | +2.800 |
drag | +2.476 |
Priv | +2.450 |
Klux | +2.361 |
Neg logit contributions | |
�士 | -4.352 |
UCS | -4.337 |
UTF | -4.302 |
osph | -4.033 |
py | -3.922 |
Token | and |
Token ID | 290 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
ellar | +3.631 |
yrinth | +3.584 |
Priv | +3.127 |
drag | +3.106 |
Balloon | +2.992 |
Neg logit contributions | |
�士 | -4.494 |
UCS | -4.390 |
UTF | -4.315 |
osph | -4.011 |
py | -3.902 |
Token | sy |
Token ID | 827 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
ellar | +2.228 |
yrinth | +2.163 |
Priv | +1.865 |
drag | +1.830 |
Klux | +1.801 |
Neg logit contributions | |
UCS | -2.547 |
�士 | -2.523 |
UTF | -2.516 |
osph | -2.400 |
py | -2.325 |
Token | ringe |
Token ID | 38229 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ellar | +4.036 |
yrinth | +3.743 |
sted | +2.550 |
ever | +2.303 |
apor | +2.188 |
Neg logit contributions | |
�士 | -15.808 |
UTF | -15.411 |
UCS | -15.189 |
� | -13.904 |
osph | -13.716 |
Token | possession |
Token ID | 7797 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
ellar | +0.764 |
yrinth | +0.739 |
Priv | +0.634 |
Balloon | +0.615 |
drag | +0.614 |
Neg logit contributions | |
UCS | -0.937 |
�士 | -0.925 |
UTF | -0.918 |
osph | -0.870 |
py | -0.849 |
Token | without |
Token ID | 1231 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
ellar | +1.712 |
yrinth | +1.679 |
Priv | +1.442 |
drag | +1.410 |
Balloon | +1.401 |
Neg logit contributions | |
UCS | -1.905 |
�士 | -1.881 |
UTF | -1.850 |
osph | -1.740 |
py | -1.703 |
Token | prescriptions |
Token ID | 34092 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
ellar | +1.863 |
yrinth | +1.836 |
Priv | +1.548 |
Balloon | +1.490 |
drag | +1.483 |
Neg logit contributions | |
�士 | -2.351 |
UCS | -2.340 |
UTF | -2.311 |
osph | -2.219 |
py | -2.160 |
Token | have |
Token ID | 423 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
ellar | +1.694 |
yrinth | +1.661 |
Priv | +1.427 |
drag | +1.397 |
Balloon | +1.393 |
Neg logit contributions | |
UCS | -1.839 |
�士 | -1.822 |
UTF | -1.784 |
osph | -1.676 |
py | -1.644 |
Token | . |
Token ID | 13 |
Feature activation | +7.21e+00 |
Pos logit contributions | |
ellar | +5.755 |
yrinth | +5.049 |
Priv | +4.953 |
[_ | +4.826 |
--------- | +4.746 |
Neg logit contributions | |
�士 | -10.763 |
UCS | -9.378 |
UTF | -9.158 |
senal | -9.144 |
osph | -9.060 |
Token | View |
Token ID | 3582 |
Feature activation | +8.46e+00 |
Pos logit contributions | |
ellar | +2.474 |
yrinth | +2.220 |
Priv | +1.897 |
Balloon | +1.718 |
BW | +1.639 |
Neg logit contributions | |
�士 | -7.717 |
UCS | -7.660 |
UTF | -7.594 |
osph | -7.423 |
py | -7.149 |
Token | all |
Token ID | 477 |
Feature activation | +1.19e+01 |
Pos logit contributions | |
ellar | +4.715 |
yrinth | +4.392 |
Priv | +4.064 |
drag | +4.045 |
BW | +3.823 |
Neg logit contributions | |
�士 | -7.472 |
UTF | -6.946 |
UCS | -6.920 |
osph | -6.631 |
py | -6.409 |
Token | New |
Token ID | 968 |
Feature activation | +8.88e+00 |
Pos logit contributions | |
ellar | +3.809 |
Priv | +3.561 |
Balloon | +3.019 |
yrinth | +3.001 |
BW | +2.912 |
Neg logit contributions | |
�士 | -12.950 |
osph | -11.871 |
UTF | -11.858 |
UCS | -11.677 |
senal | -11.250 |
Token | York |
Token ID | 1971 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
ellar | +4.254 |
yrinth | +3.903 |
Priv | +3.784 |
BW | +3.438 |
--------- | +3.429 |
Neg logit contributions | |
�士 | -8.528 |
UTF | -7.798 |
UCS | -7.779 |
osph | -7.502 |
pu | -7.235 |
Token | Times |
Token ID | 3782 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
ellar | +3.401 |
yrinth | +3.267 |
Priv | +2.969 |
Balloon | +2.891 |
Klux | +2.864 |
Neg logit contributions | |
�士 | -3.349 |
UCS | -3.205 |
UTF | -3.115 |
osph | -3.002 |
py | -2.871 |
Token | newsletters |
Token ID | 16983 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
ellar | +4.012 |
Priv | +3.800 |
yrinth | +3.529 |
drag | +3.250 |
--------- | +3.178 |
Neg logit contributions | |
�士 | -15.277 |
UTF | -13.712 |
UCS | -13.612 |
osph | -13.517 |
pu | -13.089 |
Token | . |
Token ID | 13 |
Feature activation | +9.27e+00 |
Pos logit contributions | |
ellar | +2.238 |
yrinth | +2.156 |
Priv | +1.874 |
Balloon | +1.828 |
--------- | +1.811 |
Neg logit contributions | |
�士 | -2.361 |
UCS | -2.358 |
UTF | -2.266 |
osph | -2.167 |
py | -2.112 |
Token |
|
Token ID | 198 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
ellar | +4.789 |
yrinth | +4.210 |
Priv | +4.014 |
--------- | +3.895 |
BW | +3.849 |
Neg logit contributions | |
�士 | -8.942 |
UCS | -7.891 |
UTF | -7.760 |
osph | -7.754 |
senal | -7.434 |
Token |
|
Token ID | 198 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
UCS | +0.468 |
UTF | +0.449 |
�士 | +0.427 |
py | +0.423 |
osph | +0.421 |
Neg logit contributions | |
yrinth | -0.458 |
ellar | -0.457 |
Priv | -0.376 |
Klux | -0.375 |
Balloon | -0.374 |
Token | For |
Token ID | 1890 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
UCS | +0.642 |
�士 | +0.618 |
UTF | +0.614 |
osph | +0.587 |
py | +0.574 |
Neg logit contributions | |
ellar | -0.623 |
yrinth | -0.611 |
Priv | -0.519 |
Balloon | -0.510 |
Klux | -0.508 |
Token | requests |
Token ID | 7007 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
ellar | +2.851 |
yrinth | +2.843 |
Priv | +2.451 |
Balloon | +2.322 |
Klux | +2.303 |
Neg logit contributions | |
�士 | -4.158 |
UCS | -4.108 |
UTF | -4.057 |
osph | -3.905 |
py | -3.820 |
Token | for |
Token ID | 329 |
Feature activation | +8.85e+00 |
Pos logit contributions | |
ellar | +1.840 |
yrinth | +1.795 |
Priv | +1.540 |
drag | +1.486 |
Klux | +1.482 |
Neg logit contributions | |
UCS | -2.326 |
�士 | -2.296 |
UTF | -2.234 |
osph | -2.151 |
py | -2.104 |
Token | comment |
Token ID | 2912 |
Feature activation | -9.40e-02 |
Pos logit contributions | |
ellar | +3.857 |
yrinth | +3.530 |
Priv | +3.049 |
--------- | +2.904 |
intrusion | +2.866 |
Neg logit contributions | |
�士 | -8.267 |
osph | -8.203 |
UCS | -8.199 |
UTF | -8.111 |
py | -7.805 |
Token | and |
Token ID | 290 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
UCS | +0.069 |
�士 | +0.067 |
UTF | +0.066 |
osph | +0.063 |
py | +0.062 |
Neg logit contributions | |
ellar | -0.068 |
yrinth | -0.067 |
Priv | -0.057 |
Balloon | -0.056 |
Klux | -0.056 |
Token | Boh |
Token ID | 44366 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
yrinth | +3.276 |
ellar | +3.251 |
Priv | +2.988 |
Balloon | +2.771 |
--------- | +2.701 |
Neg logit contributions | |
�士 | -3.952 |
UCS | -3.947 |
UTF | -3.891 |
osph | -3.664 |
py | -3.573 |
Token | oli |
Token ID | 11106 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
UCS | +0.627 |
�士 | +0.601 |
UTF | +0.599 |
osph | +0.559 |
py | +0.552 |
Neg logit contributions | |
ellar | -0.678 |
yrinth | -0.666 |
Priv | -0.568 |
Balloon | -0.560 |
Klux | -0.558 |
Token | ub |
Token ID | 549 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
ellar | +6.051 |
yrinth | +5.832 |
Priv | +4.992 |
BW | +4.678 |
Klux | +4.671 |
Neg logit contributions | |
�士 | -13.087 |
UCS | -12.080 |
UTF | -11.442 |
� | -10.762 |
osph | -10.603 |
Token | ov |
Token ID | 709 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ellar | +1.372 |
yrinth | +1.343 |
Priv | +1.114 |
Balloon | +1.092 |
Klux | +1.087 |
Neg logit contributions | |
UCS | -1.730 |
�士 | -1.699 |
UTF | -1.670 |
osph | -1.582 |
py | -1.558 |
Token | could |
Token ID | 714 |
Feature activation | +5.45e+00 |
Pos logit contributions | |
ellar | +0.094 |
yrinth | +0.092 |
Priv | +0.077 |
Balloon | +0.075 |
Klux | +0.075 |
Neg logit contributions | |
UCS | -0.116 |
�士 | -0.112 |
UTF | -0.112 |
osph | -0.106 |
py | -0.105 |
Token | not |
Token ID | 407 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
ellar | +3.366 |
yrinth | +3.194 |
drag | +2.713 |
Priv | +2.704 |
Balloon | +2.665 |
Neg logit contributions | |
�士 | -4.527 |
UCS | -4.499 |
UTF | -4.413 |
osph | -4.124 |
py | -4.029 |
Token | be |
Token ID | 307 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
ellar | +2.949 |
yrinth | +2.819 |
drag | +2.401 |
Priv | +2.400 |
Balloon | +2.349 |
Neg logit contributions | |
UCS | -3.946 |
�士 | -3.911 |
UTF | -3.849 |
osph | -3.619 |
py | -3.561 |
Token | Simon |
Token ID | 11288 |
Feature activation | +9.38e+00 |
Pos logit contributions | |
ellar | +0.630 |
yrinth | +0.617 |
Priv | +0.537 |
Balloon | +0.525 |
Doodle | +0.517 |
Neg logit contributions | |
UCS | -0.653 |
�士 | -0.642 |
UTF | -0.635 |
osph | -0.608 |
py | -0.589 |
Token | Gerr |
Token ID | 45140 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
ellar | +5.493 |
yrinth | +4.991 |
Priv | +4.692 |
Balloon | +4.531 |
Doodle | +4.380 |
Neg logit contributions | |
�士 | -7.759 |
UTF | -7.501 |
UCS | -7.282 |
osph | -6.959 |
py | -6.728 |
Token | ans |
Token ID | 504 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
ellar | +3.230 |
yrinth | +3.147 |
Priv | +2.755 |
Balloon | +2.712 |
Klux | +2.704 |
Neg logit contributions | |
UCS | -2.289 |
�士 | -2.209 |
UTF | -2.184 |
osph | -2.038 |
py | -2.011 |
Token | ( |
Token ID | 357 |
Feature activation | +5.90e+00 |
Pos logit contributions | |
ellar | +1.977 |
yrinth | +1.903 |
Priv | +1.641 |
Balloon | +1.599 |
BW | +1.587 |
Neg logit contributions | |
�士 | -2.425 |
UCS | -2.412 |
UTF | -2.357 |
osph | -2.276 |
py | -2.201 |
Token | Green |
Token ID | 13719 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
ellar | +3.564 |
yrinth | +3.210 |
BW | +3.019 |
Priv | +2.932 |
LG | +2.919 |
Neg logit contributions | |
�士 | -5.005 |
UCS | -4.823 |
osph | -4.654 |
UTF | -4.437 |
py | -4.362 |
Token | Edge |
Token ID | 37021 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
ellar | +3.679 |
yrinth | +3.277 |
BW | +2.700 |
Priv | +2.666 |
drag | +2.572 |
Neg logit contributions | |
�士 | -10.877 |
UCS | -10.587 |
UTF | -10.130 |
osph | -9.776 |
py | -9.624 |
Token | Cycling |
Token ID | 25550 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
ellar | +3.577 |
yrinth | +2.782 |
Priv | +2.772 |
Balloon | +2.539 |
)-- | +2.452 |
Neg logit contributions | |
�士 | -15.410 |
UTF | -14.333 |
osph | -13.910 |
UCS | -13.853 |
py | -13.391 |
Token | Team |
Token ID | 4816 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
ellar | +1.232 |
yrinth | +1.194 |
Priv | +0.975 |
Balloon | +0.949 |
Klux | +0.933 |
Neg logit contributions | |
UCS | -2.022 |
�士 | -1.987 |
UTF | -1.964 |
osph | -1.888 |
py | -1.855 |
Token | ) |
Token ID | 8 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ellar | +2.063 |
yrinth | +1.958 |
Priv | +1.671 |
Balloon | +1.625 |
--------- | +1.620 |
Neg logit contributions | |
�士 | -2.901 |
UCS | -2.868 |
UTF | -2.760 |
osph | -2.662 |
py | -2.587 |
Token | s |
Token ID | 264 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
ellar | +1.246 |
yrinth | +1.226 |
Priv | +1.060 |
Balloon | +1.038 |
drag | +1.027 |
Neg logit contributions | |
UCS | -1.167 |
UTF | -1.127 |
�士 | -1.120 |
osph | -1.071 |
py | -1.054 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
UCS | +1.022 |
UTF | +0.979 |
�士 | +0.921 |
py | +0.914 |
osph | +0.912 |
Neg logit contributions | |
yrinth | -1.189 |
ellar | -1.180 |
Priv | -0.993 |
Klux | -0.991 |
Balloon | -0.987 |
Token | 's |
Token ID | 338 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
ellar | +0.759 |
yrinth | +0.742 |
Priv | +0.630 |
Balloon | +0.622 |
drag | +0.616 |
Neg logit contributions | |
UCS | -0.825 |
�士 | -0.799 |
UTF | -0.796 |
osph | -0.754 |
py | -0.739 |
Token | the |
Token ID | 262 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
ellar | +1.401 |
yrinth | +1.366 |
Priv | +1.155 |
drag | +1.133 |
Balloon | +1.131 |
Neg logit contributions | |
UCS | -1.654 |
�士 | -1.618 |
UTF | -1.610 |
osph | -1.534 |
py | -1.492 |
Token | largest |
Token ID | 4387 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
ellar | +1.938 |
yrinth | +1.888 |
Priv | +1.610 |
Balloon | +1.596 |
drag | +1.575 |
Neg logit contributions | |
UCS | -2.443 |
�士 | -2.440 |
UTF | -2.413 |
osph | -2.297 |
py | -2.245 |
Token | crocod |
Token ID | 37565 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
ellar | +6.087 |
yrinth | +5.607 |
drag | +5.418 |
intrusion | +5.048 |
Balloon | +4.998 |
Neg logit contributions | |
�士 | -9.199 |
UTF | -8.912 |
UCS | -8.765 |
osph | -8.542 |
pu | -8.079 |
Token | ile |
Token ID | 576 |
Feature activation | +8.80e+00 |
Pos logit contributions | |
ellar | +2.714 |
yrinth | +2.617 |
Priv | +2.014 |
drag | +1.991 |
--------- | +1.980 |
Neg logit contributions | |
UCS | -4.238 |
�士 | -4.157 |
UTF | -4.096 |
osph | -3.806 |
� | -3.780 |
Token | ever |
Token ID | 1683 |
Feature activation | +1.36e+01 |
Pos logit contributions | |
ellar | +4.823 |
yrinth | +4.598 |
drag | +4.216 |
intrusion | +3.966 |
Priv | +3.943 |
Neg logit contributions | |
�士 | -7.449 |
UTF | -7.099 |
UCS | -7.015 |
osph | -6.854 |
pu | -6.481 |
Token | to |
Token ID | 284 |
Feature activation | +6.73e+00 |
Pos logit contributions | |
ellar | +6.642 |
drag | +5.963 |
yrinth | +5.721 |
Priv | +5.390 |
queens | +5.336 |
Neg logit contributions | |
�士 | -12.116 |
UTF | -11.152 |
UCS | -10.944 |
osph | -10.683 |
pu | -10.039 |
Token | be |
Token ID | 307 |
Feature activation | +5.86e+00 |
Pos logit contributions | |
ellar | +4.241 |
yrinth | +4.073 |
drag | +3.664 |
Priv | +3.502 |
Balloon | +3.450 |
Neg logit contributions | |
�士 | -5.306 |
UCS | -5.264 |
UTF | -5.243 |
osph | -4.834 |
py | -4.792 |
Token | taken |
Token ID | 2077 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
ellar | +3.383 |
yrinth | +3.263 |
drag | +2.847 |
Priv | +2.776 |
Balloon | +2.720 |
Neg logit contributions | |
�士 | -4.933 |
UCS | -4.855 |
UTF | -4.805 |
osph | -4.609 |
py | -4.449 |
Token | alive |
Token ID | 6776 |
Feature activation | +7.54e+00 |
Pos logit contributions | |
ellar | +3.606 |
yrinth | +3.461 |
drag | +3.107 |
Priv | +3.086 |
Balloon | +3.049 |
Neg logit contributions | |
�士 | -4.460 |
UCS | -4.290 |
UTF | -4.205 |
osph | -4.054 |
pu | -3.917 |
Token | . |
Token ID | 13 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ellar | +4.281 |
yrinth | +4.133 |
drag | +3.675 |
Balloon | +3.610 |
Priv | +3.559 |
Neg logit contributions | |
�士 | -6.362 |
UCS | -6.025 |
UTF | -5.935 |
osph | -5.659 |
pu | -5.528 |
Token | a |
Token ID | 257 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
UCS | +3.464 |
UTF | +3.284 |
py | +3.139 |
osph | +3.054 |
pu | +3.026 |
Neg logit contributions | |
yrinth | -3.961 |
ellar | -3.827 |
Klux | -3.154 |
Priv | -3.148 |
Doodle | -3.145 |
Token | skillet |
Token ID | 41306 |
Feature activation | -1.26e+01 |
Pos logit contributions | |
UCS | +5.495 |
UTF | +5.311 |
py | +5.062 |
osph | +4.802 |
pu | +4.766 |
Neg logit contributions | |
yrinth | -11.268 |
ellar | -10.952 |
Doodle | -9.639 |
Priv | -9.583 |
msec | -9.473 |
Token | over |
Token ID | 625 |
Feature activation | -6.01e+00 |
Pos logit contributions | |
UCS | +6.046 |
UTF | +5.738 |
py | +5.660 |
osph | +5.363 |
pu | +5.067 |
Neg logit contributions | |
yrinth | -11.798 |
ellar | -11.180 |
Doodle | -9.948 |
Balloon | -9.555 |
Priv | -9.418 |
Token | medium |
Token ID | 7090 |
Feature activation | -7.76e+00 |
Pos logit contributions | |
UCS | +3.105 |
UTF | +2.831 |
py | +2.649 |
osph | +2.638 |
pu | +2.538 |
Neg logit contributions | |
yrinth | -5.745 |
ellar | -5.660 |
Doodle | -4.947 |
Priv | -4.854 |
Balloon | -4.786 |
Token | - |
Token ID | 12 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
UCS | +4.469 |
UTF | +4.302 |
py | +4.049 |
osph | +3.951 |
pu | +3.904 |
Neg logit contributions | |
yrinth | -6.886 |
ellar | -6.588 |
Doodle | -5.695 |
Balloon | -5.617 |
Priv | -5.606 |
Token | high |
Token ID | 8929 |
Feature activation | -1.98e+01 |
Pos logit contributions | |
UTF | +3.670 |
py | +3.552 |
UCS | +3.478 |
pu | +3.250 |
osph | +3.117 |
Neg logit contributions | |
yrinth | -11.868 |
ellar | -11.715 |
Doodle | -11.264 |
Balloon | -10.600 |
Priv | -10.497 |
Token | heat |
Token ID | 4894 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
osph | +4.371 |
py | +4.361 |
UTF | +4.358 |
UCS | +4.014 |
pu | +3.603 |
Neg logit contributions | |
yrinth | -22.110 |
ellar | -20.360 |
Doodle | -18.976 |
idav | -18.960 |
eleph | -18.613 |
Token | . |
Token ID | 13 |
Feature activation | -9.85e+00 |
Pos logit contributions | |
UCS | +5.649 |
UTF | +5.274 |
py | +5.111 |
osph | +4.736 |
pu | +4.694 |
Neg logit contributions | |
yrinth | -12.066 |
ellar | -11.133 |
eleph | -10.501 |
Klux | -9.859 |
Doodle | -9.572 |
Token | Place |
Token ID | 8474 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
UCS | +7.531 |
py | +7.119 |
UTF | +7.070 |
osph | +7.057 |
pu | +6.763 |
Neg logit contributions | |
yrinth | -6.666 |
ellar | -6.432 |
queens | -5.045 |
BW | -5.029 |
Klux | -4.962 |
Token | f |
Token ID | 277 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
UCS | +6.410 |
py | +5.934 |
UTF | +5.905 |
pu | +5.634 |
osph | +5.287 |
Neg logit contributions | |
yrinth | -11.982 |
ellar | -11.714 |
BW | -9.805 |
Priv | -9.795 |
Doodle | -9.755 |
Token | rit |
Token ID | 799 |
Feature activation | -7.59e+00 |
Pos logit contributions | |
pu | +4.565 |
osph | +4.561 |
UTF | +4.522 |
py | +4.516 |
UCS | +4.237 |
Neg logit contributions | |
yrinth | -11.472 |
ellar | -11.204 |
eleph | -10.755 |
Doodle | -10.666 |
Balloon | -10.441 |
Token | t |
Token ID | 83 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
py | +7.216 |
pu | +6.901 |
UTF | +6.744 |
UCS | +6.708 |
osph | +6.629 |
Neg logit contributions | |
yrinth | -8.434 |
ellar | -7.951 |
Balloon | -6.948 |
Priv | -6.859 |
eleph | -6.857 |
Token | crowd |
Token ID | 4315 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
UCS | +2.282 |
UTF | +2.167 |
osph | +2.085 |
py | +2.067 |
�士 | +2.035 |
Neg logit contributions | |
ellar | -2.467 |
yrinth | -2.465 |
Balloon | -2.061 |
Priv | -2.058 |
Klux | -2.022 |
Token | the |
Token ID | 262 |
Feature activation | -9.13e+00 |
Pos logit contributions | |
UCS | +3.444 |
UTF | +3.205 |
py | +3.070 |
osph | +3.000 |
pu | +2.962 |
Neg logit contributions | |
yrinth | -4.085 |
ellar | -3.873 |
Klux | -3.290 |
Balloon | -3.240 |
Priv | -3.223 |
Token | pan |
Token ID | 3425 |
Feature activation | -5.24e+00 |
Pos logit contributions | |
UCS | +4.034 |
py | +3.734 |
UTF | +3.620 |
pu | +3.469 |
osph | +3.360 |
Neg logit contributions | |
yrinth | -9.397 |
ellar | -8.837 |
Doodle | -7.749 |
idav | -7.662 |
Klux | -7.657 |
Token | ; |
Token ID | 26 |
Feature activation | -7.56e+00 |
Pos logit contributions | |
UCS | +3.142 |
UTF | +2.984 |
py | +2.796 |
pu | +2.687 |
osph | +2.685 |
Neg logit contributions | |
yrinth | -4.564 |
ellar | -4.419 |
Klux | -3.738 |
Balloon | -3.715 |
queens | -3.660 |
Token | only |
Token ID | 691 |
Feature activation | -1.86e+01 |
Pos logit contributions | |
UCS | +5.812 |
UTF | +5.520 |
py | +5.518 |
osph | +5.338 |
pu | +5.298 |
Neg logit contributions | |
yrinth | -5.117 |
ellar | -4.838 |
Priv | -4.017 |
Klux | -3.969 |
Balloon | -3.940 |
Token | cook |
Token ID | 4255 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
py | +4.866 |
UTF | +4.608 |
osph | +4.476 |
UCS | +4.296 |
pu | +3.608 |
Neg logit contributions | |
yrinth | -19.620 |
ellar | -18.215 |
Priv | -16.611 |
Balloon | -16.536 |
BW | -16.368 |
Token | about |
Token ID | 546 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
UCS | +7.439 |
py | +7.179 |
UTF | +7.001 |
pu | +6.759 |
osph | +6.694 |
Neg logit contributions | |
yrinth | -8.374 |
ellar | -8.239 |
Balloon | -6.642 |
Doodle | -6.621 |
Priv | -6.580 |
Token | 3 |
Token ID | 513 |
Feature activation | -9.99e+00 |
Pos logit contributions | |
UCS | +3.412 |
UTF | +3.107 |
py | +2.966 |
pu | +2.832 |
osph | +2.768 |
Neg logit contributions | |
ellar | -5.374 |
yrinth | -5.346 |
Klux | -4.497 |
Priv | -4.473 |
Doodle | -4.401 |
Token | f |
Token ID | 277 |
Feature activation | -1.29e+01 |
Pos logit contributions | |
UCS | +5.356 |
UTF | +5.043 |
py | +5.011 |
pu | +4.799 |
osph | +4.619 |
Neg logit contributions | |
yrinth | -8.949 |
ellar | -8.723 |
Doodle | -7.495 |
Priv | -7.349 |
BW | -7.312 |
Token | rit |
Token ID | 799 |
Feature activation | -6.33e+00 |
Pos logit contributions | |
py | +5.109 |
pu | +5.105 |
UTF | +4.992 |
osph | +4.892 |
UCS | +4.643 |
Neg logit contributions | |
yrinth | -12.297 |
ellar | -12.032 |
eleph | -11.619 |
Doodle | -11.515 |
Balloon | -11.256 |
Token | ED |
Token ID | 1961 |
Feature activation | -9.51e-01 |
Pos logit contributions | |
UCS | +0.422 |
UTF | +0.405 |
�士 | +0.394 |
osph | +0.377 |
py | +0.375 |
Neg logit contributions | |
yrinth | -0.474 |
ellar | -0.473 |
Priv | -0.398 |
Klux | -0.395 |
Balloon | -0.394 |
Token | NET |
Token ID | 30502 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
UCS | +0.746 |
UTF | +0.720 |
�士 | +0.720 |
osph | +0.689 |
py | +0.677 |
Neg logit contributions | |
ellar | -0.634 |
yrinth | -0.623 |
Priv | -0.525 |
Balloon | -0.517 |
Klux | -0.509 |
Token | CALL |
Token ID | 42815 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
ellar | +3.093 |
yrinth | +2.807 |
Priv | +2.593 |
Balloon | +2.519 |
Doodle | +2.485 |
Neg logit contributions | |
�士 | -5.056 |
UCS | -4.920 |
UTF | -4.857 |
osph | -4.806 |
py | -4.586 |
Token | UPDATE |
Token ID | 35717 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
UCS | +0.459 |
UTF | +0.442 |
�士 | +0.442 |
osph | +0.422 |
py | +0.414 |
Neg logit contributions | |
ellar | -0.466 |
yrinth | -0.458 |
Priv | -0.392 |
Balloon | -0.387 |
Klux | -0.383 |
Token | : |
Token ID | 25 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
UCS | +2.630 |
UTF | +2.472 |
py | +2.273 |
�士 | +2.214 |
osph | +2.208 |
Neg logit contributions | |
yrinth | -3.321 |
ellar | -3.228 |
Klux | -2.740 |
Balloon | -2.656 |
Priv | -2.653 |
Token | 05 |
Token ID | 8870 |
Feature activation | -1.68e+01 |
Pos logit contributions | |
UCS | +0.926 |
UTF | +0.890 |
�士 | +0.888 |
osph | +0.847 |
py | +0.834 |
Neg logit contributions | |
ellar | -0.868 |
yrinth | -0.854 |
Priv | -0.720 |
Balloon | -0.710 |
Klux | -0.705 |
Token | 50 |
Token ID | 1120 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
UCS | +5.730 |
UTF | +5.686 |
py | +5.415 |
pu | +5.077 |
� | +4.642 |
Neg logit contributions | |
yrinth | -16.826 |
ellar | -15.796 |
vernment | -14.517 |
intrusion | -14.323 |
Klux | -14.222 |
Token | z |
Token ID | 89 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
UCS | +0.999 |
UTF | +0.956 |
�士 | +0.927 |
osph | +0.905 |
py | +0.900 |
Neg logit contributions | |
ellar | -1.154 |
yrinth | -1.147 |
Priv | -0.975 |
Balloon | -0.967 |
Klux | -0.962 |
Token | VOL |
Token ID | 38570 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ellar | +0.911 |
yrinth | +0.889 |
Priv | +0.777 |
Balloon | +0.758 |
BW | +0.745 |
Neg logit contributions | |
UCS | -0.994 |
�士 | -0.980 |
UTF | -0.974 |
osph | -0.934 |
py | -0.908 |
Token | UN |
Token ID | 4944 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
UCS | +1.144 |
UTF | +1.102 |
�士 | +1.095 |
osph | +1.047 |
py | +1.035 |
Neg logit contributions | |
ellar | -0.973 |
yrinth | -0.959 |
Priv | -0.795 |
Balloon | -0.784 |
Klux | -0.779 |
Token | TE |
Token ID | 9328 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
UCS | +1.040 |
UTF | +0.990 |
�士 | +0.988 |
osph | +0.932 |
py | +0.912 |
Neg logit contributions | |
ellar | -1.432 |
yrinth | -1.412 |
Priv | -1.228 |
Balloon | -1.214 |
Klux | -1.209 |
Token | Le |
Token ID | 1004 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
ellar | +0.727 |
yrinth | +0.707 |
Priv | +0.611 |
Balloon | +0.603 |
Doodle | +0.590 |
Neg logit contributions | |
UCS | -0.842 |
�士 | -0.837 |
UTF | -0.820 |
osph | -0.789 |
py | -0.770 |
Token | a |
Token ID | 64 |
Feature activation | -6.22e+00 |
Pos logit contributions | |
UCS | +0.115 |
UTF | +0.111 |
�士 | +0.109 |
osph | +0.106 |
py | +0.105 |
Neg logit contributions | |
ellar | -0.082 |
yrinth | -0.081 |
Priv | -0.066 |
Balloon | -0.065 |
Klux | -0.064 |
Token | Suzuki |
Token ID | 35807 |
Feature activation | -4.72e+00 |
Pos logit contributions | |
UCS | +3.048 |
UTF | +2.628 |
py | +2.432 |
osph | +2.357 |
�士 | +2.322 |
Neg logit contributions | |
yrinth | -6.187 |
ellar | -6.109 |
Klux | -5.253 |
BW | -5.209 |
apor | -5.179 |
Token | , |
Token ID | 11 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
UCS | +3.176 |
UTF | +2.968 |
py | +2.803 |
osph | +2.711 |
pu | +2.654 |
Neg logit contributions | |
yrinth | -3.885 |
ellar | -3.757 |
Klux | -3.181 |
Priv | -3.062 |
Balloon | -3.048 |
Token | The |
Token ID | 383 |
Feature activation | -6.07e+00 |
Pos logit contributions | |
UCS | +3.675 |
UTF | +3.316 |
py | +3.149 |
osph | +3.048 |
pu | +3.007 |
Neg logit contributions | |
yrinth | -4.677 |
ellar | -4.505 |
Klux | -3.843 |
queens | -3.738 |
intrusion | -3.681 |
Token | Chronicle |
Token ID | 14160 |
Feature activation | -1.63e+01 |
Pos logit contributions | |
UCS | +3.538 |
UTF | +3.197 |
py | +2.956 |
osph | +2.893 |
�士 | +2.839 |
Neg logit contributions | |
yrinth | -5.440 |
ellar | -5.290 |
Klux | -4.540 |
Balloon | -4.443 |
Priv | -4.441 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
UCS | +6.505 |
UTF | +5.199 |
py | +4.810 |
pu | +4.212 |
osph | +4.124 |
Neg logit contributions | |
yrinth | -16.989 |
ellar | -16.261 |
eleph | -14.757 |
Klux | -14.067 |
eatures | -13.808 |
Token | of |
Token ID | 286 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
ellar | +0.993 |
yrinth | +0.974 |
Priv | +0.820 |
Balloon | +0.808 |
Klux | +0.802 |
Neg logit contributions | |
UCS | -1.108 |
�士 | -1.070 |
UTF | -1.066 |
osph | -1.016 |
py | -0.999 |
Token | 15 |
Token ID | 1315 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
UCS | +3.115 |
UTF | +2.959 |
�士 | +2.776 |
py | +2.761 |
osph | +2.759 |
Neg logit contributions | |
yrinth | -2.685 |
ellar | -2.622 |
Doodle | -2.094 |
Klux | -2.084 |
Priv | -2.083 |
Token | Photo |
Token ID | 5555 |
Feature activation | -8.10e+00 |
Pos logit contributions | |
UCS | +2.629 |
UTF | +2.474 |
py | +2.357 |
osph | +2.342 |
�士 | +2.338 |
Neg logit contributions | |
yrinth | -2.338 |
ellar | -2.303 |
Klux | -1.860 |
BW | -1.812 |
Priv | -1.804 |
Token | : |
Token ID | 25 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
UCS | +4.538 |
UTF | +4.221 |
py | +3.958 |
pu | +3.856 |
� | +3.668 |
Neg logit contributions | |
yrinth | -7.553 |
ellar | -6.942 |
eleph | -6.189 |
Klux | -6.109 |
Balloon | -5.942 |
Token | together |
Token ID | 1978 |
Feature activation | -7.08e+00 |
Pos logit contributions | |
UCS | +4.502 |
UTF | +4.363 |
py | +4.087 |
osph | +4.057 |
pu | +3.990 |
Neg logit contributions | |
ellar | -3.848 |
yrinth | -3.836 |
Balloon | -3.120 |
Doodle | -3.112 |
Priv | -3.079 |
Token | . |
Token ID | 13 |
Feature activation | -9.17e+00 |
Pos logit contributions | |
UCS | +3.991 |
UTF | +3.760 |
py | +3.572 |
osph | +3.370 |
pu | +3.361 |
Neg logit contributions | |
yrinth | -6.398 |
ellar | -6.095 |
Klux | -5.332 |
Doodle | -5.167 |
Priv | -5.145 |
Token | 4 |
Token ID | 604 |
Feature activation | -7.29e+00 |
Pos logit contributions | |
UCS | +5.032 |
UTF | +4.787 |
py | +4.614 |
�士 | +4.587 |
osph | +4.418 |
Neg logit contributions | |
ellar | -8.024 |
yrinth | -7.880 |
Klux | -6.883 |
Balloon | -6.820 |
Priv | -6.797 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
UCS | +4.103 |
UTF | +3.950 |
py | +3.737 |
pu | +3.507 |
osph | +3.447 |
Neg logit contributions | |
yrinth | -6.669 |
ellar | -6.340 |
Klux | -5.511 |
eleph | -5.419 |
Doodle | -5.351 |
Token | Make |
Token ID | 6889 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
UCS | +7.320 |
UTF | +7.104 |
py | +6.902 |
�士 | +6.899 |
osph | +6.702 |
Neg logit contributions | |
ellar | -7.756 |
yrinth | -7.588 |
msec | -6.176 |
Klux | -6.155 |
queens | -6.109 |
Token | 6 |
Token ID | 718 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
UCS | +4.786 |
py | +4.109 |
UTF | +3.863 |
pu | +3.706 |
osph | +3.606 |
Neg logit contributions | |
ellar | -14.122 |
yrinth | -14.011 |
BW | -12.132 |
Klux | -11.991 |
Priv | -11.924 |
Token | p |
Token ID | 279 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
py | +5.075 |
UCS | +4.679 |
pu | +4.566 |
pi | +3.883 |
UTF | +3.868 |
Neg logit contributions | |
yrinth | -16.399 |
ellar | -15.921 |
BW | -13.949 |
eleph | -13.842 |
Klux | -13.749 |
Token | att |
Token ID | 1078 |
Feature activation | -7.95e+00 |
Pos logit contributions | |
UCS | +2.492 |
py | +2.385 |
UTF | +2.372 |
osph | +2.348 |
pu | +2.333 |
Neg logit contributions | |
yrinth | -3.358 |
ellar | -3.324 |
Priv | -2.964 |
Doodle | -2.925 |
Balloon | -2.888 |
Token | ies |
Token ID | 444 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
UCS | +3.013 |
py | +2.908 |
UTF | +2.733 |
osph | +2.687 |
pu | +2.646 |
Neg logit contributions | |
yrinth | -8.148 |
ellar | -8.008 |
Priv | -7.164 |
Doodle | -7.112 |
Balloon | -7.075 |
Token | . |
Token ID | 13 |
Feature activation | -7.63e+00 |
Pos logit contributions | |
UCS | +2.136 |
UTF | +2.013 |
py | +1.899 |
osph | +1.871 |
�士 | +1.850 |
Neg logit contributions | |
yrinth | -2.692 |
ellar | -2.682 |
Klux | -2.240 |
Priv | -2.229 |
Balloon | -2.210 |
Token | 5 |
Token ID | 642 |
Feature activation | -6.70e+00 |
Pos logit contributions | |
UCS | +5.060 |
UTF | +4.990 |
�士 | +4.806 |
osph | +4.722 |
py | +4.718 |
Neg logit contributions | |
ellar | -5.752 |
yrinth | -5.629 |
Klux | -4.750 |
Priv | -4.741 |
Balloon | -4.709 |
Token | not |
Token ID | 407 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
UCS | +4.485 |
UTF | +4.205 |
py | +4.145 |
osph | +4.048 |
pu | +3.841 |
Neg logit contributions | |
yrinth | -6.393 |
ellar | -6.282 |
Klux | -5.487 |
Priv | -5.390 |
Balloon | -5.320 |
Token | deep |
Token ID | 2769 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
ellar | +3.199 |
yrinth | +3.161 |
drag | +2.662 |
Priv | +2.625 |
--------- | +2.603 |
Neg logit contributions | |
�士 | -4.323 |
UCS | -4.148 |
UTF | -4.016 |
osph | -3.932 |
py | -3.762 |
Token | fried |
Token ID | 23018 |
Feature activation | -8.64e+00 |
Pos logit contributions | |
UCS | +4.500 |
UTF | +4.155 |
py | +4.131 |
osph | +3.850 |
pu | +3.796 |
Neg logit contributions | |
yrinth | -9.758 |
ellar | -9.608 |
Priv | -8.382 |
Balloon | -8.305 |
Doodle | -8.163 |
Token | . |
Token ID | 13 |
Feature activation | -6.00e+00 |
Pos logit contributions | |
UCS | +4.601 |
UTF | +4.346 |
py | +4.139 |
osph | +3.925 |
pu | +3.855 |
Neg logit contributions | |
yrinth | -7.842 |
ellar | -7.562 |
Klux | -6.542 |
Priv | -6.431 |
Doodle | -6.413 |
Token | 6 |
Token ID | 718 |
Feature activation | -6.43e+00 |
Pos logit contributions | |
UCS | +3.510 |
UTF | +3.348 |
�士 | +3.273 |
py | +3.150 |
osph | +3.141 |
Neg logit contributions | |
ellar | -5.157 |
yrinth | -5.086 |
Klux | -4.378 |
Priv | -4.363 |
Balloon | -4.357 |
Token | . |
Token ID | 13 |
Feature activation | -1.53e+01 |
Pos logit contributions | |
UCS | +3.768 |
UTF | +3.628 |
py | +3.390 |
pu | +3.232 |
osph | +3.212 |
Neg logit contributions | |
yrinth | -5.724 |
ellar | -5.514 |
Klux | -4.748 |
Balloon | -4.646 |
Doodle | -4.632 |
Token | Drain |
Token ID | 36024 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
UCS | +6.436 |
UTF | +6.061 |
py | +5.432 |
osph | +5.317 |
pu | +5.082 |
Neg logit contributions | |
yrinth | -14.298 |
ellar | -14.072 |
Klux | -12.340 |
hoops | -12.273 |
eleph | -12.166 |
Token | on |
Token ID | 319 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
UCS | +0.555 |
UTF | +0.528 |
�士 | +0.520 |
osph | +0.497 |
py | +0.489 |
Neg logit contributions | |
ellar | -0.724 |
yrinth | -0.715 |
Priv | -0.615 |
Balloon | -0.609 |
Klux | -0.608 |
Token | a |
Token ID | 257 |
Feature activation | -7.08e+00 |
Pos logit contributions | |
UCS | +0.751 |
UTF | +0.718 |
�士 | +0.698 |
osph | +0.681 |
py | +0.678 |
Neg logit contributions | |
ellar | -0.669 |
yrinth | -0.666 |
Priv | -0.547 |
Balloon | -0.542 |
Klux | -0.541 |
Token | paper |
Token ID | 3348 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
UCS | +5.453 |
UTF | +5.051 |
py | +4.966 |
osph | +4.847 |
pu | +4.820 |
Neg logit contributions | |
yrinth | -5.031 |
ellar | -4.756 |
BW | -3.827 |
Priv | -3.809 |
Klux | -3.803 |
Token | towel |
Token ID | 24808 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
UCS | +3.232 |
UTF | +3.055 |
�士 | +2.930 |
py | +2.926 |
osph | +2.921 |
Neg logit contributions | |
yrinth | -3.088 |
ellar | -3.060 |
Priv | -2.517 |
Balloon | -2.487 |
Klux | -2.484 |
Token | ? |
Token ID | 30 |
Feature activation | -6.25e+00 |
Pos logit contributions | |
UCS | +1.164 |
UTF | +1.117 |
py | +1.043 |
osph | +1.036 |
�士 | +1.030 |
Neg logit contributions | |
yrinth | -1.359 |
ellar | -1.353 |
Klux | -1.130 |
Balloon | -1.129 |
Priv | -1.114 |
Token | No |
Token ID | 1400 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
UCS | +4.035 |
UTF | +3.711 |
py | +3.602 |
pu | +3.476 |
osph | +3.377 |
Neg logit contributions | |
yrinth | -5.268 |
ellar | -5.065 |
Klux | -4.341 |
queens | -4.130 |
BW | -4.127 |
Token | more |
Token ID | 517 |
Feature activation | -7.31e+00 |
Pos logit contributions | |
UCS | +3.301 |
UTF | +3.001 |
py | +2.891 |
osph | +2.888 |
pu | +2.781 |
Neg logit contributions | |
yrinth | -4.411 |
ellar | -4.226 |
Balloon | -3.640 |
Klux | -3.597 |
Priv | -3.591 |
Token | bad |
Token ID | 2089 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
UCS | +3.480 |
py | +3.137 |
UTF | +3.003 |
pu | +2.966 |
bul | +2.830 |
Neg logit contributions | |
yrinth | -7.227 |
ellar | -6.976 |
Balloon | -6.097 |
Klux | -6.057 |
idav | -6.013 |
Token | news |
Token ID | 1705 |
Feature activation | -8.82e+00 |
Pos logit contributions | |
UCS | +1.456 |
UTF | +1.314 |
osph | +1.215 |
py | +1.197 |
�士 | +1.157 |
Neg logit contributions | |
yrinth | -3.206 |
ellar | -3.184 |
Balloon | -2.767 |
Klux | -2.759 |
Priv | -2.740 |
Token | pl |
Token ID | 458 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
UCS | +4.197 |
UTF | +3.759 |
py | +3.708 |
osph | +3.653 |
pu | +3.459 |
Neg logit contributions | |
yrinth | -8.396 |
ellar | -8.383 |
Klux | -7.137 |
Balloon | -7.120 |
Doodle | -7.045 |
Token | s |
Token ID | 82 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
py | +5.797 |
pu | +5.604 |
UCS | +5.485 |
UTF | +5.262 |
pi | +5.147 |
Neg logit contributions | |
yrinth | -14.946 |
ellar | -14.396 |
eleph | -14.368 |
Doodle | -13.329 |
conclud | -12.917 |
Token | . |
Token ID | 13 |
Feature activation | -7.94e+00 |
Pos logit contributions | |
UCS | +0.557 |
UTF | +0.533 |
�士 | +0.508 |
osph | +0.499 |
py | +0.498 |
Neg logit contributions | |
yrinth | -0.636 |
ellar | -0.635 |
Priv | -0.532 |
Klux | -0.530 |
Balloon | -0.529 |
Token | Writer |
Token ID | 26606 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
UCS | +6.028 |
UTF | +5.698 |
�士 | +5.539 |
py | +5.465 |
osph | +5.384 |
Neg logit contributions | |
ellar | -5.401 |
yrinth | -5.314 |
Klux | -4.327 |
--------- | -4.227 |
Priv | -4.217 |
Token | " |
Token ID | 366 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
ellar | +1.581 |
yrinth | +1.550 |
Priv | +1.323 |
Balloon | +1.305 |
BW | +1.289 |
Neg logit contributions | |
UCS | -1.754 |
�士 | -1.725 |
UTF | -1.697 |
osph | -1.625 |
py | -1.594 |
Token | I |
Token ID | 40 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
UCS | +1.465 |
UTF | +1.414 |
�士 | +1.399 |
osph | +1.340 |
py | +1.326 |
Neg logit contributions | |
ellar | -1.400 |
yrinth | -1.379 |
Priv | -1.162 |
Balloon | -1.142 |
Klux | -1.141 |
Token | . |
Token ID | 13 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
UCS | +2.335 |
UTF | +2.207 |
py | +2.079 |
osph | +2.069 |
pu | +1.992 |
Neg logit contributions | |
yrinth | -3.035 |
ellar | -2.999 |
Balloon | -2.526 |
Priv | -2.518 |
Klux | -2.518 |
Token | 3 |
Token ID | 513 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
UCS | +2.096 |
UTF | +2.019 |
�士 | +2.005 |
osph | +1.913 |
py | +1.895 |
Neg logit contributions | |
ellar | -2.046 |
yrinth | -2.007 |
Priv | -1.692 |
Balloon | -1.672 |
Klux | -1.670 |
Token | . |
Token ID | 13 |
Feature activation | -9.99e+00 |
Pos logit contributions | |
UCS | +2.493 |
UTF | +2.400 |
py | +2.247 |
osph | +2.185 |
pu | +2.144 |
Neg logit contributions | |
yrinth | -3.327 |
ellar | -3.249 |
Klux | -2.757 |
Priv | -2.722 |
Balloon | -2.718 |
Token | In |
Token ID | 554 |
Feature activation | -8.75e+00 |
Pos logit contributions | |
UCS | +5.916 |
UTF | +5.593 |
�士 | +5.414 |
py | +5.379 |
osph | +5.352 |
Neg logit contributions | |
ellar | -8.357 |
yrinth | -8.242 |
msec | -6.898 |
Klux | -6.861 |
queens | -6.816 |
Token | a |
Token ID | 257 |
Feature activation | -9.92e+00 |
Pos logit contributions | |
UCS | +5.385 |
UTF | +5.000 |
py | +4.868 |
pu | +4.675 |
osph | +4.663 |
Neg logit contributions | |
yrinth | -7.223 |
ellar | -7.000 |
Doodle | -5.894 |
Priv | -5.862 |
BW | -5.771 |
Token | large |
Token ID | 1588 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
UCS | +4.197 |
UTF | +3.708 |
py | +3.364 |
pu | +3.190 |
osph | +3.137 |
Neg logit contributions | |
yrinth | -10.394 |
ellar | -10.169 |
Doodle | -9.089 |
Priv | -8.866 |
BW | -8.697 |
Token | bowl |
Token ID | 9396 |
Feature activation | -7.85e+00 |
Pos logit contributions | |
UCS | +7.063 |
UTF | +6.952 |
py | +6.243 |
pu | +6.153 |
osph | +6.037 |
Neg logit contributions | |
yrinth | -14.285 |
ellar | -13.236 |
Doodle | -11.498 |
eleph | -11.418 |
Priv | -11.268 |
Token | , |
Token ID | 11 |
Feature activation | -1.26e+01 |
Pos logit contributions | |
UCS | +4.692 |
UTF | +4.404 |
py | +4.367 |
osph | +4.239 |
pu | +4.099 |
Neg logit contributions | |
yrinth | -6.612 |
ellar | -6.357 |
Klux | -5.421 |
Balloon | -5.383 |
Priv | -5.382 |
Token | combine |
Token ID | 12082 |
Feature activation | -8.92e+00 |
Pos logit contributions | |
UCS | +3.721 |
osph | +3.357 |
UTF | +3.344 |
py | +3.224 |
pu | +2.906 |
Neg logit contributions | |
ellar | -13.713 |
yrinth | -13.699 |
Priv | -11.991 |
Balloon | -11.831 |
Doodle | -11.716 |
Token | the |
Token ID | 262 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
UCS | +5.625 |
UTF | +5.061 |
py | +4.862 |
osph | +4.755 |
pu | +4.676 |
Neg logit contributions | |
yrinth | -7.489 |
ellar | -7.109 |
Priv | -6.040 |
Balloon | -5.954 |
BW | -5.933 |
Token | broccoli |
Token ID | 44653 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
UCS | +2.263 |
UTF | +1.514 |
py | +1.188 |
pu | +0.882 |
broccoli | +0.782 |
Neg logit contributions | |
yrinth | -18.902 |
ellar | -18.346 |
Doodle | -16.595 |
Priv | -16.439 |
IFT | -16.133 |
Token | ters |
Token ID | 1010 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
UCS | +4.374 |
UTF | +4.154 |
py | +4.101 |
osph | +4.039 |
pu | +3.946 |
Neg logit contributions | |
yrinth | -4.764 |
ellar | -4.719 |
Balloon | -4.000 |
Priv | -3.963 |
Doodle | -3.879 |
Token | at |
Token ID | 379 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
UCS | +3.615 |
py | +3.373 |
UTF | +3.372 |
osph | +3.192 |
pu | +3.154 |
Neg logit contributions | |
yrinth | -4.720 |
ellar | -4.585 |
Klux | -3.926 |
Doodle | -3.890 |
Priv | -3.853 |
Token | a |
Token ID | 257 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
UCS | +1.256 |
UTF | +1.200 |
py | +1.139 |
�士 | +1.130 |
osph | +1.126 |
Neg logit contributions | |
yrinth | -1.220 |
ellar | -1.212 |
Priv | -0.992 |
Klux | -0.987 |
Balloon | -0.981 |
Token | time |
Token ID | 640 |
Feature activation | -5.18e+00 |
Pos logit contributions | |
UCS | +2.455 |
UTF | +2.331 |
py | +2.271 |
osph | +2.259 |
pu | +2.173 |
Neg logit contributions | |
yrinth | -2.275 |
ellar | -2.250 |
Priv | -1.837 |
Klux | -1.806 |
Balloon | -1.802 |
Token | ), |
Token ID | 828 |
Feature activation | -9.34e+00 |
Pos logit contributions | |
UCS | +2.952 |
UTF | +2.734 |
osph | +2.627 |
py | +2.538 |
pu | +2.451 |
Neg logit contributions | |
yrinth | -4.581 |
ellar | -4.535 |
Priv | -3.934 |
Klux | -3.878 |
BW | -3.857 |
Token | reduce |
Token ID | 4646 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
UCS | +4.125 |
UTF | +3.828 |
osph | +3.810 |
py | +3.668 |
pu | +3.414 |
Neg logit contributions | |
yrinth | -9.333 |
ellar | -9.267 |
Balloon | -8.105 |
BW | -8.100 |
Klux | -8.070 |
Token | heat |
Token ID | 4894 |
Feature activation | -8.89e+00 |
Pos logit contributions | |
UCS | +3.884 |
UTF | +3.486 |
py | +3.477 |
osph | +3.189 |
pu | +2.862 |
Neg logit contributions | |
yrinth | -17.603 |
ellar | -16.449 |
Doodle | -14.880 |
idav | -14.648 |
Balloon | -14.491 |
Token | to |
Token ID | 284 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
UCS | +4.904 |
UTF | +4.506 |
py | +4.368 |
osph | +4.173 |
pu | +4.137 |
Neg logit contributions | |
yrinth | -8.209 |
ellar | -7.783 |
Klux | -6.698 |
Balloon | -6.598 |
Doodle | -6.597 |
Token | low |
Token ID | 1877 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
UCS | +2.651 |
UTF | +2.458 |
py | +2.333 |
osph | +2.314 |
pu | +2.212 |
Neg logit contributions | |
yrinth | -4.475 |
ellar | -4.470 |
Priv | -3.840 |
Doodle | -3.837 |
Balloon | -3.800 |
Token | and |
Token ID | 290 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
UCS | +3.344 |
UTF | +3.137 |
py | +3.010 |
osph | +2.895 |
pu | +2.874 |
Neg logit contributions | |
yrinth | -4.535 |
ellar | -4.421 |
Klux | -3.734 |
Balloon | -3.708 |
Doodle | -3.706 |
Token | cook |
Token ID | 4255 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
UCS | +4.509 |
py | +4.431 |
osph | +4.352 |
UTF | +4.352 |
pu | +3.741 |
Neg logit contributions | |
yrinth | -15.154 |
ellar | -14.620 |
Priv | -13.302 |
BW | -13.029 |
Balloon | -12.993 |
Token | ? |
Token ID | 30 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
UCS | +1.916 |
UTF | +1.846 |
py | +1.701 |
pu | +1.661 |
osph | +1.657 |
Neg logit contributions | |
yrinth | -2.441 |
ellar | -2.396 |
Klux | -2.020 |
Balloon | -2.006 |
Priv | -1.966 |
Token | No |
Token ID | 1400 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
UCS | +3.205 |
UTF | +2.991 |
py | +2.848 |
pu | +2.735 |
osph | +2.712 |
Neg logit contributions | |
yrinth | -3.866 |
ellar | -3.731 |
Klux | -3.170 |
BW | -3.036 |
queens | -3.026 |
Token | more |
Token ID | 517 |
Feature activation | -7.03e+00 |
Pos logit contributions | |
UCS | +2.138 |
UTF | +1.989 |
osph | +1.883 |
py | +1.881 |
pu | +1.800 |
Neg logit contributions | |
yrinth | -2.529 |
ellar | -2.458 |
Balloon | -2.104 |
Priv | -2.071 |
Klux | -2.063 |
Token | bad |
Token ID | 2089 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
UCS | +3.367 |
py | +2.979 |
UTF | +2.921 |
pu | +2.812 |
bul | +2.775 |
Neg logit contributions | |
yrinth | -6.918 |
ellar | -6.619 |
Balloon | -5.839 |
Klux | -5.812 |
idav | -5.711 |
Token | news |
Token ID | 1705 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
UCS | +0.424 |
UTF | +0.393 |
�士 | +0.372 |
osph | +0.363 |
py | +0.357 |
Neg logit contributions | |
ellar | -0.831 |
yrinth | -0.828 |
Balloon | -0.718 |
Priv | -0.717 |
Klux | -0.714 |
Token | pl |
Token ID | 458 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
UCS | +4.648 |
UTF | +4.181 |
py | +4.035 |
osph | +4.028 |
pu | +3.781 |
Neg logit contributions | |
yrinth | -9.957 |
ellar | -9.789 |
Klux | -8.429 |
Doodle | -8.391 |
Balloon | -8.363 |
Token | s |
Token ID | 82 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
py | +5.789 |
UTF | +5.412 |
pu | +5.389 |
UCS | +5.367 |
pi | +4.926 |
Neg logit contributions | |
yrinth | -14.801 |
eleph | -14.253 |
ellar | -14.127 |
Doodle | -13.153 |
conclud | -12.797 |
Token | . |
Token ID | 13 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
UCS | +1.517 |
UTF | +1.448 |
py | +1.350 |
osph | +1.332 |
�士 | +1.325 |
Neg logit contributions | |
yrinth | -1.876 |
ellar | -1.848 |
Klux | -1.558 |
Balloon | -1.541 |
Priv | -1.537 |
Token |
|
Token ID | 198 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
UCS | +2.294 |
UTF | +2.204 |
�士 | +2.187 |
osph | +2.088 |
py | +2.071 |
Neg logit contributions | |
ellar | -2.075 |
yrinth | -2.040 |
Priv | -1.699 |
Klux | -1.682 |
Balloon | -1.677 |
Token |
|
Token ID | 198 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
UCS | +0.620 |
UTF | +0.595 |
�士 | +0.569 |
py | +0.561 |
osph | +0.559 |
Neg logit contributions | |
yrinth | -0.602 |
ellar | -0.601 |
Priv | -0.496 |
Klux | -0.495 |
Balloon | -0.492 |
Token | Good |
Token ID | 10248 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
UCS | +0.977 |
UTF | +0.938 |
�士 | +0.936 |
osph | +0.892 |
py | +0.878 |
Neg logit contributions | |
ellar | -0.921 |
yrinth | -0.906 |
Priv | -0.763 |
Balloon | -0.752 |
Klux | -0.749 |
Token | a |
Token ID | 257 |
Feature activation | -9.92e+00 |
Pos logit contributions | |
UCS | +5.385 |
UTF | +5.000 |
py | +4.868 |
pu | +4.675 |
osph | +4.663 |
Neg logit contributions | |
yrinth | -7.223 |
ellar | -7.000 |
Doodle | -5.894 |
Priv | -5.862 |
BW | -5.771 |
Token | large |
Token ID | 1588 |
Feature activation | -1.52e+01 |
Pos logit contributions | |
UCS | +4.197 |
UTF | +3.708 |
py | +3.364 |
pu | +3.190 |
osph | +3.137 |
Neg logit contributions | |
yrinth | -10.394 |
ellar | -10.169 |
Doodle | -9.089 |
Priv | -8.866 |
BW | -8.697 |
Token | bowl |
Token ID | 9396 |
Feature activation | -7.85e+00 |
Pos logit contributions | |
UCS | +7.063 |
UTF | +6.952 |
py | +6.243 |
pu | +6.153 |
osph | +6.037 |
Neg logit contributions | |
yrinth | -14.285 |
ellar | -13.236 |
Doodle | -11.498 |
eleph | -11.418 |
Priv | -11.268 |
Token | , |
Token ID | 11 |
Feature activation | -1.26e+01 |
Pos logit contributions | |
UCS | +4.692 |
UTF | +4.404 |
py | +4.367 |
osph | +4.239 |
pu | +4.099 |
Neg logit contributions | |
yrinth | -6.612 |
ellar | -6.357 |
Klux | -5.421 |
Balloon | -5.383 |
Priv | -5.382 |
Token | combine |
Token ID | 12082 |
Feature activation | -8.92e+00 |
Pos logit contributions | |
UCS | +3.721 |
osph | +3.357 |
UTF | +3.344 |
py | +3.224 |
pu | +2.906 |
Neg logit contributions | |
ellar | -13.713 |
yrinth | -13.699 |
Priv | -11.991 |
Balloon | -11.831 |
Doodle | -11.716 |
Token | the |
Token ID | 262 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
UCS | +5.625 |
UTF | +5.061 |
py | +4.862 |
osph | +4.755 |
pu | +4.676 |
Neg logit contributions | |
yrinth | -7.489 |
ellar | -7.109 |
Priv | -6.040 |
Balloon | -5.954 |
BW | -5.933 |
Token | broccoli |
Token ID | 44653 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
UCS | +2.263 |
UTF | +1.514 |
py | +1.188 |
pu | +0.882 |
broccoli | +0.782 |
Neg logit contributions | |
yrinth | -18.902 |
ellar | -18.346 |
Doodle | -16.595 |
Priv | -16.439 |
IFT | -16.133 |
Token | pieces |
Token ID | 5207 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
UCS | +7.793 |
UTF | +6.964 |
py | +6.868 |
pu | +6.620 |
osph | +6.598 |
Neg logit contributions | |
yrinth | -9.113 |
ellar | -8.815 |
Balloon | -7.327 |
Doodle | -7.318 |
BW | -7.185 |
Token | with |
Token ID | 351 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
UCS | +5.400 |
py | +4.776 |
UTF | +4.560 |
osph | +4.458 |
pu | +4.351 |
Neg logit contributions | |
yrinth | -10.492 |
ellar | -10.286 |
Doodle | -8.930 |
Klux | -8.717 |
Priv | -8.688 |
Token | all |
Token ID | 477 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
UCS | +3.529 |
UTF | +3.244 |
py | +3.063 |
osph | +2.997 |
pu | +2.928 |
Neg logit contributions | |
yrinth | -4.878 |
ellar | -4.791 |
Klux | -4.077 |
Priv | -4.056 |
Doodle | -4.056 |
Token | the |
Token ID | 262 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
UCS | +4.174 |
UTF | +3.865 |
py | +3.711 |
osph | +3.608 |
pu | +3.529 |
Neg logit contributions | |
yrinth | -5.277 |
ellar | -4.989 |
Klux | -4.288 |
Balloon | -4.211 |
BW | -4.178 |
Token | . |
Token ID | 764 |
Feature activation | +5.85e+00 |
Pos logit contributions | |
ellar | +4.037 |
yrinth | +3.677 |
Priv | +3.410 |
drag | +3.322 |
[_ | +3.276 |
Neg logit contributions | |
�士 | -6.266 |
UCS | -5.770 |
UTF | -5.660 |
osph | -5.561 |
py | -5.203 |
Token | normal |
Token ID | 3487 |
Feature activation | +6.38e+00 |
Pos logit contributions | |
ellar | +3.672 |
yrinth | +3.665 |
drag | +3.084 |
Priv | +3.002 |
Balloon | +2.936 |
Neg logit contributions | |
UCS | -4.525 |
UTF | -4.501 |
�士 | -4.435 |
osph | -4.262 |
� | -4.127 |
Token | * |
Token ID | 1635 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
ellar | +2.963 |
yrinth | +2.738 |
Priv | +2.321 |
drag | +2.295 |
BW | +2.252 |
Neg logit contributions | |
�士 | -6.291 |
UCS | -6.017 |
UTF | -5.883 |
osph | -5.734 |
py | -5.467 |
Token | 1 |
Token ID | 352 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
UCS | +2.214 |
UTF | +2.092 |
osph | +1.991 |
py | +1.977 |
�士 | +1.962 |
Neg logit contributions | |
ellar | -2.333 |
yrinth | -2.329 |
Priv | -1.916 |
Klux | -1.911 |
Balloon | -1.904 |
Token | ; |
Token ID | 2162 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
ellar | +1.572 |
yrinth | +1.528 |
Priv | +1.285 |
Balloon | +1.254 |
Klux | +1.237 |
Neg logit contributions | |
UCS | -2.067 |
�士 | -2.031 |
UTF | -2.000 |
osph | -1.922 |
py | -1.880 |
Token | } |
Token ID | 1782 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
UCS | +0.239 |
UTF | +0.227 |
�士 | +0.223 |
osph | +0.214 |
py | +0.213 |
Neg logit contributions | |
ellar | -0.262 |
yrinth | -0.260 |
Priv | -0.220 |
Klux | -0.218 |
Balloon | -0.217 |
Token |
|
Token ID | 198 |
Feature activation | -6.34e+00 |
Pos logit contributions | |
UCS | +8.225 |
py | +7.560 |
UTF | +7.507 |
osph | +7.131 |
�士 | +6.759 |
Neg logit contributions | |
yrinth | -11.804 |
ellar | -11.714 |
Klux | -10.254 |
Balloon | -9.985 |
BW | -9.871 |
Token |
|
Token ID | 198 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
UCS | +3.957 |
UTF | +3.760 |
py | +3.659 |
pu | +3.432 |
osph | +3.370 |
Neg logit contributions | |
yrinth | -5.442 |
ellar | -5.164 |
Klux | -4.497 |
eleph | -4.434 |
Doodle | -4.370 |
Token | The |
Token ID | 464 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
UCS | +3.365 |
UTF | +3.292 |
�士 | +3.162 |
py | +3.105 |
osph | +3.080 |
Neg logit contributions | |
ellar | -3.623 |
yrinth | -3.568 |
Priv | -3.047 |
Balloon | -3.027 |
Klux | -2.991 |
Token | result |
Token ID | 1255 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
UCS | +2.196 |
UTF | +2.094 |
�士 | +2.081 |
osph | +2.000 |
py | +1.982 |
Neg logit contributions | |
ellar | -1.912 |
yrinth | -1.879 |
Priv | -1.555 |
Klux | -1.543 |
Balloon | -1.538 |
Token | pushes |
Token ID | 20070 |
Feature activation | -7.53e+00 |
Pos logit contributions | |
ellar | +1.091 |
yrinth | +1.067 |
Priv | +0.898 |
Balloon | +0.889 |
--------- | +0.875 |
Neg logit contributions | |
UCS | -1.295 |
�士 | -1.276 |
UTF | -1.251 |
osph | -1.197 |
py | -1.162 |
Token | ), |
Token ID | 828 |
Feature activation | -9.34e+00 |
Pos logit contributions | |
UCS | +2.952 |
UTF | +2.734 |
osph | +2.627 |
py | +2.538 |
pu | +2.451 |
Neg logit contributions | |
yrinth | -4.581 |
ellar | -4.535 |
Priv | -3.934 |
Klux | -3.878 |
BW | -3.857 |
Token | reduce |
Token ID | 4646 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
UCS | +4.125 |
UTF | +3.828 |
osph | +3.810 |
py | +3.668 |
pu | +3.414 |
Neg logit contributions | |
yrinth | -9.333 |
ellar | -9.267 |
Balloon | -8.105 |
BW | -8.100 |
Klux | -8.070 |
Token | heat |
Token ID | 4894 |
Feature activation | -8.89e+00 |
Pos logit contributions | |
UCS | +3.884 |
UTF | +3.486 |
py | +3.477 |
osph | +3.189 |
pu | +2.862 |
Neg logit contributions | |
yrinth | -17.603 |
ellar | -16.449 |
Doodle | -14.880 |
idav | -14.648 |
Balloon | -14.491 |
Token | to |
Token ID | 284 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
UCS | +4.904 |
UTF | +4.506 |
py | +4.368 |
osph | +4.173 |
pu | +4.137 |
Neg logit contributions | |
yrinth | -8.209 |
ellar | -7.783 |
Klux | -6.698 |
Balloon | -6.598 |
Doodle | -6.597 |
Token | low |
Token ID | 1877 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
UCS | +2.651 |
UTF | +2.458 |
py | +2.333 |
osph | +2.314 |
pu | +2.212 |
Neg logit contributions | |
yrinth | -4.475 |
ellar | -4.470 |
Priv | -3.840 |
Doodle | -3.837 |
Balloon | -3.800 |
Token | and |
Token ID | 290 |
Feature activation | -1.49e+01 |
Pos logit contributions | |
UCS | +3.344 |
UTF | +3.137 |
py | +3.010 |
osph | +2.895 |
pu | +2.874 |
Neg logit contributions | |
yrinth | -4.535 |
ellar | -4.421 |
Klux | -3.734 |
Balloon | -3.708 |
Doodle | -3.706 |
Token | cook |
Token ID | 4255 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
UCS | +4.509 |
py | +4.431 |
osph | +4.352 |
UTF | +4.352 |
pu | +3.741 |
Neg logit contributions | |
yrinth | -15.154 |
ellar | -14.620 |
Priv | -13.302 |
BW | -13.029 |
Balloon | -12.993 |
Token | f |
Token ID | 277 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
UCS | +6.434 |
py | +6.043 |
UTF | +5.974 |
pu | +5.569 |
osph | +5.399 |
Neg logit contributions | |
yrinth | -12.708 |
ellar | -12.326 |
Priv | -10.518 |
Doodle | -10.419 |
BW | -10.392 |
Token | rit |
Token ID | 799 |
Feature activation | -6.50e+00 |
Pos logit contributions | |
UTF | +4.630 |
py | +4.616 |
pu | +4.589 |
osph | +4.545 |
UCS | +4.362 |
Neg logit contributions | |
yrinth | -11.328 |
ellar | -11.082 |
eleph | -10.629 |
Doodle | -10.513 |
Balloon | -10.399 |
Token | ters |
Token ID | 1010 |
Feature activation | -7.74e+00 |
Pos logit contributions | |
UCS | +4.521 |
UTF | +4.290 |
py | +4.218 |
osph | +4.167 |
pu | +4.056 |
Neg logit contributions | |
yrinth | -4.814 |
ellar | -4.779 |
Balloon | -4.081 |
Priv | -4.042 |
BW | -3.932 |
Token | on |
Token ID | 319 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
UCS | +3.786 |
UTF | +3.471 |
py | +3.453 |
pu | +3.191 |
osph | +3.191 |
Neg logit contributions | |
yrinth | -7.432 |
ellar | -7.263 |
Klux | -6.335 |
Doodle | -6.228 |
Priv | -6.214 |
Token | of |
Token ID | 286 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
ellar | +2.216 |
yrinth | +2.152 |
Priv | +1.821 |
Balloon | +1.783 |
drag | +1.750 |
Neg logit contributions | |
UCS | -2.744 |
�士 | -2.712 |
UTF | -2.671 |
osph | -2.550 |
py | -2.497 |
Token | the |
Token ID | 262 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
UCS | +1.042 |
UTF | +1.003 |
�士 | +1.000 |
osph | +0.956 |
py | +0.943 |
Neg logit contributions | |
ellar | -0.888 |
yrinth | -0.873 |
Priv | -0.728 |
Balloon | -0.717 |
Klux | -0.713 |
Token | passport |
Token ID | 17981 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
UCS | +1.547 |
UTF | +1.484 |
�士 | +1.479 |
osph | +1.412 |
py | +1.395 |
Neg logit contributions | |
ellar | -1.293 |
yrinth | -1.275 |
Priv | -1.050 |
Klux | -1.039 |
Balloon | -1.038 |
Token | , |
Token ID | 11 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
UCS | +0.206 |
�士 | +0.198 |
UTF | +0.198 |
osph | +0.188 |
py | +0.185 |
Neg logit contributions | |
ellar | -0.195 |
yrinth | -0.191 |
Priv | -0.162 |
Balloon | -0.160 |
Klux | -0.158 |
Token | whichever |
Token ID | 26204 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
UCS | +3.189 |
UTF | +2.999 |
�士 | +2.943 |
osph | +2.842 |
py | +2.829 |
Neg logit contributions | |
ellar | -3.385 |
yrinth | -3.374 |
Klux | -2.813 |
Priv | -2.759 |
Balloon | -2.756 |
Token | comes |
Token ID | 2058 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
UCS | +6.643 |
UTF | +6.092 |
�士 | +5.705 |
osph | +5.658 |
py | +5.652 |
Neg logit contributions | |
yrinth | -8.032 |
ellar | -7.865 |
Klux | -6.569 |
BW | -6.548 |
--------- | -6.476 |
Token | sooner |
Token ID | 14556 |
Feature activation | -5.20e+00 |
Pos logit contributions | |
UCS | +7.765 |
UTF | +7.303 |
py | +6.838 |
osph | +6.796 |
�士 | +6.730 |
Neg logit contributions | |
yrinth | -12.529 |
ellar | -12.073 |
BW | -10.383 |
Doodle | -10.264 |
Priv | -10.143 |
Token | in |
Token ID | 287 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
UCS | +3.491 |
UTF | +3.341 |
�士 | +3.221 |
osph | +3.174 |
py | +3.135 |
Neg logit contributions | |
ellar | -4.024 |
yrinth | -3.987 |
Priv | -3.384 |
Klux | -3.350 |
Doodle | -3.323 |
Token | case |
Token ID | 1339 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
UCS | +4.008 |
UTF | +3.807 |
�士 | +3.713 |
osph | +3.577 |
py | +3.547 |
Neg logit contributions | |
ellar | -3.831 |
yrinth | -3.783 |
Klux | -3.166 |
Priv | -3.147 |
Balloon | -3.112 |
Token | the |
Token ID | 262 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
ellar | +0.215 |
yrinth | +0.210 |
Priv | +0.177 |
Balloon | +0.173 |
Klux | +0.171 |
Neg logit contributions | |
UCS | -0.253 |
�士 | -0.244 |
UTF | -0.244 |
osph | -0.234 |
py | -0.230 |
Token | individual |
Token ID | 1981 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
UCS | +4.105 |
UTF | +3.909 |
�士 | +3.855 |
osph | +3.677 |
py | +3.667 |
Neg logit contributions | |
ellar | -3.443 |
yrinth | -3.441 |
Klux | -2.806 |
Priv | -2.760 |
Balloon | -2.749 |
Token | with |
Token ID | 351 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
UCS | +5.400 |
py | +4.776 |
UTF | +4.560 |
osph | +4.458 |
pu | +4.351 |
Neg logit contributions | |
yrinth | -10.492 |
ellar | -10.286 |
Doodle | -8.930 |
Klux | -8.717 |
Priv | -8.688 |
Token | all |
Token ID | 477 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
UCS | +3.529 |
UTF | +3.244 |
py | +3.063 |
osph | +2.997 |
pu | +2.928 |
Neg logit contributions | |
yrinth | -4.878 |
ellar | -4.791 |
Klux | -4.077 |
Priv | -4.056 |
Doodle | -4.056 |
Token | the |
Token ID | 262 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
UCS | +4.174 |
UTF | +3.865 |
py | +3.711 |
osph | +3.608 |
pu | +3.529 |
Neg logit contributions | |
yrinth | -5.277 |
ellar | -4.989 |
Klux | -4.288 |
Balloon | -4.211 |
BW | -4.178 |
Token | other |
Token ID | 584 |
Feature activation | -5.77e+00 |
Pos logit contributions | |
UCS | +4.132 |
UTF | +3.805 |
osph | +3.614 |
py | +3.607 |
pu | +3.466 |
Neg logit contributions | |
yrinth | -5.269 |
ellar | -5.070 |
Balloon | -4.285 |
Klux | -4.279 |
Doodle | -4.271 |
Token | ingredients |
Token ID | 9391 |
Feature activation | -5.32e+00 |
Pos logit contributions | |
UCS | +4.946 |
UTF | +4.741 |
osph | +4.473 |
py | +4.450 |
�士 | +4.329 |
Neg logit contributions | |
yrinth | -3.445 |
ellar | -3.275 |
Doodle | -2.679 |
Priv | -2.674 |
BW | -2.664 |
Token | and |
Token ID | 290 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
UCS | +3.298 |
UTF | +3.075 |
py | +2.971 |
osph | +2.899 |
pu | +2.824 |
Neg logit contributions | |
yrinth | -4.479 |
ellar | -4.350 |
Klux | -3.712 |
Doodle | -3.710 |
Balloon | -3.687 |
Token | mix |
Token ID | 5022 |
Feature activation | -6.74e+00 |
Pos logit contributions | |
osph | +7.215 |
UCS | +7.175 |
py | +7.166 |
UTF | +6.698 |
pu | +6.308 |
Neg logit contributions | |
yrinth | -12.385 |
ellar | -12.351 |
eleph | -10.603 |
idav | -10.526 |
Priv | -10.415 |
Token | well |
Token ID | 880 |
Feature activation | -7.31e+00 |
Pos logit contributions | |
UCS | +5.321 |
UTF | +5.092 |
py | +4.860 |
osph | +4.746 |
pu | +4.630 |
Neg logit contributions | |
yrinth | -4.472 |
ellar | -4.410 |
Doodle | -3.584 |
Balloon | -3.530 |
Priv | -3.507 |
Token | until |
Token ID | 1566 |
Feature activation | -7.99e+00 |
Pos logit contributions | |
UCS | +3.911 |
UTF | +3.650 |
osph | +3.573 |
py | +3.203 |
pu | +3.186 |
Neg logit contributions | |
yrinth | -6.552 |
ellar | -6.290 |
Priv | -5.550 |
Klux | -5.524 |
BW | -5.512 |
Token | the |
Token ID | 262 |
Feature activation | -8.03e+00 |
Pos logit contributions | |
UCS | +4.992 |
UTF | +4.543 |
py | +4.410 |
osph | +4.360 |
pu | +4.172 |
Neg logit contributions | |
yrinth | -6.667 |
ellar | -6.319 |
Priv | -5.448 |
Klux | -5.398 |
Balloon | -5.369 |
Token | mixture |
Token ID | 11710 |
Feature activation | -8.79e+00 |
Pos logit contributions | |
UCS | +4.588 |
UTF | +4.154 |
py | +4.135 |
osph | +4.102 |
pu | +3.824 |
Neg logit contributions | |
yrinth | -6.884 |
ellar | -6.754 |
Priv | -5.780 |
Klux | -5.727 |
Doodle | -5.717 |
Token | fever |
Token ID | 17372 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
UCS | +0.903 |
UTF | +0.866 |
�士 | +0.864 |
osph | +0.821 |
py | +0.807 |
Neg logit contributions | |
ellar | -0.945 |
yrinth | -0.930 |
Priv | -0.792 |
Balloon | -0.782 |
Klux | -0.778 |
Token | � |
Token ID | 447 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
ellar | +0.946 |
yrinth | +0.935 |
Priv | +0.789 |
Balloon | +0.779 |
Klux | +0.768 |
Neg logit contributions | |
UCS | -1.027 |
�士 | -1.006 |
UTF | -0.994 |
osph | -0.944 |
py | -0.923 |
Token | � |
Token ID | 251 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
UCS | +0.748 |
UTF | +0.723 |
�士 | +0.720 |
osph | +0.693 |
py | +0.685 |
Neg logit contributions | |
ellar | -0.435 |
yrinth | -0.426 |
Priv | -0.337 |
Balloon | -0.331 |
Klux | -0.328 |
Token | or |
Token ID | 393 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
UCS | +2.233 |
UTF | +2.137 |
�士 | +2.105 |
osph | +2.025 |
py | +2.015 |
Neg logit contributions | |
ellar | -2.186 |
yrinth | -2.153 |
Priv | -1.801 |
Balloon | -1.781 |
Klux | -1.780 |
Token | something |
Token ID | 1223 |
Feature activation | -9.31e+00 |
Pos logit contributions | |
UCS | +3.212 |
UTF | +3.034 |
�士 | +2.998 |
osph | +2.904 |
py | +2.872 |
Neg logit contributions | |
ellar | -3.268 |
yrinth | -3.206 |
Priv | -2.685 |
Balloon | -2.650 |
Klux | -2.647 |
Token | like |
Token ID | 588 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
UCS | +6.124 |
UTF | +5.829 |
�士 | +5.570 |
py | +5.542 |
osph | +5.453 |
Neg logit contributions | |
ellar | -7.146 |
yrinth | -7.041 |
Priv | -5.968 |
Klux | -5.845 |
Balloon | -5.822 |
Token | that |
Token ID | 326 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
UCS | +8.001 |
UTF | +7.185 |
�士 | +6.910 |
py | +6.775 |
osph | +6.640 |
Neg logit contributions | |
ellar | -12.241 |
yrinth | -11.953 |
Priv | -10.142 |
--------- | -10.050 |
Doodle | -9.970 |
Token | . |
Token ID | 13 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
UCS | +3.478 |
UTF | +3.343 |
�士 | +3.274 |
osph | +3.142 |
py | +3.135 |
Neg logit contributions | |
ellar | -3.853 |
yrinth | -3.786 |
Priv | -3.222 |
Balloon | -3.186 |
Klux | -3.186 |
Token | That |
Token ID | 1320 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ellar | +0.073 |
yrinth | +0.072 |
Priv | +0.062 |
Balloon | +0.061 |
Klux | +0.060 |
Neg logit contributions | |
UCS | -0.079 |
�士 | -0.077 |
UTF | -0.076 |
osph | -0.073 |
py | -0.071 |
Token | � |
Token ID | 447 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
ellar | +1.324 |
yrinth | +1.310 |
Priv | +1.122 |
Balloon | +1.105 |
Klux | +1.097 |
Neg logit contributions | |
UCS | -1.233 |
�士 | -1.192 |
UTF | -1.180 |
osph | -1.116 |
py | -1.082 |
Token | � |
Token ID | 247 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
ellar | +0.024 |
yrinth | +0.023 |
Priv | +0.018 |
Balloon | +0.017 |
Klux | +0.017 |
Neg logit contributions | |
UCS | -0.046 |
UTF | -0.045 |
�士 | -0.045 |
osph | -0.043 |
py | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
UCS | +3.728 |
UTF | +3.561 |
�士 | +3.511 |
osph | +3.394 |
py | +3.357 |
Neg logit contributions | |
ellar | -3.676 |
yrinth | -3.640 |
Priv | -3.034 |
Klux | -3.000 |
Balloon | -2.986 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
UCS | +2.311 |
UTF | +2.214 |
�士 | +2.204 |
osph | +2.103 |
py | +2.077 |
Neg logit contributions | |
ellar | -2.291 |
yrinth | -2.252 |
Priv | -1.897 |
Balloon | -1.873 |
Klux | -1.869 |
Token | ma |
Token ID | 17266 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
UCS | +2.746 |
UTF | +2.619 |
�士 | +2.596 |
osph | +2.487 |
py | +2.460 |
Neg logit contributions | |
ellar | -2.723 |
yrinth | -2.685 |
Priv | -2.256 |
Klux | -2.223 |
Balloon | -2.222 |
Token | N |
Token ID | 399 |
Feature activation | -6.81e+00 |
Pos logit contributions | |
UCS | +0.490 |
�士 | +0.471 |
UTF | +0.470 |
osph | +0.445 |
py | +0.439 |
Neg logit contributions | |
ellar | -0.488 |
yrinth | -0.480 |
Priv | -0.409 |
Balloon | -0.403 |
Klux | -0.401 |
Token | ā |
Token ID | 10235 |
Feature activation | -7.99e+00 |
Pos logit contributions | |
UCS | +5.235 |
UTF | +5.068 |
�士 | +4.958 |
osph | +4.853 |
py | +4.780 |
Neg logit contributions | |
ellar | -4.503 |
yrinth | -4.482 |
Priv | -3.734 |
Balloon | -3.647 |
Klux | -3.603 |
Token | n |
Token ID | 77 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
UCS | +5.907 |
UTF | +5.638 |
�士 | +5.558 |
osph | +5.492 |
pu | +5.485 |
Neg logit contributions | |
ellar | -5.438 |
yrinth | -5.362 |
Priv | -4.427 |
Klux | -4.359 |
BW | -4.341 |
Token | ā |
Token ID | 10235 |
Feature activation | -6.86e+00 |
Pos logit contributions | |
UCS | +10.067 |
pu | +9.779 |
UTF | +9.620 |
osph | +9.619 |
py | +9.515 |
Neg logit contributions | |
yrinth | -9.161 |
ellar | -8.973 |
Klux | -7.201 |
Priv | -7.178 |
BW | -7.145 |
Token | k |
Token ID | 74 |
Feature activation | -7.60e+00 |
Pos logit contributions | |
UCS | +5.126 |
UTF | +4.883 |
�士 | +4.813 |
osph | +4.724 |
pu | +4.701 |
Neg logit contributions | |
ellar | -4.730 |
yrinth | -4.660 |
Priv | -3.820 |
Klux | -3.785 |
BW | -3.736 |
Token | uli |
Token ID | 32176 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
UCS | +5.283 |
UTF | +5.062 |
�士 | +4.930 |
osph | +4.891 |
py | +4.801 |
Neg logit contributions | |
ellar | -5.518 |
yrinth | -5.493 |
Priv | -4.624 |
Balloon | -4.562 |
Klux | -4.560 |
Token | , |
Token ID | 11 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
UCS | +2.258 |
UTF | +2.165 |
�士 | +2.147 |
osph | +2.060 |
py | +2.029 |
Neg logit contributions | |
ellar | -2.209 |
yrinth | -2.176 |
Priv | -1.824 |
Balloon | -1.800 |
Klux | -1.796 |
Token | Hawai |
Token ID | 10847 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
UCS | +2.327 |
UTF | +2.229 |
�士 | +2.216 |
osph | +2.121 |
py | +2.092 |
Neg logit contributions | |
ellar | -2.251 |
yrinth | -2.214 |
Priv | -1.859 |
Balloon | -1.833 |
Klux | -1.830 |
Token | ali |
Token ID | 7344 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
UCS | +6.977 |
UTF | +6.740 |
py | +6.735 |
osph | +6.715 |
�士 | +6.521 |
Neg logit contributions | |
ellar | -6.156 |
yrinth | -6.127 |
Priv | -5.264 |
Balloon | -5.256 |
Klux | -5.142 |
Token | ( |
Token ID | 357 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
UCS | +0.196 |
UTF | +0.188 |
�士 | +0.188 |
osph | +0.179 |
py | +0.176 |
Neg logit contributions | |
ellar | -0.190 |
yrinth | -0.187 |
Priv | -0.158 |
Balloon | -0.155 |
Klux | -0.155 |
Token | ve |
Token ID | 303 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
UCS | +1.790 |
UTF | +1.724 |
�士 | +1.716 |
osph | +1.640 |
py | +1.619 |
Neg logit contributions | |
ellar | -1.651 |
yrinth | -1.625 |
Priv | -1.366 |
Balloon | -1.346 |
Klux | -1.339 |
Token | get |
Token ID | 1136 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ellar | +0.536 |
yrinth | +0.519 |
Priv | +0.384 |
Balloon | +0.377 |
Klux | +0.373 |
Neg logit contributions | |
UCS | -1.205 |
�士 | -1.181 |
UTF | -1.169 |
osph | -1.119 |
py | -1.093 |
Token | arian |
Token ID | 3699 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
UCS | +1.054 |
UTF | +1.012 |
�士 | +1.009 |
osph | +0.963 |
py | +0.948 |
Neg logit contributions | |
ellar | -1.009 |
yrinth | -0.994 |
Priv | -0.839 |
Balloon | -0.827 |
Klux | -0.824 |
Token | pl |
Token ID | 458 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
ellar | +0.724 |
yrinth | +0.709 |
Priv | +0.595 |
Balloon | +0.581 |
Klux | +0.577 |
Neg logit contributions | |
UCS | -0.870 |
�士 | -0.841 |
UTF | -0.838 |
osph | -0.795 |
py | -0.783 |
Token | atter |
Token ID | 1436 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
osph | +7.333 |
py | +7.244 |
UCS | +7.209 |
UTF | +7.136 |
atin | +6.911 |
Neg logit contributions | |
yrinth | -11.141 |
ellar | -10.802 |
Priv | -10.290 |
Doodle | -10.166 |
Balloon | -10.157 |
Token | ) |
Token ID | 8 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
UCS | +2.667 |
UTF | +2.555 |
�士 | +2.512 |
osph | +2.440 |
py | +2.415 |
Neg logit contributions | |
ellar | -2.753 |
yrinth | -2.711 |
Priv | -2.288 |
Klux | -2.268 |
Balloon | -2.259 |
Token | consisting |
Token ID | 17747 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
UCS | +2.046 |
UTF | +1.963 |
�士 | +1.936 |
osph | +1.865 |
py | +1.847 |
Neg logit contributions | |
ellar | -2.159 |
yrinth | -2.130 |
Priv | -1.795 |
Balloon | -1.780 |
Klux | -1.775 |
Token | of |
Token ID | 286 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
UCS | +0.672 |
UTF | +0.645 |
�士 | +0.643 |
osph | +0.614 |
py | +0.605 |
Neg logit contributions | |
ellar | -0.602 |
yrinth | -0.592 |
Priv | -0.496 |
Balloon | -0.489 |
Klux | -0.486 |
Token | s |
Token ID | 264 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
UCS | +3.283 |
UTF | +3.140 |
�士 | +3.096 |
osph | +2.978 |
py | +2.953 |
Neg logit contributions | |
ellar | -3.402 |
yrinth | -3.372 |
Priv | -2.805 |
Klux | -2.788 |
Balloon | -2.786 |
Token | _ |
Token ID | 4808 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
UCS | +1.129 |
UTF | +1.087 |
�士 | +1.084 |
osph | +1.037 |
py | +1.022 |
Neg logit contributions | |
ellar | -0.939 |
yrinth | -0.923 |
Priv | -0.767 |
Balloon | -0.755 |
Klux | -0.751 |
Token | P |
Token ID | 47 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
UCS | +1.732 |
UTF | +1.654 |
�士 | +1.642 |
osph | +1.553 |
py | +1.529 |
Neg logit contributions | |
ellar | -2.296 |
yrinth | -2.269 |
Priv | -1.963 |
Balloon | -1.938 |
Klux | -1.934 |
Token | ulse |
Token ID | 9615 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
ellar | +0.247 |
yrinth | +0.244 |
Priv | +0.214 |
Balloon | +0.212 |
Klux | +0.211 |
Neg logit contributions | |
UCS | -0.149 |
UTF | -0.141 |
�士 | -0.141 |
osph | -0.131 |
py | -0.129 |
Token | Amount |
Token ID | 31264 |
Feature activation | +6.60e+00 |
Pos logit contributions | |
ellar | +1.912 |
yrinth | +1.831 |
Priv | +1.597 |
BW | +1.585 |
Balloon | +1.578 |
Neg logit contributions | |
UCS | -2.197 |
�士 | -2.193 |
UTF | -2.072 |
osph | -2.013 |
py | -1.953 |
Token | ; |
Token ID | 26 |
Feature activation | -9.03e+00 |
Pos logit contributions | |
ellar | +3.879 |
yrinth | +3.764 |
[_ | +3.248 |
Priv | +3.172 |
Balloon | +3.165 |
Neg logit contributions | |
UCS | -5.350 |
�士 | -5.281 |
UTF | -5.097 |
osph | -4.920 |
py | -4.792 |
Token | } |
Token ID | 1782 |
Feature activation | -1.42e+01 |
Pos logit contributions | |
UCS | +6.162 |
UTF | +5.585 |
�士 | +5.405 |
py | +5.270 |
pu | +5.205 |
Neg logit contributions | |
yrinth | -6.806 |
ellar | -6.779 |
Klux | -5.820 |
BW | -5.626 |
--------- | -5.590 |
Token | 1 |
Token ID | 352 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
UCS | +9.289 |
UTF | +8.199 |
py | +8.022 |
osph | +7.682 |
pu | +7.681 |
Neg logit contributions | |
ellar | -10.509 |
yrinth | -10.322 |
Klux | -8.858 |
idav | -8.382 |
BW | -8.353 |
Token | 2 |
Token ID | 362 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
UCS | +3.535 |
UTF | +3.267 |
py | +3.091 |
osph | +3.048 |
�士 | +2.987 |
Neg logit contributions | |
yrinth | -4.184 |
ellar | -4.158 |
Klux | -3.467 |
Priv | -3.444 |
BW | -3.401 |
Token | 3 |
Token ID | 513 |
Feature activation | -7.21e+00 |
Pos logit contributions | |
UCS | +0.825 |
UTF | +0.790 |
�士 | +0.780 |
osph | +0.751 |
py | +0.744 |
Neg logit contributions | |
ellar | -0.703 |
yrinth | -0.689 |
Priv | -0.572 |
Klux | -0.565 |
Balloon | -0.564 |
Token | 4 |
Token ID | 604 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
UCS | +5.071 |
UTF | +4.688 |
�士 | +4.623 |
py | +4.445 |
osph | +4.415 |
Neg logit contributions | |
ellar | -5.457 |
yrinth | -5.282 |
Klux | -4.573 |
BW | -4.539 |
Priv | -4.506 |
Token | 5 |
Token ID | 642 |
Feature activation | -6.01e+00 |
Pos logit contributions | |
UCS | +0.509 |
�士 | +0.493 |
UTF | +0.492 |
osph | +0.466 |
py | +0.459 |
Neg logit contributions | |
ellar | -0.514 |
yrinth | -0.507 |
Priv | -0.431 |
Balloon | -0.425 |
Klux | -0.419 |
Token | up |
Token ID | 510 |
Feature activation | -6.42e+00 |
Pos logit contributions | |
UCS | +3.242 |
UTF | +3.006 |
py | +2.901 |
osph | +2.868 |
�士 | +2.826 |
Neg logit contributions | |
yrinth | -3.407 |
ellar | -3.391 |
Priv | -2.809 |
Klux | -2.793 |
Balloon | -2.783 |
Token | some |
Token ID | 617 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
UCS | +4.372 |
UTF | +4.141 |
py | +3.988 |
osph | +3.844 |
pu | +3.795 |
Neg logit contributions | |
yrinth | -4.955 |
ellar | -4.849 |
Balloon | -4.036 |
Klux | -3.985 |
Doodle | -3.959 |
Token | got |
Token ID | 1392 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
UCS | +2.776 |
UTF | +2.636 |
�士 | +2.557 |
py | +2.522 |
osph | +2.481 |
Neg logit contributions | |
ellar | -2.803 |
yrinth | -2.788 |
Balloon | -2.318 |
Priv | -2.304 |
Doodle | -2.280 |
Token | cha |
Token ID | 11693 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
UCS | +1.321 |
UTF | +1.258 |
�士 | +1.179 |
py | +1.178 |
osph | +1.163 |
Neg logit contributions | |
ellar | -2.270 |
yrinth | -2.263 |
Priv | -1.960 |
Balloon | -1.941 |
Doodle | -1.938 |
Token | 's |
Token ID | 338 |
Feature activation | -5.95e+00 |
Pos logit contributions | |
ellar | +0.737 |
yrinth | +0.721 |
Priv | +0.613 |
Balloon | +0.601 |
Klux | +0.599 |
Neg logit contributions | |
UCS | -0.796 |
�士 | -0.774 |
UTF | -0.766 |
osph | -0.730 |
py | -0.717 |
Token | I |
Token ID | 314 |
Feature activation | -1.42e+01 |
Pos logit contributions | |
UCS | +3.472 |
UTF | +3.253 |
py | +3.100 |
osph | +2.988 |
pu | +2.883 |
Neg logit contributions | |
ellar | -5.150 |
yrinth | -5.135 |
Klux | -4.315 |
Balloon | -4.314 |
BW | -4.259 |
Token | encountered |
Token ID | 12956 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
UCS | +5.331 |
UTF | +4.811 |
osph | +4.790 |
py | +4.517 |
ansen | +4.300 |
Neg logit contributions | |
ellar | -13.004 |
yrinth | -12.774 |
BW | -11.807 |
Balloon | -11.779 |
Doodle | -11.370 |
Token | . |
Token ID | 13 |
Feature activation | -8.25e+00 |
Pos logit contributions | |
UCS | +2.844 |
UTF | +2.707 |
py | +2.547 |
osph | +2.485 |
pu | +2.426 |
Neg logit contributions | |
yrinth | -3.795 |
ellar | -3.734 |
Klux | -3.155 |
Balloon | -3.124 |
Doodle | -3.116 |
Token | Assuming |
Token ID | 33238 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
UCS | +5.100 |
UTF | +4.911 |
�士 | +4.695 |
osph | +4.414 |
py | +4.408 |
Neg logit contributions | |
ellar | -6.677 |
yrinth | -6.604 |
BW | -5.645 |
Klux | -5.639 |
--------- | -5.564 |
Token | you |
Token ID | 345 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
UCS | +1.290 |
UTF | +1.228 |
�士 | +1.178 |
py | +1.155 |
osph | +1.152 |
Neg logit contributions | |
ellar | -1.386 |
yrinth | -1.377 |
Priv | -1.155 |
Balloon | -1.148 |
Klux | -1.146 |
Token | already |
Token ID | 1541 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
ellar | +1.233 |
yrinth | +1.202 |
Priv | +0.964 |
Balloon | +0.939 |
Klux | +0.935 |
Neg logit contributions | |
UCS | -2.051 |
�士 | -2.006 |
UTF | -1.984 |
osph | -1.909 |
py | -1.872 |
Token | very |
Token ID | 845 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
ellar | +2.613 |
yrinth | +2.583 |
drag | +2.183 |
Priv | +2.164 |
Klux | +2.136 |
Neg logit contributions | |
UCS | -4.150 |
�士 | -4.113 |
UTF | -4.075 |
osph | -3.911 |
py | -3.779 |
Token | poorly |
Token ID | 13455 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
ellar | +0.435 |
yrinth | +0.426 |
Priv | +0.339 |
Balloon | +0.330 |
Klux | +0.329 |
Neg logit contributions | |
UCS | -0.764 |
�士 | -0.740 |
UTF | -0.740 |
osph | -0.712 |
py | -0.702 |
Token | when |
Token ID | 618 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
ellar | +2.565 |
yrinth | +2.519 |
Priv | +2.170 |
drag | +2.124 |
Balloon | +2.107 |
Neg logit contributions | |
�士 | -3.059 |
UCS | -3.053 |
UTF | -2.943 |
osph | -2.804 |
py | -2.730 |
Token | voters |
Token ID | 4446 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ellar | +0.451 |
yrinth | +0.441 |
Priv | +0.376 |
Balloon | +0.364 |
Klux | +0.363 |
Neg logit contributions | |
UCS | -0.504 |
�士 | -0.487 |
UTF | -0.486 |
osph | -0.463 |
py | -0.458 |
Token | are |
Token ID | 389 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
ellar | +0.965 |
yrinth | +0.940 |
Priv | +0.802 |
Balloon | +0.788 |
drag | +0.786 |
Neg logit contributions | |
UCS | -1.020 |
�士 | -0.992 |
UTF | -0.987 |
osph | -0.926 |
py | -0.915 |
Token | asked |
Token ID | 1965 |
Feature activation | +7.47e+00 |
Pos logit contributions | |
ellar | +2.682 |
yrinth | +2.625 |
Priv | +2.258 |
drag | +2.199 |
Klux | +2.152 |
Neg logit contributions | |
UCS | -3.514 |
�士 | -3.404 |
UTF | -3.398 |
osph | -3.214 |
py | -3.195 |
Token | about |
Token ID | 546 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
ellar | +4.517 |
yrinth | +4.398 |
drag | +3.881 |
Priv | +3.861 |
--------- | +3.717 |
Neg logit contributions | |
UCS | -5.754 |
�士 | -5.738 |
UTF | -5.659 |
osph | -5.465 |
py | -5.260 |
Token | her |
Token ID | 607 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
ellar | +2.833 |
yrinth | +2.761 |
Priv | +2.373 |
drag | +2.275 |
Klux | +2.218 |
Neg logit contributions | |
UCS | -4.012 |
�士 | -3.998 |
UTF | -3.979 |
osph | -3.793 |
py | -3.707 |
Token | honesty |
Token ID | 24345 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
ellar | +1.907 |
yrinth | +1.876 |
Priv | +1.619 |
Balloon | +1.568 |
--------- | +1.562 |
Neg logit contributions | |
UCS | -2.087 |
�士 | -2.075 |
UTF | -2.031 |
osph | -1.942 |
py | -1.895 |
Token | and |
Token ID | 290 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
ellar | +3.310 |
yrinth | +3.259 |
Priv | +2.827 |
drag | +2.743 |
--------- | +2.741 |
Neg logit contributions | |
UCS | -4.065 |
�士 | -4.017 |
UTF | -3.917 |
osph | -3.710 |
py | -3.636 |
Token | trust |
Token ID | 3774 |
Feature activation | +7.21e+00 |
Pos logit contributions | |
ellar | +1.510 |
yrinth | +1.478 |
Priv | +1.251 |
Balloon | +1.198 |
drag | +1.197 |
Neg logit contributions | |
UCS | -1.972 |
UTF | -1.928 |
�士 | -1.928 |
osph | -1.837 |
py | -1.809 |
Token | also |
Token ID | 635 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
ellar | +0.225 |
yrinth | +0.222 |
Priv | +0.186 |
Balloon | +0.184 |
drag | +0.181 |
Neg logit contributions | |
UCS | -0.253 |
�士 | -0.245 |
UTF | -0.244 |
osph | -0.231 |
py | -0.226 |
Token | tended |
Token ID | 19960 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
ellar | +3.172 |
yrinth | +3.111 |
drag | +2.718 |
Balloon | +2.673 |
Priv | +2.655 |
Neg logit contributions | |
UCS | -3.694 |
�士 | -3.682 |
UTF | -3.613 |
osph | -3.360 |
py | -3.261 |
Token | to |
Token ID | 284 |
Feature activation | +5.85e+00 |
Pos logit contributions | |
ellar | +1.907 |
yrinth | +1.842 |
drag | +1.560 |
Balloon | +1.539 |
Priv | +1.520 |
Neg logit contributions | |
UCS | -2.159 |
�士 | -2.100 |
UTF | -2.068 |
osph | -1.955 |
py | -1.931 |
Token | corro |
Token ID | 26132 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
ellar | +3.907 |
yrinth | +3.761 |
drag | +3.477 |
Balloon | +3.247 |
Priv | +3.238 |
Neg logit contributions | |
�士 | -4.506 |
UCS | -4.423 |
UTF | -4.370 |
osph | -3.999 |
pu | -3.890 |
Token | de |
Token ID | 2934 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
UCS | +1.919 |
UTF | +1.816 |
py | +1.759 |
osph | +1.749 |
�士 | +1.741 |
Neg logit contributions | |
ellar | -2.457 |
yrinth | -2.421 |
Priv | -2.084 |
BW | -2.055 |
Balloon | -2.054 |
Token | quickly |
Token ID | 2952 |
Feature activation | +6.95e+00 |
Pos logit contributions | |
UCS | +0.454 |
�士 | +0.437 |
UTF | +0.436 |
osph | +0.415 |
py | +0.408 |
Neg logit contributions | |
ellar | -0.433 |
yrinth | -0.425 |
Priv | -0.360 |
Balloon | -0.355 |
Klux | -0.352 |
Token | , |
Token ID | 11 |
Feature activation | +5.56e+00 |
Pos logit contributions | |
ellar | +4.130 |
yrinth | +3.900 |
drag | +3.450 |
Balloon | +3.385 |
Priv | +3.336 |
Neg logit contributions | |
�士 | -5.793 |
UCS | -5.612 |
UTF | -5.451 |
osph | -5.093 |
pu | -5.005 |
Token | short |
Token ID | 1790 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
ellar | +3.554 |
yrinth | +3.428 |
drag | +2.960 |
Priv | +2.932 |
Balloon | +2.923 |
Neg logit contributions | |
UCS | -4.321 |
�士 | -4.303 |
UTF | -4.222 |
osph | -3.977 |
py | -3.897 |
Token | ening |
Token ID | 3101 |
Feature activation | +8.46e-02 |
Pos logit contributions | |
ellar | +3.472 |
yrinth | +3.398 |
Balloon | +2.909 |
drag | +2.906 |
Priv | +2.846 |
Neg logit contributions | |
UCS | -3.978 |
�士 | -3.968 |
UTF | -3.882 |
osph | -3.693 |
py | -3.631 |
Token | the |
Token ID | 262 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ellar | +0.056 |
yrinth | +0.055 |
Priv | +0.046 |
Balloon | +0.046 |
drag | +0.045 |
Neg logit contributions | |
UCS | -0.067 |
�士 | -0.065 |
UTF | -0.064 |
osph | -0.061 |
py | -0.061 |
Token | life |
Token ID | 1204 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
UCS | +1.222 |
UTF | +1.172 |
�士 | +1.167 |
osph | +1.116 |
py | +1.100 |
Neg logit contributions | |
ellar | -1.121 |
yrinth | -1.104 |
Priv | -0.927 |
Balloon | -0.912 |
Klux | -0.911 |
Token | x |
Token ID | 2124 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
ellar | +3.808 |
yrinth | +3.653 |
Priv | +3.202 |
Balloon | +3.107 |
drag | +3.018 |
Neg logit contributions | |
�士 | -6.945 |
UCS | -6.841 |
UTF | -6.782 |
osph | -6.601 |
py | -6.342 |
Token | . |
Token ID | 13 |
Feature activation | +7.67e+00 |
Pos logit contributions | |
ellar | +2.818 |
yrinth | +2.673 |
Priv | +2.352 |
--------- | +2.316 |
Balloon | +2.297 |
Neg logit contributions | |
�士 | -3.228 |
UCS | -3.165 |
UTF | -3.027 |
osph | -2.939 |
py | -2.819 |
Token | x |
Token ID | 87 |
Feature activation | +9.49e+00 |
Pos logit contributions | |
ellar | +3.832 |
yrinth | +3.596 |
Klux | +2.959 |
BW | +2.906 |
--------- | +2.899 |
Neg logit contributions | |
�士 | -7.203 |
UCS | -7.035 |
UTF | -6.651 |
osph | -6.415 |
� | -6.168 |
Token | . |
Token ID | 13 |
Feature activation | +9.65e+00 |
Pos logit contributions | |
ellar | +5.297 |
yrinth | +4.621 |
--------- | +4.458 |
[_ | +4.445 |
Priv | +4.428 |
Neg logit contributions | |
�士 | -8.604 |
UCS | -7.737 |
UTF | -7.450 |
osph | -7.389 |
senal | -7.260 |
Token | x |
Token ID | 87 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
ellar | +4.444 |
yrinth | +4.360 |
Klux | +3.457 |
BW | +3.374 |
Priv | +3.358 |
Neg logit contributions | |
UCS | -8.908 |
�士 | -8.616 |
UTF | -8.459 |
osph | -8.185 |
� | -7.784 |
Token | . |
Token ID | 13 |
Feature activation | +8.66e+00 |
Pos logit contributions | |
ellar | +5.635 |
yrinth | +4.957 |
[_ | +4.859 |
--------- | +4.845 |
Priv | +4.843 |
Neg logit contributions | |
�士 | -9.639 |
UCS | -8.722 |
osph | -8.560 |
UTF | -8.534 |
senal | -8.150 |
Token | 78 |
Token ID | 3695 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
ellar | +4.313 |
yrinth | +4.283 |
[_ | +3.452 |
Klux | +3.448 |
--------- | +3.424 |
Neg logit contributions | |
UCS | -7.737 |
UTF | -7.433 |
�士 | -7.412 |
osph | -7.223 |
� | -6.701 |
Token | 115 |
Token ID | 12279 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
UCS | +2.351 |
UTF | +2.231 |
�士 | +2.197 |
osph | +2.092 |
py | +2.070 |
Neg logit contributions | |
ellar | -3.050 |
yrinth | -3.004 |
Priv | -2.564 |
Klux | -2.559 |
Balloon | -2.557 |
Token | 16 |
Token ID | 1433 |
Feature activation | +9.46e+00 |
Pos logit contributions | |
ellar | +0.917 |
yrinth | +0.891 |
Priv | +0.782 |
Balloon | +0.767 |
--------- | +0.764 |
Neg logit contributions | |
UCS | -0.733 |
�士 | -0.711 |
UTF | -0.696 |
osph | -0.672 |
py | -0.646 |
Token | 72 |
Token ID | 4761 |
Feature activation | +8.46e+00 |
Pos logit contributions | |
ellar | +5.933 |
yrinth | +5.382 |
Priv | +5.131 |
--------- | +5.103 |
Balloon | +5.073 |
Neg logit contributions | |
�士 | -7.188 |
UCS | -6.848 |
osph | -6.731 |
UTF | -6.658 |
py | -6.082 |
Token | x |
Token ID | 2124 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
ellar | +3.820 |
yrinth | +3.755 |
Priv | +3.250 |
Balloon | +3.086 |
drag | +3.045 |
Neg logit contributions | |
�士 | -7.643 |
UCS | -7.603 |
UTF | -7.491 |
osph | -7.301 |
py | -7.106 |
Token | is |
Token ID | 318 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
UCS | +2.800 |
UTF | +2.696 |
�士 | +2.669 |
osph | +2.565 |
py | +2.532 |
Neg logit contributions | |
ellar | -2.673 |
yrinth | -2.633 |
Priv | -2.209 |
Balloon | -2.182 |
Klux | -2.181 |
Token | strongly |
Token ID | 7634 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ellar | +0.721 |
yrinth | +0.708 |
Priv | +0.604 |
Balloon | +0.589 |
drag | +0.579 |
Neg logit contributions | |
UCS | -0.799 |
�士 | -0.780 |
UTF | -0.776 |
osph | -0.743 |
py | -0.726 |
Token | influenced |
Token ID | 12824 |
Feature activation | -7.37e+00 |
Pos logit contributions | |
ellar | +1.034 |
yrinth | +1.013 |
Priv | +0.858 |
Balloon | +0.837 |
Klux | +0.822 |
Neg logit contributions | |
UCS | -1.212 |
�士 | -1.178 |
UTF | -1.173 |
osph | -1.129 |
py | -1.097 |
Token | by |
Token ID | 416 |
Feature activation | -8.06e+00 |
Pos logit contributions | |
UCS | +5.196 |
UTF | +4.991 |
�士 | +4.957 |
osph | +4.730 |
py | +4.715 |
Neg logit contributions | |
ellar | -5.346 |
yrinth | -5.255 |
Priv | -4.408 |
Balloon | -4.403 |
Doodle | -4.399 |
Token | the |
Token ID | 262 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
UCS | +5.880 |
UTF | +5.508 |
�士 | +5.436 |
py | +5.207 |
osph | +5.170 |
Neg logit contributions | |
ellar | -5.784 |
yrinth | -5.673 |
Klux | -4.671 |
Balloon | -4.634 |
Doodle | -4.613 |
Token | story |
Token ID | 1621 |
Feature activation | +7.09e+00 |
Pos logit contributions | |
UCS | +1.780 |
UTF | +1.706 |
�士 | +1.697 |
osph | +1.621 |
py | +1.602 |
Neg logit contributions | |
ellar | -1.596 |
yrinth | -1.570 |
Priv | -1.307 |
Balloon | -1.292 |
Klux | -1.290 |
Token | of |
Token ID | 286 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
yrinth | +4.360 |
ellar | +4.318 |
Priv | +3.752 |
Balloon | +3.575 |
drag | +3.563 |
Neg logit contributions | |
UCS | -5.513 |
UTF | -5.467 |
�士 | -5.467 |
osph | -5.231 |
py | -5.056 |
Token | George |
Token ID | 4502 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
UCS | +0.025 |
�士 | +0.024 |
UTF | +0.024 |
osph | +0.023 |
py | +0.023 |
Neg logit contributions | |
ellar | -0.024 |
yrinth | -0.024 |
Priv | -0.020 |
Balloon | -0.020 |
Klux | -0.020 |
Token | W |
Token ID | 370 |
Feature activation | +5.69e+00 |
Pos logit contributions | |
ellar | +0.831 |
yrinth | +0.802 |
Priv | +0.701 |
Balloon | +0.689 |
Klux | +0.674 |
Neg logit contributions | |
UCS | -0.985 |
�士 | -0.969 |
UTF | -0.966 |
osph | -0.919 |
py | -0.898 |
Token | . |
Token ID | 13 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
ellar | +3.685 |
yrinth | +3.611 |
Priv | +3.048 |
Klux | +3.018 |
Balloon | +3.018 |
Neg logit contributions | |
UCS | -4.390 |
UTF | -4.245 |
�士 | -4.119 |
py | -3.965 |
osph | -3.953 |
Token | Bush |
Token ID | 5511 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
ellar | +2.068 |
yrinth | +1.934 |
Priv | +1.608 |
Balloon | +1.531 |
Klux | +1.520 |
Neg logit contributions | |
UCS | -5.179 |
�士 | -5.107 |
UTF | -5.066 |
osph | -4.898 |
py | -4.816 |
Token | 've |
Token ID | 1053 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
ellar | +3.269 |
yrinth | +3.208 |
drag | +2.852 |
Priv | +2.783 |
Balloon | +2.718 |
Neg logit contributions | |
�士 | -3.785 |
UCS | -3.756 |
UTF | -3.669 |
osph | -3.442 |
py | -3.369 |
Token | spoke |
Token ID | 5158 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ellar | +2.127 |
yrinth | +2.074 |
Priv | +1.800 |
Balloon | +1.764 |
drag | +1.756 |
Neg logit contributions | |
UCS | -2.416 |
�士 | -2.395 |
UTF | -2.337 |
osph | -2.217 |
py | -2.158 |
Token | , |
Token ID | 11 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
UCS | +0.990 |
UTF | +0.953 |
�士 | +0.943 |
osph | +0.902 |
py | +0.891 |
Neg logit contributions | |
ellar | -0.971 |
yrinth | -0.958 |
Priv | -0.805 |
Klux | -0.794 |
Balloon | -0.794 |
Token | " |
Token ID | 366 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
UCS | +0.429 |
UTF | +0.413 |
�士 | +0.412 |
osph | +0.393 |
py | +0.387 |
Neg logit contributions | |
ellar | -0.392 |
yrinth | -0.386 |
Priv | -0.325 |
Balloon | -0.320 |
Klux | -0.317 |
Token | Bel |
Token ID | 12193 |
Feature activation | +8.99e+00 |
Pos logit contributions | |
ellar | +2.368 |
yrinth | +2.328 |
--------- | +1.986 |
BW | +1.981 |
Priv | +1.973 |
Neg logit contributions | |
UCS | -2.737 |
�士 | -2.677 |
UTF | -2.538 |
osph | -2.525 |
py | -2.382 |
Token | ieve |
Token ID | 12311 |
Feature activation | +8.80e+00 |
Pos logit contributions | |
yrinth | +4.079 |
ellar | +3.874 |
apor | +3.195 |
Priv | +3.176 |
drag | +3.115 |
Neg logit contributions | |
�士 | -8.367 |
UCS | -8.285 |
UTF | -8.063 |
osph | -7.617 |
� | -7.409 |
Token | me |
Token ID | 502 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
ellar | +4.867 |
yrinth | +4.630 |
Priv | +3.924 |
Balloon | +3.836 |
drag | +3.792 |
Neg logit contributions | |
�士 | -7.287 |
UCS | -7.230 |
UTF | -7.104 |
osph | -6.992 |
pu | -6.723 |
Token | , |
Token ID | 11 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
ellar | +0.126 |
yrinth | +0.125 |
Priv | +0.106 |
Balloon | +0.105 |
--------- | +0.103 |
Neg logit contributions | |
UCS | -0.139 |
�士 | -0.134 |
UTF | -0.133 |
osph | -0.128 |
py | -0.125 |
Token | Anna |
Token ID | 11735 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
ellar | +0.536 |
yrinth | +0.528 |
Priv | +0.450 |
Balloon | +0.445 |
Klux | +0.436 |
Neg logit contributions | |
UCS | -0.553 |
�士 | -0.535 |
UTF | -0.533 |
osph | -0.508 |
py | -0.497 |
Token | . |
Token ID | 13 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
UCS | +2.155 |
UTF | +2.068 |
�士 | +2.051 |
osph | +1.949 |
py | +1.938 |
Neg logit contributions | |
ellar | -2.280 |
yrinth | -2.245 |
Priv | -1.901 |
Klux | -1.880 |
Balloon | -1.876 |
Token | If |
Token ID | 1002 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
ellar | +1.857 |
yrinth | +1.813 |
Priv | +1.611 |
Balloon | +1.590 |
Doodle | +1.546 |
Neg logit contributions | |
UCS | -1.986 |
�士 | -1.968 |
UTF | -1.928 |
osph | -1.881 |
py | -1.797 |
Token | Ireland |
Token ID | 7517 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ellar | +1.567 |
yrinth | +1.543 |
Priv | +1.302 |
Balloon | +1.267 |
drag | +1.255 |
Neg logit contributions | |
UCS | -1.967 |
�士 | -1.908 |
UTF | -1.904 |
osph | -1.817 |
py | -1.794 |
Token | � |
Token ID | 447 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ellar | +0.125 |
yrinth | +0.122 |
Priv | +0.103 |
Balloon | +0.102 |
Klux | +0.101 |
Neg logit contributions | |
UCS | -0.136 |
�士 | -0.131 |
UTF | -0.131 |
osph | -0.124 |
py | -0.122 |
Token | � |
Token ID | 247 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
UCS | +1.478 |
UTF | +1.440 |
�士 | +1.433 |
osph | +1.389 |
py | +1.370 |
Neg logit contributions | |
ellar | -0.726 |
yrinth | -0.713 |
Priv | -0.543 |
Balloon | -0.532 |
Klux | -0.524 |
Token | s |
Token ID | 82 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
UCS | +0.191 |
UTF | +0.184 |
�士 | +0.184 |
osph | +0.174 |
py | +0.170 |
Neg logit contributions | |
ellar | -0.193 |
yrinth | -0.191 |
Priv | -0.162 |
Balloon | -0.159 |
Klux | -0.159 |
Token | national |
Token ID | 2260 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
UCS | +1.100 |
UTF | +1.056 |
�士 | +1.045 |
osph | +1.006 |
py | +0.992 |
Neg logit contributions | |
ellar | -0.968 |
yrinth | -0.951 |
Priv | -0.789 |
Balloon | -0.782 |
Klux | -0.781 |
Token | accounts |
Token ID | 5504 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
UCS | +0.014 |
�士 | +0.014 |
UTF | +0.014 |
osph | +0.013 |
py | +0.013 |
Neg logit contributions | |
ellar | -0.014 |
yrinth | -0.014 |
Priv | -0.012 |
Balloon | -0.011 |
Klux | -0.011 |
Token | will |
Token ID | 481 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
ellar | +0.946 |
yrinth | +0.933 |
Priv | +0.794 |
Balloon | +0.782 |
drag | +0.776 |
Neg logit contributions | |
UCS | -0.998 |
�士 | -0.962 |
UTF | -0.960 |
osph | -0.904 |
py | -0.887 |
Token | also |
Token ID | 635 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
UCS | +2.374 |
UTF | +2.257 |
�士 | +2.216 |
osph | +2.191 |
py | +2.155 |
Neg logit contributions | |
ellar | -2.369 |
yrinth | -2.335 |
Priv | -1.955 |
Klux | -1.949 |
Balloon | -1.923 |
Token | provide |
Token ID | 2148 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
UCS | +1.212 |
UTF | +1.156 |
�士 | +1.147 |
osph | +1.105 |
py | +1.088 |
Neg logit contributions | |
ellar | -1.293 |
yrinth | -1.274 |
Priv | -1.080 |
Klux | -1.068 |
Balloon | -1.066 |
Token | few |
Token ID | 1178 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
ellar | +1.311 |
yrinth | +1.278 |
Priv | +1.080 |
drag | +1.058 |
Balloon | +1.053 |
Neg logit contributions | |
UCS | -1.565 |
�士 | -1.526 |
UTF | -1.520 |
osph | -1.454 |
py | -1.420 |
Token | answers |
Token ID | 7429 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
UCS | +2.674 |
UTF | +2.558 |
�士 | +2.533 |
osph | +2.422 |
py | +2.413 |
Neg logit contributions | |
ellar | -2.490 |
yrinth | -2.483 |
Priv | -2.075 |
Balloon | -2.066 |
Klux | -2.063 |
Token | remarkable |
Token ID | 11004 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ellar | +0.051 |
yrinth | +0.050 |
Priv | +0.043 |
Balloon | +0.042 |
Klux | +0.042 |
Neg logit contributions | |
UCS | -0.058 |
UTF | -0.056 |
�士 | -0.056 |
osph | -0.053 |
py | -0.052 |
Token | with |
Token ID | 351 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
UCS | +0.784 |
UTF | +0.754 |
�士 | +0.752 |
osph | +0.716 |
py | +0.705 |
Neg logit contributions | |
ellar | -0.744 |
yrinth | -0.732 |
Priv | -0.618 |
Balloon | -0.609 |
Klux | -0.606 |
Token | regard |
Token ID | 2754 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
ellar | +3.809 |
yrinth | +3.744 |
Priv | +3.220 |
Balloon | +3.178 |
drag | +3.122 |
Neg logit contributions | |
�士 | -5.031 |
UCS | -5.022 |
UTF | -4.911 |
osph | -4.778 |
py | -4.549 |
Token | to |
Token ID | 284 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
ellar | +1.845 |
yrinth | +1.779 |
Priv | +1.529 |
Balloon | +1.500 |
drag | +1.497 |
Neg logit contributions | |
�士 | -1.967 |
UCS | -1.966 |
UTF | -1.897 |
osph | -1.805 |
py | -1.766 |
Token | common |
Token ID | 2219 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
ellar | +2.790 |
yrinth | +2.742 |
Priv | +2.373 |
Balloon | +2.336 |
drag | +2.318 |
Neg logit contributions | |
UCS | -3.547 |
�士 | -3.544 |
UTF | -3.501 |
osph | -3.346 |
py | -3.209 |
Token | species |
Token ID | 4693 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
ellar | +2.251 |
yrinth | +2.204 |
Priv | +1.886 |
Balloon | +1.842 |
drag | +1.820 |
Neg logit contributions | |
UCS | -2.561 |
�士 | -2.516 |
UTF | -2.468 |
osph | -2.344 |
py | -2.264 |
Token | , |
Token ID | 11 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
ellar | +0.129 |
yrinth | +0.126 |
Priv | +0.106 |
Balloon | +0.104 |
Klux | +0.102 |
Neg logit contributions | |
UCS | -0.152 |
�士 | -0.148 |
UTF | -0.148 |
osph | -0.140 |
py | -0.137 |
Token | wildlife |
Token ID | 15599 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
UCS | +0.642 |
UTF | +0.618 |
�士 | +0.618 |
osph | +0.589 |
py | +0.579 |
Neg logit contributions | |
ellar | -0.567 |
yrinth | -0.557 |
Priv | -0.468 |
Balloon | -0.461 |
Klux | -0.457 |
Token | video |
Token ID | 2008 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
UCS | +1.007 |
UTF | +0.971 |
�士 | +0.970 |
osph | +0.922 |
py | +0.908 |
Neg logit contributions | |
ellar | -0.919 |
yrinth | -0.903 |
Priv | -0.761 |
Balloon | -0.749 |
Klux | -0.744 |
Token | of |
Token ID | 286 |
Feature activation | +6.77e+00 |
Pos logit contributions | |
ellar | +1.898 |
yrinth | +1.841 |
Priv | +1.593 |
drag | +1.558 |
Balloon | +1.554 |
Neg logit contributions | |
UCS | -2.037 |
�士 | -2.020 |
UTF | -1.981 |
osph | -1.856 |
py | -1.819 |
Token | the |
Token ID | 262 |
Feature activation | +6.27e+00 |
Pos logit contributions | |
ellar | +3.971 |
yrinth | +3.915 |
Priv | +3.364 |
drag | +3.354 |
Balloon | +3.301 |
Neg logit contributions | |
�士 | -5.470 |
UTF | -5.404 |
UCS | -5.402 |
osph | -5.162 |
py | -4.879 |
Token | huge |
Token ID | 3236 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
ellar | +1.091 |
yrinth | +1.058 |
Priv | +0.926 |
drag | +0.908 |
Balloon | +0.902 |
Neg logit contributions | |
UCS | -1.154 |
�士 | -1.150 |
UTF | -1.124 |
osph | -1.070 |
py | -1.041 |
Token | portion |
Token ID | 6903 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ellar | +1.403 |
yrinth | +1.355 |
Priv | +1.197 |
drag | +1.178 |
Balloon | +1.152 |
Neg logit contributions | |
UCS | -1.586 |
�士 | -1.577 |
UTF | -1.554 |
osph | -1.482 |
py | -1.450 |
Token | of |
Token ID | 286 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
ellar | +0.804 |
yrinth | +0.783 |
Priv | +0.661 |
Balloon | +0.648 |
Klux | +0.641 |
Neg logit contributions | |
UCS | -0.934 |
�士 | -0.913 |
UTF | -0.899 |
osph | -0.857 |
py | -0.842 |
Token | its |
Token ID | 663 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
ellar | +1.557 |
yrinth | +1.525 |
Priv | +1.289 |
Balloon | +1.248 |
drag | +1.246 |
Neg logit contributions | |
UCS | -2.149 |
�士 | -2.128 |
UTF | -2.102 |
osph | -2.025 |
py | -1.975 |
Token | revenue |
Token ID | 6426 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
ellar | +2.897 |
yrinth | +2.803 |
Priv | +2.504 |
drag | +2.460 |
Doodle | +2.383 |
Neg logit contributions | |
�士 | -3.689 |
UCS | -3.609 |
UTF | -3.554 |
osph | -3.437 |
pu | -3.311 |
Token | from |
Token ID | 422 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
ellar | +2.029 |
yrinth | +1.980 |
Priv | +1.682 |
drag | +1.653 |
Balloon | +1.634 |
Neg logit contributions | |
UCS | -2.434 |
�士 | -2.416 |
UTF | -2.355 |
osph | -2.209 |
pu | -2.166 |
Token | online |
Token ID | 2691 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
UCS | +0.360 |
�士 | +0.348 |
UTF | +0.348 |
osph | +0.332 |
py | +0.326 |
Neg logit contributions | |
ellar | -0.311 |
yrinth | -0.305 |
Priv | -0.257 |
Balloon | -0.253 |
Klux | -0.250 |
Token | ads |
Token ID | 9011 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
ellar | +0.955 |
yrinth | +0.939 |
Priv | +0.791 |
Balloon | +0.778 |
drag | +0.773 |
Neg logit contributions | |
UCS | -1.201 |
�士 | -1.174 |
UTF | -1.170 |
osph | -1.115 |
py | -1.089 |
Token | , |
Token ID | 11 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
UCS | +2.127 |
UTF | +2.043 |
�士 | +2.028 |
osph | +1.941 |
py | +1.919 |
Neg logit contributions | |
ellar | -2.039 |
yrinth | -2.006 |
Priv | -1.693 |
Balloon | -1.669 |
Klux | -1.667 |
Token | Google |
Token ID | 3012 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
ellar | +0.421 |
yrinth | +0.415 |
Priv | +0.354 |
Balloon | +0.348 |
Doodle | +0.343 |
Neg logit contributions | |
UCS | -0.446 |
UTF | -0.433 |
�士 | -0.433 |
osph | -0.412 |
py | -0.403 |
Token | has |
Token ID | 468 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
UCS | +2.252 |
UTF | +2.158 |
�士 | +2.139 |
osph | +2.048 |
py | +2.027 |
Neg logit contributions | |
ellar | -2.095 |
yrinth | -2.065 |
Priv | -1.724 |
Klux | -1.701 |
Balloon | -1.696 |
Token | a |
Token ID | 64 |
Feature activation | +7.24e+00 |
Pos logit contributions | |
ellar | +1.937 |
yrinth | +1.898 |
Priv | +1.601 |
Balloon | +1.544 |
--------- | +1.543 |
Neg logit contributions | |
UCS | -2.448 |
�士 | -2.376 |
UTF | -2.347 |
osph | -2.247 |
py | -2.183 |
Token | measure |
Token ID | 3953 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
ellar | +4.286 |
yrinth | +4.234 |
Priv | +3.746 |
drag | +3.685 |
Balloon | +3.568 |
Neg logit contributions | |
�士 | -5.830 |
UCS | -5.754 |
UTF | -5.698 |
osph | -5.393 |
py | -5.195 |
Token | that |
Token ID | 326 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
ellar | +2.889 |
yrinth | +2.791 |
Priv | +2.487 |
Balloon | +2.341 |
drag | +2.326 |
Neg logit contributions | |
UCS | -3.543 |
�士 | -3.471 |
UTF | -3.461 |
osph | -3.292 |
py | -3.229 |
Token | itself |
Token ID | 2346 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
ellar | +3.501 |
yrinth | +3.447 |
Priv | +3.068 |
Balloon | +2.933 |
drag | +2.893 |
Neg logit contributions | |
UCS | -4.411 |
�士 | -4.355 |
UTF | -4.337 |
osph | -4.149 |
py | -4.040 |
Token | stretched |
Token ID | 19110 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
ellar | +1.210 |
yrinth | +1.195 |
Priv | +1.018 |
Balloon | +0.993 |
drag | +0.988 |
Neg logit contributions | |
UCS | -1.465 |
�士 | -1.428 |
UTF | -1.417 |
osph | -1.349 |
py | -1.317 |
Token | the |
Token ID | 262 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
UCS | +2.606 |
UTF | +2.515 |
�士 | +2.489 |
osph | +2.388 |
py | +2.365 |
Neg logit contributions | |
ellar | -2.161 |
yrinth | -2.138 |
Priv | -1.746 |
Balloon | -1.729 |
Klux | -1.727 |
Token | bounds |
Token ID | 22303 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
ellar | +0.740 |
yrinth | +0.726 |
Priv | +0.610 |
Balloon | +0.599 |
Klux | +0.591 |
Neg logit contributions | |
UCS | -0.911 |
�士 | -0.879 |
UTF | -0.876 |
osph | -0.837 |
py | -0.826 |
Token | of |
Token ID | 286 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
UCS | +1.642 |
UTF | +1.582 |
�士 | +1.578 |
osph | +1.503 |
py | +1.486 |
Neg logit contributions | |
ellar | -1.554 |
yrinth | -1.532 |
Priv | -1.287 |
Balloon | -1.269 |
Klux | -1.269 |
Token | democratic |
Token ID | 10518 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
UCS | +0.595 |
UTF | +0.574 |
�士 | +0.572 |
osph | +0.549 |
py | +0.541 |
Neg logit contributions | |
ellar | -0.436 |
yrinth | -0.428 |
Priv | -0.352 |
Balloon | -0.345 |
Klux | -0.343 |
Token | legitimacy |
Token ID | 22726 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
ellar | +0.375 |
yrinth | +0.365 |
Priv | +0.304 |
Balloon | +0.298 |
Klux | +0.293 |
Neg logit contributions | |
UCS | -0.517 |
�士 | -0.500 |
UTF | -0.499 |
osph | -0.478 |
py | -0.471 |
Token | . |
Token ID | 13 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ellar | +0.621 |
yrinth | +0.606 |
Priv | +0.519 |
Balloon | +0.509 |
Klux | +0.503 |
Neg logit contributions | |
UCS | -0.670 |
�士 | -0.648 |
UTF | -0.641 |
osph | -0.611 |
py | -0.597 |
Token | about |
Token ID | 546 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
ellar | +2.182 |
yrinth | +2.131 |
Priv | +1.826 |
drag | +1.791 |
Balloon | +1.786 |
Neg logit contributions | |
�士 | -2.543 |
UCS | -2.529 |
UTF | -2.464 |
osph | -2.344 |
py | -2.266 |
Token | that |
Token ID | 326 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
UCS | +2.843 |
UTF | +2.705 |
�士 | +2.646 |
osph | +2.558 |
py | +2.549 |
Neg logit contributions | |
ellar | -2.527 |
yrinth | -2.504 |
Priv | -2.034 |
Klux | -2.023 |
Balloon | -2.017 |
Token | day |
Token ID | 1110 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
UCS | +3.359 |
UTF | +3.177 |
�士 | +3.086 |
py | +2.992 |
osph | +2.984 |
Neg logit contributions | |
ellar | -3.250 |
yrinth | -3.239 |
Priv | -2.643 |
Klux | -2.633 |
Balloon | -2.609 |
Token | 's |
Token ID | 338 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ellar | +2.636 |
yrinth | +2.571 |
Priv | +2.199 |
Balloon | +2.175 |
--------- | +2.163 |
Neg logit contributions | |
�士 | -3.009 |
UCS | -2.996 |
UTF | -2.941 |
osph | -2.791 |
py | -2.703 |
Token | game |
Token ID | 983 |
Feature activation | +6.21e+00 |
Pos logit contributions | |
ellar | +0.964 |
yrinth | +0.946 |
Priv | +0.803 |
Balloon | +0.785 |
Doodle | +0.780 |
Neg logit contributions | |
UCS | -1.207 |
�士 | -1.194 |
UTF | -1.180 |
osph | -1.129 |
py | -1.102 |
Token | to |
Token ID | 284 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
ellar | +3.922 |
yrinth | +3.771 |
Priv | +3.284 |
--------- | +3.269 |
drag | +3.249 |
Neg logit contributions | |
�士 | -4.909 |
UCS | -4.788 |
UTF | -4.684 |
osph | -4.493 |
pu | -4.317 |
Token | be |
Token ID | 307 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
UCS | +0.295 |
UTF | +0.284 |
�士 | +0.284 |
osph | +0.270 |
py | +0.266 |
Neg logit contributions | |
ellar | -0.264 |
yrinth | -0.260 |
Priv | -0.218 |
Balloon | -0.215 |
Klux | -0.214 |
Token | played |
Token ID | 2826 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
UCS | +4.135 |
UTF | +3.920 |
�士 | +3.878 |
py | +3.735 |
osph | +3.718 |
Neg logit contributions | |
ellar | -3.918 |
yrinth | -3.884 |
Priv | -3.174 |
Balloon | -3.140 |
Klux | -3.129 |
Token | in |
Token ID | 287 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
ellar | +0.800 |
yrinth | +0.781 |
Priv | +0.667 |
Balloon | +0.659 |
Klux | +0.650 |
Neg logit contributions | |
UCS | -0.890 |
�士 | -0.877 |
UTF | -0.860 |
osph | -0.822 |
py | -0.801 |
Token | freezing |
Token ID | 20884 |
Feature activation | +7.93e-01 |
Pos logit contributions | |
ellar | +1.413 |
yrinth | +1.385 |
Priv | +1.186 |
Balloon | +1.178 |
drag | +1.165 |
Neg logit contributions | |
UCS | -1.645 |
�士 | -1.642 |
UTF | -1.620 |
osph | -1.559 |
py | -1.511 |
Token | temperatures |
Token ID | 10101 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
ellar | +0.529 |
yrinth | +0.517 |
Priv | +0.438 |
Balloon | +0.434 |
Klux | +0.427 |
Neg logit contributions | |
UCS | -0.617 |
�士 | -0.605 |
UTF | -0.600 |
osph | -0.572 |
py | -0.562 |
Token | { |
Token ID | 1391 |
Feature activation | -6.24e+00 |
Pos logit contributions | |
UCS | +2.868 |
UTF | +2.745 |
�士 | +2.703 |
osph | +2.589 |
py | +2.579 |
Neg logit contributions | |
ellar | -2.676 |
yrinth | -2.636 |
Priv | -2.208 |
Klux | -2.187 |
Balloon | -2.176 |
Token | 1 |
Token ID | 16 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
UCS | +4.655 |
UTF | +4.473 |
�士 | +4.354 |
py | +4.239 |
osph | +4.194 |
Neg logit contributions | |
ellar | -4.343 |
yrinth | -4.270 |
Priv | -3.602 |
Klux | -3.560 |
Balloon | -3.507 |
Token | , |
Token ID | 11 |
Feature activation | -6.25e+00 |
Pos logit contributions | |
UCS | +0.384 |
�士 | +0.371 |
UTF | +0.370 |
osph | +0.353 |
py | +0.346 |
Neg logit contributions | |
ellar | -0.343 |
yrinth | -0.336 |
Priv | -0.282 |
Balloon | -0.279 |
Klux | -0.276 |
Token | 6 |
Token ID | 21 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
UCS | +4.154 |
UTF | +3.939 |
�士 | +3.835 |
osph | +3.676 |
py | +3.664 |
Neg logit contributions | |
ellar | -4.876 |
yrinth | -4.807 |
Priv | -4.092 |
Klux | -4.050 |
Balloon | -4.007 |
Token | } |
Token ID | 92 |
Feature activation | -8.21e+00 |
Pos logit contributions | |
UCS | +1.118 |
UTF | +1.075 |
�士 | +1.074 |
osph | +1.021 |
py | +1.000 |
Neg logit contributions | |
ellar | -1.135 |
yrinth | -1.116 |
Priv | -0.946 |
Balloon | -0.937 |
Klux | -0.929 |
Token | has |
Token ID | 468 |
Feature activation | -6.60e+00 |
Pos logit contributions | |
UCS | +5.817 |
UTF | +5.527 |
�士 | +5.255 |
py | +5.224 |
osph | +5.177 |
Neg logit contributions | |
ellar | -5.858 |
yrinth | -5.826 |
Klux | -4.892 |
Priv | -4.870 |
Balloon | -4.777 |
Token | valid |
Token ID | 4938 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
UCS | +4.874 |
UTF | +4.635 |
�士 | +4.496 |
osph | +4.330 |
py | +4.293 |
Neg logit contributions | |
ellar | -4.607 |
yrinth | -4.564 |
Priv | -3.798 |
Klux | -3.791 |
BW | -3.752 |
Token | N |
Token ID | 399 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
UCS | +3.970 |
UTF | +3.818 |
�士 | +3.693 |
osph | +3.561 |
py | +3.540 |
Neg logit contributions | |
ellar | -3.612 |
yrinth | -3.565 |
Klux | -3.000 |
Priv | -2.980 |
Balloon | -2.926 |
Token | Ns |
Token ID | 47503 |
Feature activation | -6.55e+00 |
Pos logit contributions | |
UCS | +3.858 |
UTF | +3.750 |
�士 | +3.674 |
osph | +3.535 |
py | +3.504 |
Neg logit contributions | |
ellar | -3.102 |
yrinth | -3.073 |
Priv | -2.555 |
Balloon | -2.509 |
Klux | -2.500 |
Token | at |
Token ID | 379 |
Feature activation | -4.78e+00 |
Pos logit contributions | |
UCS | +4.638 |
UTF | +4.420 |
�士 | +4.177 |
py | +4.120 |
osph | +4.116 |
Neg logit contributions | |
ellar | -4.779 |
yrinth | -4.778 |
Klux | -4.025 |
Priv | -3.985 |
BW | -3.892 |
Token | { |
Token ID | 1391 |
Feature activation | -7.08e+00 |
Pos logit contributions | |
UCS | +3.600 |
UTF | +3.434 |
�士 | +3.365 |
osph | +3.232 |
py | +3.215 |
Neg logit contributions | |
ellar | -3.340 |
yrinth | -3.289 |
Priv | -2.754 |
Klux | -2.731 |
BW | -2.687 |
Token | , |
Token ID | 11 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
UCS | +3.670 |
UTF | +3.511 |
�士 | +3.407 |
osph | +3.317 |
py | +3.303 |
Neg logit contributions | |
ellar | -3.702 |
yrinth | -3.672 |
Klux | -3.115 |
Priv | -3.104 |
Balloon | -3.058 |
Token | so |
Token ID | 523 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
UCS | +1.406 |
UTF | +1.347 |
�士 | +1.338 |
osph | +1.280 |
py | +1.266 |
Neg logit contributions | |
ellar | -1.297 |
yrinth | -1.277 |
Priv | -1.067 |
Klux | -1.055 |
Balloon | -1.052 |
Token | far |
Token ID | 1290 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
ellar | +0.784 |
yrinth | +0.763 |
Priv | +0.629 |
Balloon | +0.617 |
Klux | +0.606 |
Neg logit contributions | |
UCS | -1.108 |
�士 | -1.087 |
UTF | -1.077 |
osph | -1.032 |
py | -1.011 |
Token | it |
Token ID | 340 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ellar | +1.370 |
yrinth | +1.342 |
Priv | +1.141 |
Balloon | +1.130 |
Doodle | +1.097 |
Neg logit contributions | |
UCS | -1.641 |
�士 | -1.607 |
UTF | -1.598 |
osph | -1.530 |
py | -1.488 |
Token | appears |
Token ID | 3568 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
UCS | +1.174 |
UTF | +1.129 |
�士 | +1.127 |
osph | +1.076 |
py | +1.060 |
Neg logit contributions | |
ellar | -1.035 |
yrinth | -1.018 |
Priv | -0.852 |
Balloon | -0.840 |
Klux | -0.835 |
Token | as |
Token ID | 355 |
Feature activation | -7.68e+00 |
Pos logit contributions | |
ellar | +0.988 |
yrinth | +0.965 |
Priv | +0.826 |
Balloon | +0.816 |
drag | +0.793 |
Neg logit contributions | |
UCS | -1.096 |
�士 | -1.074 |
UTF | -1.071 |
osph | -1.021 |
py | -0.993 |
Token | though |
Token ID | 996 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
UCS | +4.139 |
UTF | +3.788 |
�士 | +3.713 |
py | +3.574 |
osph | +3.466 |
Neg logit contributions | |
ellar | -6.926 |
yrinth | -6.888 |
Klux | -6.010 |
Balloon | -5.908 |
BW | -5.881 |
Token | Ubuntu |
Token ID | 14949 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
ellar | +1.154 |
yrinth | +1.128 |
Priv | +0.964 |
Balloon | +0.952 |
Doodle | +0.927 |
Neg logit contributions | |
UCS | -1.313 |
�士 | -1.291 |
UTF | -1.284 |
osph | -1.225 |
py | -1.191 |
Token | and |
Token ID | 290 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
UCS | +0.213 |
UTF | +0.206 |
�士 | +0.206 |
osph | +0.196 |
py | +0.193 |
Neg logit contributions | |
ellar | -0.192 |
yrinth | -0.188 |
Priv | -0.159 |
Balloon | -0.156 |
Klux | -0.154 |
Token | its |
Token ID | 663 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
ellar | +1.736 |
yrinth | +1.695 |
Priv | +1.466 |
Balloon | +1.439 |
drag | +1.403 |
Neg logit contributions | |
UCS | -1.987 |
�士 | -1.977 |
UTF | -1.960 |
osph | -1.877 |
py | -1.819 |
Token | community |
Token ID | 2055 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
ellar | +1.601 |
yrinth | +1.530 |
Priv | +1.337 |
Balloon | +1.302 |
Doodle | +1.288 |
Neg logit contributions | |
�士 | -1.833 |
UCS | -1.830 |
UTF | -1.808 |
osph | -1.732 |
py | -1.676 |
Token | it |
Token ID | 340 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
UCS | +2.807 |
UTF | +2.655 |
�士 | +2.622 |
osph | +2.534 |
py | +2.504 |
Neg logit contributions | |
ellar | -2.828 |
yrinth | -2.765 |
Klux | -2.308 |
Priv | -2.304 |
Balloon | -2.288 |
Token | is |
Token ID | 318 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
ellar | +0.915 |
yrinth | +0.906 |
Priv | +0.760 |
Balloon | +0.748 |
Klux | +0.739 |
Neg logit contributions | |
UCS | -0.998 |
�士 | -0.967 |
UTF | -0.959 |
osph | -0.906 |
py | -0.888 |
Token | one |
Token ID | 530 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
UCS | +1.197 |
UTF | +1.152 |
�士 | +1.151 |
osph | +1.096 |
py | +1.080 |
Neg logit contributions | |
ellar | -1.079 |
yrinth | -1.062 |
Priv | -0.892 |
Balloon | -0.878 |
Klux | -0.873 |
Token | of |
Token ID | 286 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
UCS | +3.784 |
UTF | +3.605 |
�士 | +3.558 |
osph | +3.426 |
py | +3.402 |
Neg logit contributions | |
ellar | -3.929 |
yrinth | -3.859 |
Priv | -3.275 |
Klux | -3.266 |
Balloon | -3.240 |
Token | the |
Token ID | 262 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
ellar | +0.070 |
yrinth | +0.069 |
Priv | +0.058 |
Balloon | +0.057 |
--------- | +0.056 |
Neg logit contributions | |
UCS | -0.082 |
UTF | -0.079 |
�士 | -0.079 |
osph | -0.076 |
py | -0.074 |
Token | few |
Token ID | 1178 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
UCS | +0.496 |
UTF | +0.478 |
�士 | +0.477 |
osph | +0.454 |
py | +0.446 |
Neg logit contributions | |
ellar | -0.464 |
yrinth | -0.457 |
Priv | -0.386 |
Balloon | -0.380 |
Klux | -0.377 |
Token | that |
Token ID | 326 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
UCS | +1.870 |
UTF | +1.800 |
�士 | +1.793 |
osph | +1.719 |
py | +1.698 |
Neg logit contributions | |
ellar | -1.476 |
yrinth | -1.449 |
Priv | -1.196 |
Balloon | -1.178 |
Klux | -1.173 |
Token | my |
Token ID | 616 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
UCS | +2.622 |
UTF | +2.498 |
�士 | +2.470 |
osph | +2.372 |
py | +2.346 |
Neg logit contributions | |
ellar | -2.737 |
yrinth | -2.677 |
Priv | -2.267 |
Klux | -2.255 |
Balloon | -2.247 |
Token | closest |
Token ID | 11706 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
UCS | +2.441 |
UTF | +2.327 |
�士 | +2.310 |
osph | +2.211 |
py | +2.190 |
Neg logit contributions | |
ellar | -2.403 |
yrinth | -2.361 |
Priv | -1.981 |
Klux | -1.969 |
Balloon | -1.960 |
Token | gaming |
Token ID | 7776 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
ellar | +0.647 |
yrinth | +0.633 |
Priv | +0.543 |
Balloon | +0.528 |
Klux | +0.521 |
Neg logit contributions | |
UCS | -0.692 |
UTF | -0.673 |
�士 | -0.671 |
osph | -0.641 |
py | -0.625 |
Token | mates |
Token ID | 27973 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
UCS | +1.947 |
UTF | +1.861 |
�士 | +1.855 |
osph | +1.768 |
py | +1.750 |
Neg logit contributions | |
ellar | -1.867 |
yrinth | -1.839 |
Priv | -1.542 |
Balloon | -1.526 |
Klux | -1.522 |
Token | will |
Token ID | 481 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
UCS | +2.375 |
UTF | +2.252 |
�士 | +2.226 |
osph | +2.129 |
py | +2.123 |
Neg logit contributions | |
ellar | -2.914 |
yrinth | -2.866 |
Priv | -2.461 |
Klux | -2.435 |
Balloon | -2.426 |
Token | also |
Token ID | 635 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
UCS | +1.743 |
UTF | +1.659 |
�士 | +1.640 |
osph | +1.579 |
py | +1.565 |
Neg logit contributions | |
ellar | -1.881 |
yrinth | -1.851 |
Priv | -1.574 |
Klux | -1.561 |
Balloon | -1.546 |
Token | need |
Token ID | 761 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
UCS | +0.516 |
UTF | +0.494 |
�士 | +0.494 |
osph | +0.466 |
py | +0.457 |
Neg logit contributions | |
ellar | -0.603 |
yrinth | -0.594 |
Priv | -0.511 |
Balloon | -0.505 |
Klux | -0.500 |
Token | to |
Token ID | 284 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
UCS | +0.268 |
UTF | +0.258 |
�士 | +0.256 |
osph | +0.245 |
py | +0.240 |
Neg logit contributions | |
ellar | -0.258 |
yrinth | -0.252 |
Priv | -0.213 |
Balloon | -0.210 |
Klux | -0.209 |
Token | detach |
Token ID | 48224 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
UCS | +2.224 |
UTF | +2.124 |
�士 | +2.095 |
osph | +2.027 |
py | +2.006 |
Neg logit contributions | |
ellar | -2.213 |
yrinth | -2.181 |
Priv | -1.829 |
Klux | -1.813 |
Balloon | -1.803 |
Token | the |
Token ID | 262 |
Feature activation | -5.19e+00 |
Pos logit contributions | |
UCS | +2.107 |
UTF | +2.025 |
�士 | +2.020 |
osph | +1.929 |
py | +1.902 |
Neg logit contributions | |
ellar | -1.852 |
yrinth | -1.822 |
Priv | -1.523 |
Balloon | -1.500 |
Klux | -1.495 |
Token | cables |
Token ID | 18018 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
UCS | +3.987 |
UTF | +3.770 |
�士 | +3.746 |
osph | +3.587 |
py | +3.584 |
Neg logit contributions | |
ellar | -3.561 |
yrinth | -3.519 |
Klux | -2.886 |
Priv | -2.878 |
Doodle | -2.837 |
Token | leading |
Token ID | 3756 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
UCS | +1.583 |
UTF | +1.516 |
�士 | +1.505 |
osph | +1.440 |
py | +1.426 |
Neg logit contributions | |
ellar | -1.530 |
yrinth | -1.509 |
Priv | -1.267 |
Balloon | -1.250 |
Klux | -1.250 |
Token | to |
Token ID | 284 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
UCS | +1.374 |
UTF | +1.319 |
�士 | +1.316 |
osph | +1.251 |
py | +1.230 |
Neg logit contributions | |
ellar | -1.379 |
yrinth | -1.356 |
Priv | -1.150 |
Balloon | -1.135 |
Klux | -1.128 |
Token | the |
Token ID | 262 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
UCS | +0.081 |
UTF | +0.079 |
�士 | +0.078 |
osph | +0.075 |
py | +0.073 |
Neg logit contributions | |
ellar | -0.068 |
yrinth | -0.066 |
Priv | -0.056 |
Balloon | -0.055 |
drag | -0.054 |
Token | traction |
Token ID | 23692 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
UCS | +1.821 |
UTF | +1.746 |
�士 | +1.739 |
osph | +1.663 |
py | +1.643 |
Neg logit contributions | |
ellar | -1.608 |
yrinth | -1.582 |
Priv | -1.316 |
Klux | -1.298 |
Balloon | -1.297 |
Token | ? |
Token ID | 30 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
UCS | +3.657 |
UTF | +3.475 |
�士 | +3.404 |
py | +3.310 |
osph | +3.287 |
Neg logit contributions | |
yrinth | -3.903 |
ellar | -3.887 |
Priv | -3.256 |
Klux | -3.251 |
Balloon | -3.232 |
Token | Think |
Token ID | 11382 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
UCS | +2.107 |
UTF | +2.010 |
�士 | +1.990 |
osph | +1.898 |
py | +1.894 |
Neg logit contributions | |
ellar | -1.995 |
yrinth | -1.973 |
Klux | -1.628 |
Priv | -1.624 |
Balloon | -1.609 |
Token | again |
Token ID | 757 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
ellar | +1.948 |
yrinth | +1.876 |
Priv | +1.521 |
Balloon | +1.508 |
BW | +1.468 |
Neg logit contributions | |
UCS | -3.473 |
�士 | -3.382 |
UTF | -3.368 |
osph | -3.248 |
py | -3.166 |
Token | . |
Token ID | 13 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
ellar | +3.317 |
yrinth | +3.243 |
Priv | +2.834 |
Balloon | +2.778 |
Doodle | +2.759 |
Neg logit contributions | |
�士 | -3.777 |
UCS | -3.761 |
UTF | -3.669 |
osph | -3.536 |
py | -3.372 |
Token | Here |
Token ID | 3423 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
ellar | +0.243 |
yrinth | +0.238 |
Priv | +0.205 |
Balloon | +0.200 |
Doodle | +0.197 |
Neg logit contributions | |
UCS | -0.278 |
�士 | -0.271 |
UTF | -0.270 |
osph | -0.258 |
py | -0.251 |
Token | 's |
Token ID | 338 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
UCS | +2.684 |
UTF | +2.557 |
�士 | +2.549 |
osph | +2.438 |
py | +2.410 |
Neg logit contributions | |
ellar | -2.632 |
yrinth | -2.599 |
Priv | -2.177 |
Balloon | -2.156 |
Klux | -2.154 |
Token | how |
Token ID | 703 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
UCS | +1.580 |
UTF | +1.512 |
�士 | +1.507 |
osph | +1.440 |
py | +1.421 |
Neg logit contributions | |
ellar | -1.464 |
yrinth | -1.442 |
Priv | -1.205 |
Balloon | -1.190 |
Klux | -1.187 |
Token | Wales |
Token ID | 11769 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
UCS | +0.980 |
UTF | +0.943 |
�士 | +0.941 |
osph | +0.897 |
py | +0.883 |
Neg logit contributions | |
ellar | -0.911 |
yrinth | -0.896 |
Priv | -0.755 |
Balloon | -0.744 |
Klux | -0.740 |
Token | lined |
Token ID | 16566 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
ellar | +2.096 |
yrinth | +2.049 |
Priv | +1.751 |
Balloon | +1.732 |
drag | +1.732 |
Neg logit contributions | |
UCS | -2.303 |
�士 | -2.248 |
UTF | -2.245 |
osph | -2.113 |
py | -2.044 |
Token | up |
Token ID | 510 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
UCS | +0.162 |
�士 | +0.157 |
UTF | +0.157 |
osph | +0.150 |
py | +0.147 |
Neg logit contributions | |
ellar | -0.129 |
yrinth | -0.126 |
Priv | -0.105 |
Balloon | -0.103 |
Klux | -0.103 |
Token | for |
Token ID | 329 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
ellar | +2.644 |
yrinth | +2.567 |
Priv | +2.259 |
drag | +2.202 |
Balloon | +2.194 |
Neg logit contributions | |
�士 | -3.198 |
UCS | -3.112 |
UTF | -3.088 |
osph | -2.971 |
pu | -2.816 |
Token | loans |
Token ID | 10021 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ellar | +3.044 |
yrinth | +2.984 |
Priv | +2.738 |
Balloon | +2.620 |
drag | +2.554 |
Neg logit contributions | |
�士 | -2.986 |
UCS | -2.983 |
UTF | -2.917 |
osph | -2.732 |
py | -2.671 |
Token | are |
Token ID | 389 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
UCS | +0.842 |
UTF | +0.803 |
�士 | +0.797 |
osph | +0.764 |
py | +0.752 |
Neg logit contributions | |
ellar | -0.916 |
yrinth | -0.903 |
Priv | -0.766 |
Balloon | -0.756 |
Klux | -0.756 |
Token | Vi |
Token ID | 16049 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
ellar | +3.393 |
yrinth | +3.348 |
Priv | +3.052 |
Balloon | +2.875 |
drag | +2.817 |
Neg logit contributions | |
�士 | -3.938 |
UCS | -3.898 |
UTF | -3.888 |
osph | -3.665 |
py | -3.583 |
Token | aches |
Token ID | 3694 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
ellar | +2.133 |
yrinth | +2.083 |
Priv | +1.743 |
Klux | +1.707 |
Balloon | +1.698 |
Neg logit contributions | |
UCS | -2.708 |
�士 | -2.648 |
UTF | -2.577 |
osph | -2.426 |
py | -2.402 |
Token | lav |
Token ID | 18809 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
ellar | +1.065 |
yrinth | +1.005 |
Priv | +0.683 |
Balloon | +0.598 |
Klux | +0.594 |
Neg logit contributions | |
UCS | -3.914 |
�士 | -3.840 |
UTF | -3.822 |
osph | -3.681 |
py | -3.590 |
Token | Pl |
Token ID | 1345 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
ellar | +3.388 |
yrinth | +3.317 |
Priv | +2.970 |
Balloon | +2.833 |
drag | +2.734 |
Neg logit contributions | |
UCS | -3.784 |
�士 | -3.746 |
UTF | -3.707 |
osph | -3.437 |
py | -3.354 |
Token | ak |
Token ID | 461 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
UCS | +8.544 |
osph | +8.504 |
UTF | +8.321 |
py | +8.286 |
pu | +7.979 |
Neg logit contributions | |
yrinth | -6.980 |
ellar | -6.952 |
Doodle | -5.880 |
Balloon | -5.864 |
Priv | -5.759 |
Token | as |
Token ID | 292 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
UCS | +0.454 |
�士 | +0.439 |
UTF | +0.436 |
osph | +0.408 |
py | +0.402 |
Neg logit contributions | |
ellar | -0.418 |
yrinth | -0.414 |
Priv | -0.347 |
Balloon | -0.340 |
Klux | -0.339 |
Token | ov |
Token ID | 709 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ellar | +0.792 |
yrinth | +0.775 |
Priv | +0.655 |
Balloon | +0.637 |
Klux | +0.632 |
Neg logit contributions | |
UCS | -0.940 |
�士 | -0.913 |
UTF | -0.905 |
osph | -0.851 |
py | -0.833 |
Token | , |
Token ID | 11 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
ellar | +0.699 |
yrinth | +0.680 |
Priv | +0.582 |
Balloon | +0.567 |
Klux | +0.554 |
Neg logit contributions | |
UCS | -0.820 |
�士 | -0.791 |
UTF | -0.790 |
osph | -0.743 |
py | -0.731 |
Token | Vol |
Token ID | 4709 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
ellar | +3.195 |
yrinth | +3.169 |
Priv | +2.850 |
Balloon | +2.676 |
drag | +2.640 |
Neg logit contributions | |
UCS | -3.989 |
�士 | -3.969 |
UTF | -3.944 |
osph | -3.696 |
py | -3.645 |
Token | is |
Token ID | 318 |
Feature activation | -5.01e+00 |
Pos logit contributions | |
UCS | +7.023 |
UTF | +6.742 |
�士 | +6.532 |
osph | +6.323 |
py | +6.196 |
Neg logit contributions | |
ellar | -7.470 |
yrinth | -7.421 |
Doodle | -6.171 |
BW | -6.064 |
Balloon | -6.029 |
Token | now |
Token ID | 783 |
Feature activation | -6.56e+00 |
Pos logit contributions | |
UCS | +3.792 |
UTF | +3.597 |
�士 | +3.585 |
osph | +3.432 |
py | +3.392 |
Neg logit contributions | |
ellar | -3.496 |
yrinth | -3.440 |
Priv | -2.805 |
Klux | -2.793 |
BW | -2.789 |
Token | the |
Token ID | 262 |
Feature activation | -7.88e+00 |
Pos logit contributions | |
UCS | +4.834 |
UTF | +4.571 |
�士 | +4.564 |
osph | +4.357 |
py | +4.309 |
Neg logit contributions | |
ellar | -4.645 |
yrinth | -4.592 |
Balloon | -3.748 |
Priv | -3.736 |
BW | -3.729 |
Token | Party |
Token ID | 3615 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
UCS | +5.397 |
�士 | +5.095 |
UTF | +5.009 |
osph | +4.900 |
py | +4.789 |
Neg logit contributions | |
yrinth | -5.863 |
ellar | -5.842 |
BW | -4.828 |
Priv | -4.767 |
--------- | -4.765 |
Token | of |
Token ID | 286 |
Feature activation | -7.95e+00 |
Pos logit contributions | |
UCS | +6.623 |
�士 | +6.357 |
UTF | +6.293 |
osph | +6.028 |
py | +5.921 |
Neg logit contributions | |
yrinth | -7.722 |
ellar | -7.704 |
BW | -6.485 |
Balloon | -6.436 |
Doodle | -6.409 |
Token | Trump |
Token ID | 1301 |
Feature activation | -1.36e+01 |
Pos logit contributions | |
UCS | +5.831 |
UTF | +5.504 |
�士 | +5.454 |
osph | +5.217 |
py | +5.198 |
Neg logit contributions | |
ellar | -5.555 |
yrinth | -5.495 |
BW | -4.567 |
--------- | -4.488 |
Doodle | -4.422 |
Token | . |
Token ID | 13 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
UCS | +8.155 |
UTF | +7.567 |
�士 | +7.336 |
osph | +7.243 |
py | +7.155 |
Neg logit contributions | |
yrinth | -10.445 |
ellar | -10.369 |
Doodle | -8.572 |
Klux | -8.546 |
BW | -8.538 |
Token | � |
Token ID | 447 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
UCS | +4.011 |
UTF | +3.803 |
�士 | +3.736 |
py | +3.574 |
osph | +3.552 |
Neg logit contributions | |
ellar | -3.998 |
yrinth | -3.948 |
Klux | -3.254 |
Balloon | -3.197 |
Priv | -3.182 |
Token | � |
Token ID | 251 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
UCS | +0.169 |
UTF | +0.162 |
�士 | +0.159 |
osph | +0.155 |
py | +0.153 |
Neg logit contributions | |
ellar | -0.120 |
yrinth | -0.119 |
Priv | -0.097 |
Balloon | -0.095 |
Klux | -0.094 |
Token |
|
Token ID | 198 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
UCS | +4.258 |
UTF | +4.042 |
�士 | +3.962 |
py | +3.791 |
osph | +3.787 |
Neg logit contributions | |
ellar | -4.247 |
yrinth | -4.187 |
Klux | -3.441 |
Balloon | -3.412 |
Doodle | -3.400 |
Token |
|
Token ID | 198 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
UCS | +2.300 |
UTF | +2.196 |
py | +2.081 |
osph | +2.015 |
pu | +2.000 |
Neg logit contributions | |
yrinth | -2.619 |
ellar | -2.545 |
Klux | -2.146 |
Balloon | -2.121 |
Doodle | -2.103 |
Token | again |
Token ID | 757 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
ellar | +1.338 |
yrinth | +1.274 |
Priv | +0.992 |
Balloon | +0.946 |
--------- | +0.941 |
Neg logit contributions | |
UCS | -2.973 |
�士 | -2.956 |
UTF | -2.900 |
osph | -2.788 |
py | -2.748 |
Token | that |
Token ID | 326 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
UCS | +2.374 |
UTF | +2.228 |
py | +2.121 |
osph | +2.113 |
�士 | +2.087 |
Neg logit contributions | |
yrinth | -2.835 |
ellar | -2.827 |
Klux | -2.388 |
Priv | -2.367 |
Balloon | -2.364 |
Token | the |
Token ID | 262 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
UCS | +2.572 |
UTF | +2.428 |
py | +2.291 |
�士 | +2.284 |
osph | +2.284 |
Neg logit contributions | |
yrinth | -2.627 |
ellar | -2.590 |
Klux | -2.156 |
Priv | -2.140 |
Balloon | -2.132 |
Token | old |
Token ID | 1468 |
Feature activation | -8.69e+00 |
Pos logit contributions | |
UCS | +3.541 |
UTF | +3.406 |
�士 | +3.277 |
osph | +3.176 |
py | +3.171 |
Neg logit contributions | |
ellar | -3.560 |
yrinth | -3.548 |
Priv | -2.939 |
Balloon | -2.939 |
Klux | -2.916 |
Token | address |
Token ID | 2209 |
Feature activation | -9.83e+00 |
Pos logit contributions | |
UCS | +6.022 |
UTF | +5.738 |
py | +5.447 |
osph | +5.432 |
pu | +5.268 |
Neg logit contributions | |
yrinth | -6.459 |
ellar | -6.341 |
BW | -5.271 |
Klux | -5.268 |
Balloon | -5.231 |
Token | https |
Token ID | 3740 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
UCS | +6.569 |
UTF | +6.247 |
�士 | +6.052 |
py | +5.845 |
osph | +5.733 |
Neg logit contributions | |
ellar | -7.440 |
yrinth | -7.312 |
Klux | -6.249 |
--------- | -6.109 |
Doodle | -6.108 |
Token | :// |
Token ID | 1378 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
UCS | +6.251 |
UTF | +6.165 |
py | +5.577 |
pu | +5.474 |
osph | +5.406 |
Neg logit contributions | |
yrinth | -10.621 |
ellar | -10.023 |
Balloon | -8.956 |
Doodle | -8.775 |
Klux | -8.769 |
Token | . |
Token ID | 764 |
Feature activation | -6.42e+00 |
Pos logit contributions | |
UCS | +7.376 |
UTF | +7.111 |
�士 | +6.831 |
py | +6.614 |
osph | +6.520 |
Neg logit contributions | |
yrinth | -8.748 |
ellar | -8.727 |
Klux | -7.346 |
Balloon | -7.317 |
BW | -7.249 |
Token | nice |
Token ID | 44460 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
UCS | +3.294 |
UTF | +3.150 |
�士 | +3.031 |
py | +2.978 |
osph | +2.885 |
Neg logit contributions | |
ellar | -6.018 |
yrinth | -5.926 |
Priv | -5.214 |
Balloon | -5.173 |
Klux | -5.126 |
Token | hash |
Token ID | 17831 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
UCS | +1.400 |
UTF | +1.357 |
�士 | +1.304 |
osph | +1.295 |
py | +1.290 |
Neg logit contributions | |
ellar | -1.426 |
yrinth | -1.416 |
Priv | -1.201 |
Balloon | -1.191 |
Doodle | -1.168 |
Token | . |
Token ID | 13 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ellar | +2.200 |
yrinth | +2.110 |
Priv | +1.855 |
Balloon | +1.801 |
--------- | +1.794 |
Neg logit contributions | |
�士 | -2.421 |
UCS | -2.388 |
UTF | -2.298 |
osph | -2.215 |
py | -2.132 |
Token | days |
Token ID | 1528 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
UCS | +0.026 |
�士 | +0.026 |
UTF | +0.025 |
osph | +0.024 |
py | +0.024 |
Neg logit contributions | |
ellar | -0.022 |
yrinth | -0.021 |
Priv | -0.018 |
Balloon | -0.018 |
Klux | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
ellar | +1.825 |
yrinth | +1.773 |
Priv | +1.516 |
Balloon | +1.501 |
drag | +1.484 |
Neg logit contributions | |
UCS | -2.092 |
�士 | -2.065 |
UTF | -2.022 |
osph | -1.929 |
py | -1.872 |
Token | implementing |
Token ID | 15427 |
Feature activation | -4.91e+00 |
Pos logit contributions | |
UCS | +1.473 |
UTF | +1.408 |
�士 | +1.394 |
osph | +1.335 |
py | +1.321 |
Neg logit contributions | |
ellar | -1.450 |
yrinth | -1.427 |
Priv | -1.200 |
Klux | -1.186 |
Balloon | -1.185 |
Token | methods |
Token ID | 5050 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
UCS | +3.697 |
UTF | +3.506 |
�士 | +3.448 |
osph | +3.309 |
py | +3.305 |
Neg logit contributions | |
ellar | -3.442 |
yrinth | -3.376 |
Klux | -2.807 |
Priv | -2.782 |
Balloon | -2.771 |
Token | add |
Token ID | 751 |
Feature activation | -8.65e+00 |
Pos logit contributions | |
UCS | +2.835 |
UTF | +2.704 |
�士 | +2.656 |
osph | +2.563 |
py | +2.560 |
Neg logit contributions | |
ellar | -2.933 |
yrinth | -2.905 |
Klux | -2.435 |
Priv | -2.435 |
Balloon | -2.424 |
Token | Points |
Token ID | 40710 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
UCS | +6.546 |
UTF | +6.377 |
�士 | +6.127 |
py | +6.082 |
osph | +5.985 |
Neg logit contributions | |
ellar | -5.691 |
yrinth | -5.645 |
Balloon | -4.628 |
Klux | -4.590 |
Priv | -4.511 |
Token | ( |
Token ID | 7 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
UCS | +7.780 |
UTF | +7.671 |
py | +7.365 |
�士 | +7.268 |
osph | +7.026 |
Neg logit contributions | |
ellar | -8.636 |
yrinth | -8.572 |
Klux | -7.205 |
Doodle | -7.022 |
Balloon | -7.020 |
Token | user |
Token ID | 7220 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
UCS | +1.035 |
�士 | +0.995 |
UTF | +0.994 |
osph | +0.950 |
py | +0.934 |
Neg logit contributions | |
ellar | -0.873 |
yrinth | -0.859 |
Priv | -0.716 |
Balloon | -0.705 |
Klux | -0.700 |
Token | , |
Token ID | 11 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
UCS | +0.108 |
�士 | +0.104 |
UTF | +0.103 |
osph | +0.099 |
py | +0.097 |
Neg logit contributions | |
ellar | -0.096 |
yrinth | -0.095 |
Priv | -0.080 |
Balloon | -0.079 |
Klux | -0.078 |
Token | points |
Token ID | 2173 |
Feature activation | -5.20e+00 |
Pos logit contributions | |
UCS | +1.502 |
UTF | +1.443 |
�士 | +1.439 |
osph | +1.373 |
py | +1.353 |
Neg logit contributions | |
ellar | -1.385 |
yrinth | -1.363 |
Priv | -1.145 |
Balloon | -1.129 |
Klux | -1.124 |
Token | ) |
Token ID | 8 |
Feature activation | -7.27e+00 |
Pos logit contributions | |
UCS | +3.894 |
UTF | +3.782 |
�士 | +3.693 |
py | +3.577 |
osph | +3.558 |
Neg logit contributions | |
ellar | -3.598 |
yrinth | -3.571 |
Priv | -2.966 |
Klux | -2.941 |
Doodle | -2.910 |
Token | }, |
Token ID | 5512 |
Feature activation | -7.99e+00 |
Pos logit contributions | |
UCS | +2.801 |
UTF | +2.662 |
�士 | +2.637 |
osph | +2.501 |
py | +2.481 |
Neg logit contributions | |
ellar | -3.398 |
yrinth | -3.359 |
Priv | -2.894 |
Klux | -2.845 |
Balloon | -2.841 |
Token | {{ |
Token ID | 22935 |
Feature activation | -6.74e+00 |
Pos logit contributions | |
UCS | +5.127 |
UTF | +4.813 |
�士 | +4.652 |
py | +4.474 |
osph | +4.451 |
Neg logit contributions | |
ellar | -6.336 |
yrinth | -6.256 |
Priv | -5.334 |
Klux | -5.321 |
BW | -5.209 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
UCS | +4.433 |
UTF | +4.330 |
�士 | +4.155 |
py | +4.060 |
osph | +4.013 |
Neg logit contributions | |
ellar | -5.204 |
yrinth | -5.140 |
Priv | -4.430 |
Balloon | -4.332 |
Doodle | -4.308 |
Token | , |
Token ID | 11 |
Feature activation | -7.17e+00 |
Pos logit contributions | |
UCS | +1.451 |
UTF | +1.392 |
�士 | +1.378 |
osph | +1.321 |
py | +1.306 |
Neg logit contributions | |
ellar | -1.376 |
yrinth | -1.358 |
Priv | -1.143 |
Balloon | -1.123 |
Klux | -1.123 |
Token | 6 |
Token ID | 718 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
UCS | +4.621 |
UTF | +4.365 |
�士 | +4.175 |
py | +4.022 |
osph | +3.992 |
Neg logit contributions | |
ellar | -5.754 |
yrinth | -5.647 |
Klux | -4.776 |
Priv | -4.765 |
Doodle | -4.665 |
Token | }, |
Token ID | 5512 |
Feature activation | -1.26e+01 |
Pos logit contributions | |
UCS | +1.868 |
UTF | +1.768 |
�士 | +1.758 |
osph | +1.646 |
py | +1.621 |
Neg logit contributions | |
ellar | -2.975 |
yrinth | -2.940 |
Priv | -2.577 |
Balloon | -2.544 |
Klux | -2.539 |
Token | { |
Token ID | 1391 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
UCS | +7.679 |
UTF | +7.028 |
�士 | +6.941 |
py | +6.641 |
osph | +6.473 |
Neg logit contributions | |
ellar | -9.891 |
yrinth | -9.630 |
Klux | -8.362 |
Priv | -8.303 |
BW | -8.164 |
Token | 1 |
Token ID | 16 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
UCS | +6.504 |
UTF | +6.355 |
�士 | +6.086 |
py | +5.953 |
osph | +5.821 |
Neg logit contributions | |
ellar | -7.749 |
yrinth | -7.713 |
Priv | -6.656 |
Klux | -6.506 |
Balloon | -6.469 |
Token | , |
Token ID | 11 |
Feature activation | -8.46e+00 |
Pos logit contributions | |
UCS | +1.426 |
UTF | +1.365 |
py | +1.289 |
�士 | +1.280 |
osph | +1.277 |
Neg logit contributions | |
yrinth | -1.506 |
ellar | -1.493 |
Priv | -1.250 |
Klux | -1.243 |
Balloon | -1.228 |
Token | 7 |
Token ID | 767 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
UCS | +4.941 |
UTF | +4.593 |
�士 | +4.364 |
py | +4.241 |
osph | +4.166 |
Neg logit contributions | |
ellar | -7.247 |
yrinth | -7.137 |
Klux | -6.121 |
Priv | -6.069 |
BW | -5.954 |
Token | }, |
Token ID | 5512 |
Feature activation | -9.30e+00 |
Pos logit contributions | |
UCS | +0.660 |
�士 | +0.628 |
UTF | +0.628 |
osph | +0.590 |
py | +0.573 |
Neg logit contributions | |
ellar | -1.017 |
yrinth | -1.001 |
Priv | -0.874 |
Balloon | -0.868 |
Klux | -0.861 |