Token | and |
Token ID | 290 |
Feature activation | +9.35e-03 |
Pos logit contributions | |
iche | +0.032 |
aster | +0.032 |
bell | +0.032 |
use | +0.031 |
ues | +0.030 |
Neg logit contributions | |
Bob | -0.040 |
friends | -0.039 |
Luis | -0.038 |
Andy | -0.037 |
strength | -0.037 |
Token | make |
Token ID | 787 |
Feature activation | +7.05e-03 |
Pos logit contributions | |
iche | +0.013 |
ues | +0.013 |
aster | +0.013 |
use | +0.013 |
bell | +0.013 |
Neg logit contributions | |
Bob | -0.015 |
Luis | -0.014 |
Andy | -0.014 |
strength | -0.014 |
friends | -0.014 |
Token | it |
Token ID | 340 |
Feature activation | +8.40e-03 |
Pos logit contributions | |
use | +0.013 |
bell | +0.012 |
iche | +0.012 |
ues | +0.012 |
aster | +0.012 |
Neg logit contributions | |
Bob | -0.009 |
Luis | -0.009 |
Andy | -0.009 |
friends | -0.008 |
strength | -0.008 |
Token | look |
Token ID | 804 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
use | +0.012 |
ues | +0.012 |
aster | +0.012 |
iche | +0.012 |
bell | +0.012 |
Neg logit contributions | |
Bob | -0.013 |
friends | -0.013 |
himself | -0.012 |
strength | -0.012 |
Andy | -0.012 |
Token | new |
Token ID | 649 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
aster | +0.082 |
use | +0.079 |
iche | +0.075 |
Amen | +0.072 |
ven | +0.071 |
Neg logit contributions | |
friends | -0.044 |
Bob | -0.041 |
iring | -0.040 |
strength | -0.040 |
himself | -0.038 |
Token | again |
Token ID | 757 |
Feature activation | +6.41e-02 |
Pos logit contributions | |
iche | +0.032 |
aster | +0.032 |
use | +0.032 |
bell | +0.031 |
ues | +0.031 |
Neg logit contributions | |
Bob | -0.034 |
Luis | -0.032 |
Andy | -0.031 |
strength | -0.031 |
iring | -0.030 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
bell | +0.068 |
iche | +0.066 |
ues | +0.066 |
aster | +0.064 |
use | +0.062 |
Neg logit contributions | |
Bob | -0.126 |
friends | -0.121 |
Andy | -0.116 |
iring | -0.113 |
Luis | -0.113 |
Token | |
Token ID | 220 |
Feature activation | +4.81e-03 |
Pos logit contributions | |
ues | +0.030 |
use | +0.030 |
iche | +0.030 |
bell | +0.029 |
aster | +0.029 |
Neg logit contributions | |
Bob | -0.018 |
Andy | -0.017 |
Luis | -0.017 |
Zig | -0.015 |
strength | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +3.04e-03 |
Pos logit contributions | |
iche | +0.007 |
ues | +0.007 |
bell | +0.007 |
use | +0.007 |
aster | +0.007 |
Neg logit contributions | |
Luis | -0.007 |
Bob | -0.007 |
strength | -0.007 |
Andy | -0.007 |
branches | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +5.01e-03 |
Pos logit contributions | |
iche | +0.005 |
use | +0.005 |
aster | +0.005 |
bell | +0.005 |
ues | +0.005 |
Neg logit contributions | |
Bob | -0.004 |
Luis | -0.004 |
Andy | -0.004 |
strength | -0.004 |
iring | -0.004 |
Token | Tim |
Token ID | 14967 |
Feature activation | -6.41e-03 |
Pos logit contributions | |
use | +0.011 |
iche | +0.011 |
ues | +0.010 |
bell | +0.010 |
aster | +0.010 |
Neg logit contributions | |
Bob | -0.005 |
Andy | -0.004 |
Luis | -0.004 |
iring | -0.004 |
branches | -0.004 |
Token | 's |
Token ID | 338 |
Feature activation | +6.05e-03 |
Pos logit contributions | |
use | +0.007 |
iche | +0.007 |
wasteful | +0.007 |
ours | +0.007 |
draws | +0.007 |
Neg logit contributions | |
Bob | -0.017 |
Luis | -0.016 |
Flash | -0.016 |
Zig | -0.016 |
iring | -0.016 |
Token | important |
Token ID | 1593 |
Feature activation | +6.69e-04 |
Pos logit contributions | |
iche | +0.008 |
use | +0.008 |
aster | +0.008 |
ues | +0.008 |
bell | +0.008 |
Neg logit contributions | |
Bob | -0.010 |
Luis | -0.010 |
Andy | -0.009 |
iring | -0.009 |
Flash | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
ues | +0.001 |
use | +0.001 |
iche | +0.001 |
bell | +0.001 |
aster | +0.001 |
Neg logit contributions | |
Luis | -0.001 |
Bob | -0.001 |
Andy | -0.001 |
iring | -0.001 |
Flash | -0.001 |
Token | clean |
Token ID | 3424 |
Feature activation | +8.69e-03 |
Pos logit contributions | |
use | +0.017 |
iche | +0.016 |
aster | +0.016 |
bell | +0.015 |
ues | +0.015 |
Neg logit contributions | |
Luis | -0.022 |
Bob | -0.022 |
Andy | -0.021 |
iring | -0.021 |
Flash | -0.021 |
Token | up |
Token ID | 510 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
iche | +0.017 |
use | +0.017 |
ues | +0.017 |
bell | +0.017 |
aster | +0.017 |
Neg logit contributions | |
Bob | -0.009 |
Luis | -0.008 |
Andy | -0.008 |
Zig | -0.007 |
Flash | -0.007 |
Token | even |
Token ID | 772 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
use | +0.039 |
aster | +0.038 |
iche | +0.038 |
ues | +0.038 |
bell | +0.037 |
Neg logit contributions | |
Bob | -0.029 |
Luis | -0.029 |
Andy | -0.028 |
iring | -0.026 |
Zig | -0.026 |
Token | if |
Token ID | 611 |
Feature activation | +3.41e-03 |
Pos logit contributions | |
iche | +0.109 |
ues | +0.106 |
bell | +0.104 |
use | +0.104 |
Amen | +0.103 |
Neg logit contributions | |
iring | -0.077 |
friends | -0.077 |
strength | -0.076 |
Bob | -0.075 |
branches | -0.074 |
Token | you |
Token ID | 345 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
use | +0.004 |
aster | +0.004 |
wasteful | +0.004 |
iche | +0.004 |
Does | +0.004 |
Neg logit contributions | |
Luis | -0.005 |
Bob | -0.005 |
iring | -0.005 |
Flash | -0.005 |
Zig | -0.005 |
Token | don |
Token ID | 836 |
Feature activation | -1.66e-03 |
Pos logit contributions | |
iche | +0.015 |
use | +0.015 |
ues | +0.014 |
bell | +0.014 |
aster | +0.014 |
Neg logit contributions | |
Bob | -0.024 |
Luis | -0.024 |
Andy | -0.023 |
iring | -0.023 |
strength | -0.023 |
Token | 't |
Token ID | 470 |
Feature activation | -3.50e-03 |
Pos logit contributions | |
Bob | +0.002 |
Luis | +0.002 |
Andy | +0.002 |
iring | +0.002 |
strength | +0.002 |
Neg logit contributions | |
use | -0.003 |
iche | -0.003 |
ues | -0.003 |
bell | -0.003 |
aster | -0.003 |
Token | want |
Token ID | 765 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
Bob | +0.006 |
Luis | +0.006 |
Andy | +0.006 |
Flash | +0.006 |
Zig | +0.006 |
Neg logit contributions | |
iche | -0.004 |
use | -0.004 |
bell | -0.004 |
aster | -0.004 |
ues | -0.004 |
Token | can |
Token ID | 460 |
Feature activation | -1.21e-03 |
Pos logit contributions | |
Luis | +0.023 |
Bob | +0.023 |
Andy | +0.022 |
iring | +0.022 |
branches | +0.022 |
Neg logit contributions | |
use | -0.016 |
ues | -0.015 |
bell | -0.015 |
aster | -0.015 |
iche | -0.015 |
Token | we |
Token ID | 356 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
Bob | +0.002 |
Luis | +0.002 |
iring | +0.002 |
Andy | +0.002 |
strength | +0.002 |
Neg logit contributions | |
bell | -0.001 |
use | -0.001 |
aster | -0.001 |
iche | -0.001 |
ues | -0.001 |
Token | play |
Token ID | 711 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
use | +0.013 |
iche | +0.013 |
bell | +0.013 |
aster | +0.013 |
ues | +0.013 |
Neg logit contributions | |
Bob | -0.018 |
Luis | -0.017 |
Andy | -0.017 |
iring | -0.017 |
strength | -0.016 |
Token | with |
Token ID | 351 |
Feature activation | +2.77e-03 |
Pos logit contributions | |
bell | +0.026 |
use | +0.026 |
iche | +0.026 |
ues | +0.025 |
Acc | +0.025 |
Neg logit contributions | |
friends | -0.013 |
Bob | -0.013 |
Luis | -0.011 |
animals | -0.011 |
himself | -0.011 |
Token | water |
Token ID | 1660 |
Feature activation | +9.09e-03 |
Pos logit contributions | |
iche | +0.005 |
use | +0.005 |
aster | +0.005 |
ues | +0.005 |
bell | +0.005 |
Neg logit contributions | |
Bob | -0.004 |
Luis | -0.004 |
Andy | -0.003 |
iring | -0.003 |
strength | -0.003 |
Token | again |
Token ID | 757 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
Acc | +0.014 |
iche | +0.014 |
bell | +0.014 |
ues | +0.014 |
iner | +0.014 |
Neg logit contributions | |
Bob | -0.014 |
friends | -0.012 |
birds | -0.012 |
animals | -0.011 |
Luis | -0.011 |
Token | when |
Token ID | 618 |
Feature activation | -4.28e-03 |
Pos logit contributions | |
iche | +0.068 |
ues | +0.066 |
bell | +0.065 |
use | +0.062 |
dollar | +0.059 |
Neg logit contributions | |
Bob | -0.125 |
Luis | -0.115 |
Andy | -0.115 |
friends | -0.114 |
iring | -0.111 |
Token | the |
Token ID | 262 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
Bob | +0.007 |
Luis | +0.007 |
Andy | +0.006 |
iring | +0.006 |
strength | +0.006 |
Neg logit contributions | |
iche | -0.006 |
use | -0.006 |
aster | -0.006 |
ues | -0.006 |
bell | -0.006 |
Token | law |
Token ID | 1099 |
Feature activation | +1.80e-03 |
Pos logit contributions | |
iche | +0.017 |
bell | +0.017 |
use | +0.017 |
aster | +0.016 |
ues | +0.016 |
Neg logit contributions | |
Bob | -0.015 |
Luis | -0.015 |
Andy | -0.015 |
Zig | -0.014 |
Flash | -0.014 |
Token | changes |
Token ID | 2458 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
iche | +0.002 |
ues | +0.002 |
use | +0.002 |
aster | +0.002 |
Acc | +0.002 |
Neg logit contributions | |
Bob | -0.003 |
Luis | -0.003 |
Andy | -0.003 |
strength | -0.003 |
iring | -0.003 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
use | +0.014 |
iche | +0.014 |
ues | +0.013 |
bell | +0.013 |
aster | +0.013 |
Neg logit contributions | |
Bob | -0.025 |
Luis | -0.024 |
Andy | -0.023 |
iring | -0.023 |
strength | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
iche | +0.015 |
use | +0.015 |
ues | +0.015 |
bell | +0.015 |
aster | +0.015 |
Neg logit contributions | |
Bob | -0.015 |
Luis | -0.015 |
Andy | -0.014 |
strength | -0.014 |
branches | -0.014 |
Token | black |
Token ID | 2042 |
Feature activation | +9.23e-03 |
Pos logit contributions | |
iche | +0.031 |
use | +0.031 |
ues | +0.031 |
bell | +0.030 |
aster | +0.030 |
Neg logit contributions | |
Bob | -0.039 |
Luis | -0.038 |
Andy | -0.037 |
strength | -0.036 |
branches | -0.035 |
Token | mascara |
Token ID | 48430 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
iche | +0.014 |
use | +0.013 |
ues | +0.013 |
wasteful | +0.013 |
bell | +0.013 |
Neg logit contributions | |
Bob | -0.014 |
Luis | -0.013 |
strength | -0.013 |
branches | -0.013 |
friends | -0.013 |
Token | on |
Token ID | 319 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
use | +0.091 |
aster | +0.086 |
iche | +0.086 |
Amen | +0.084 |
Does | +0.082 |
Neg logit contributions | |
Bob | -0.046 |
branches | -0.044 |
iring | -0.043 |
strength | -0.042 |
friends | -0.041 |
Token | her |
Token ID | 607 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
use | +0.022 |
iche | +0.022 |
ues | +0.021 |
bell | +0.021 |
aster | +0.020 |
Neg logit contributions | |
Bob | -0.021 |
Andy | -0.019 |
Luis | -0.019 |
branches | -0.018 |
Flash | -0.018 |
Token | eyel |
Token ID | 29708 |
Feature activation | +6.33e-02 |
Pos logit contributions | |
use | +0.062 |
iche | +0.061 |
ues | +0.059 |
aster | +0.059 |
bell | +0.059 |
Neg logit contributions | |
Bob | -0.043 |
Luis | -0.040 |
Andy | -0.039 |
strength | -0.039 |
branches | -0.038 |
Token | ashes |
Token ID | 7465 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
Does | +0.099 |
Amen | +0.097 |
use | +0.093 |
Does | +0.092 |
gallery | +0.086 |
Neg logit contributions | |
feet | -0.084 |
legs | -0.083 |
Bob | -0.083 |
toes | -0.082 |
strength | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | +7.50e-04 |
Pos logit contributions | |
iche | +0.038 |
use | +0.037 |
ues | +0.036 |
bell | +0.036 |
aster | +0.036 |
Neg logit contributions | |
Bob | -0.035 |
Luis | -0.033 |
Andy | -0.033 |
strength | -0.032 |
branches | -0.032 |
Token | She |
Token ID | 1375 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
use | +0.001 |
iche | +0.001 |
bell | +0.001 |
aster | +0.001 |
ues | +0.001 |
Neg logit contributions | |
Bob | -0.001 |
Luis | -0.001 |
Andy | -0.001 |
Zig | -0.001 |
Flash | -0.001 |
Token | makes |
Token ID | 1838 |
Feature activation | +1.67e-03 |
Pos logit contributions | |
iche | +0.028 |
use | +0.028 |
aster | +0.027 |
ues | +0.027 |
bell | +0.025 |
Neg logit contributions | |
Bob | -0.028 |
strength | -0.027 |
friends | -0.026 |
Luis | -0.026 |
branches | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
iche | +0.003 |
ues | +0.002 |
aster | +0.002 |
bell | +0.002 |
use | +0.002 |
Neg logit contributions | |
Bob | -0.002 |
Luis | -0.002 |
Andy | -0.002 |
iring | -0.002 |
strength | -0.002 |
Token | can |
Token ID | 460 |
Feature activation | +8.44e-03 |
Pos logit contributions | |
iche | +0.018 |
ues | +0.018 |
use | +0.018 |
bell | +0.018 |
aster | +0.017 |
Neg logit contributions | |
Bob | -0.026 |
Luis | -0.026 |
Andy | -0.025 |
strength | -0.024 |
iring | -0.024 |
Token | shine |
Token ID | 18340 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
iche | +0.012 |
ues | +0.012 |
use | +0.011 |
aster | +0.011 |
bell | +0.011 |
Neg logit contributions | |
Bob | -0.014 |
Luis | -0.013 |
Andy | -0.013 |
Flash | -0.012 |
strength | -0.012 |
Token | like |
Token ID | 588 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
iche | +0.034 |
use | +0.033 |
ues | +0.033 |
aster | +0.032 |
bell | +0.032 |
Neg logit contributions | |
Bob | -0.037 |
Luis | -0.036 |
Andy | -0.035 |
iring | -0.033 |
strength | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
aster | +0.019 |
iche | +0.019 |
use | +0.018 |
bell | +0.018 |
ues | +0.018 |
Neg logit contributions | |
Luis | -0.015 |
Bob | -0.015 |
Andy | -0.014 |
iring | -0.014 |
strength | -0.014 |
Token | star |
Token ID | 3491 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
ues | +0.030 |
use | +0.029 |
aster | +0.029 |
ours | +0.028 |
iche | +0.028 |
Neg logit contributions | |
Bob | -0.018 |
friends | -0.017 |
Luis | -0.016 |
Andy | -0.016 |
tiger | -0.016 |
Token | again |
Token ID | 757 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
ues | +0.031 |
use | +0.030 |
Acc | +0.030 |
iche | +0.030 |
aster | +0.028 |
Neg logit contributions | |
Bob | -0.064 |
friends | -0.063 |
Luis | -0.062 |
Andy | -0.060 |
iring | -0.060 |
Token | ?" |
Token ID | 1701 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
ues | +0.060 |
iche | +0.058 |
bell | +0.056 |
dollar | +0.052 |
Acc | +0.052 |
Neg logit contributions | |
Bob | -0.131 |
Andy | -0.121 |
friends | -0.121 |
Luis | -0.120 |
branches | -0.118 |
Token | asked |
Token ID | 1965 |
Feature activation | -5.41e-03 |
Pos logit contributions | |
ues | +0.061 |
iche | +0.059 |
use | +0.057 |
bell | +0.055 |
gallery | +0.055 |
Neg logit contributions | |
Bob | -0.057 |
Andy | -0.052 |
Luis | -0.050 |
friends | -0.048 |
Kel | -0.047 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
Bob | +0.009 |
Andy | +0.008 |
Luis | +0.008 |
friends | +0.008 |
Kel | +0.007 |
Neg logit contributions | |
iche | -0.008 |
use | -0.008 |
ues | -0.008 |
aster | -0.008 |
bell | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +8.21e-03 |
Pos logit contributions | |
iche | +0.021 |
use | +0.021 |
aster | +0.021 |
ues | +0.021 |
bell | +0.020 |
Neg logit contributions | |
Bob | -0.019 |
Luis | -0.018 |
Andy | -0.018 |
strength | -0.017 |
iring | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +2.21e-03 |
Pos logit contributions | |
ues | +0.014 |
use | +0.013 |
iche | +0.013 |
bell | +0.013 |
aster | +0.013 |
Neg logit contributions | |
Bob | -0.012 |
Luis | -0.011 |
Andy | -0.011 |
Zig | -0.010 |
Flash | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
iche | +0.029 |
use | +0.028 |
aster | +0.028 |
ues | +0.027 |
bell | +0.027 |
Neg logit contributions | |
Bob | -0.025 |
Luis | -0.024 |
Andy | -0.024 |
iring | -0.023 |
strength | -0.023 |
Token | Can |
Token ID | 1680 |
Feature activation | +3.91e-03 |
Pos logit contributions | |
Bob | +0.024 |
Luis | +0.023 |
Andy | +0.023 |
strength | +0.022 |
iring | +0.022 |
Neg logit contributions | |
iche | -0.021 |
use | -0.020 |
ues | -0.020 |
bell | -0.020 |
aster | -0.020 |
Token | you |
Token ID | 345 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
use | +0.005 |
iche | +0.005 |
bell | +0.005 |
aster | +0.005 |
ues | +0.005 |
Neg logit contributions | |
Bob | -0.006 |
Luis | -0.006 |
Andy | -0.006 |
strength | -0.006 |
iring | -0.006 |
Token | wrap |
Token ID | 14441 |
Feature activation | +2.67e-03 |
Pos logit contributions | |
iche | +0.029 |
ues | +0.028 |
use | +0.027 |
cheesy | +0.027 |
ours | +0.027 |
Neg logit contributions | |
Bob | -0.024 |
Luis | -0.023 |
Andy | -0.023 |
friends | -0.022 |
strength | -0.022 |
Token | it |
Token ID | 340 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
use | +0.004 |
iche | +0.004 |
aster | +0.004 |
ues | +0.004 |
bell | +0.004 |
Neg logit contributions | |
Luis | -0.004 |
Bob | -0.004 |
Andy | -0.004 |
iring | -0.003 |
strength | -0.003 |
Token | again |
Token ID | 757 |
Feature activation | +6.26e-02 |
Pos logit contributions | |
iche | +0.045 |
use | +0.043 |
aster | +0.043 |
ues | +0.043 |
wasteful | +0.041 |
Neg logit contributions | |
Bob | -0.025 |
Luis | -0.022 |
Andy | -0.022 |
himself | -0.022 |
friends | -0.022 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
iche | +0.069 |
ues | +0.067 |
bell | +0.064 |
use | +0.062 |
dollar | +0.061 |
Neg logit contributions | |
Bob | -0.120 |
friends | -0.113 |
Andy | -0.110 |
Luis | -0.109 |
branches | -0.108 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e-04 |
Pos logit contributions | |
iche | +0.021 |
ues | +0.021 |
use | +0.021 |
bell | +0.021 |
aster | +0.020 |
Neg logit contributions | |
Bob | -0.012 |
Luis | -0.011 |
Andy | -0.011 |
friends | -0.010 |
branches | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +2.58e-03 |
Pos logit contributions | |
iche | +0.000 |
use | +0.000 |
ues | +0.000 |
bell | +0.000 |
aster | +0.000 |
Neg logit contributions | |
Bob | -0.000 |
Luis | -0.000 |
Andy | -0.000 |
strength | -0.000 |
iring | -0.000 |
Token | Mom |
Token ID | 29252 |
Feature activation | +3.99e-03 |
Pos logit contributions | |
iche | +0.004 |
ues | +0.004 |
use | +0.004 |
bell | +0.004 |
aster | +0.004 |
Neg logit contributions | |
Bob | -0.004 |
Luis | -0.004 |
Andy | -0.004 |
iring | -0.003 |
branches | -0.003 |
Token | says |
Token ID | 1139 |
Feature activation | -4.49e-03 |
Pos logit contributions | |
iche | +0.005 |
use | +0.005 |
ues | +0.005 |
aster | +0.005 |
bell | +0.005 |
Neg logit contributions | |
Bob | -0.007 |
Luis | -0.007 |
Andy | -0.007 |
strength | -0.006 |
iring | -0.006 |
Token | trees |
Token ID | 7150 |
Feature activation | -6.16e-03 |
Pos logit contributions | |
Luis | +0.000 |
Bob | +0.000 |
Calvin | +0.000 |
Andy | +0.000 |
Owen | +0.000 |
Neg logit contributions | |
use | -0.000 |
bell | -0.000 |
iche | -0.000 |
gallery | -0.000 |
wasteful | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
Bob | +0.008 |
Luis | +0.007 |
Andy | +0.007 |
strength | +0.007 |
iring | +0.007 |
Neg logit contributions | |
iche | -0.011 |
use | -0.011 |
ues | -0.010 |
bell | -0.010 |
aster | -0.010 |
Token | make |
Token ID | 787 |
Feature activation | +6.68e-03 |
Pos logit contributions | |
ues | +0.043 |
iche | +0.043 |
use | +0.042 |
bell | +0.042 |
ours | +0.039 |
Neg logit contributions | |
Bob | -0.038 |
Andy | -0.036 |
Luis | -0.036 |
branches | -0.035 |
strength | -0.035 |
Token | them |
Token ID | 606 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
iche | +0.009 |
aster | +0.009 |
ues | +0.009 |
bell | +0.008 |
ours | +0.008 |
Neg logit contributions | |
Luis | -0.011 |
Bob | -0.010 |
Calvin | -0.010 |
iring | -0.009 |
Andy | -0.009 |
Token | shine |
Token ID | 18340 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
Bob | +0.021 |
Luis | +0.020 |
Andy | +0.020 |
iring | +0.019 |
Flash | +0.019 |
Neg logit contributions | |
iche | -0.015 |
bell | -0.015 |
ues | -0.015 |
aster | -0.015 |
use | -0.015 |
Token | again |
Token ID | 757 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
use | +0.052 |
iche | +0.051 |
aster | +0.051 |
ues | +0.049 |
bell | +0.048 |
Neg logit contributions | |
Bob | -0.042 |
Luis | -0.039 |
Andy | -0.039 |
iring | -0.038 |
strength | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +7.38e-03 |
Pos logit contributions | |
iche | +0.098 |
use | +0.097 |
ues | +0.096 |
bell | +0.095 |
aster | +0.094 |
Neg logit contributions | |
Bob | -0.090 |
Luis | -0.086 |
Andy | -0.085 |
branches | -0.081 |
iring | -0.080 |
Token |
|
Token ID | 198 |
Feature activation | +3.79e-03 |
Pos logit contributions | |
iche | +0.009 |
aster | +0.008 |
ues | +0.008 |
bell | +0.008 |
Does | +0.008 |
Neg logit contributions | |
Luis | -0.013 |
iring | -0.013 |
strength | -0.012 |
Bob | -0.012 |
Andy | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
iche | +0.006 |
use | +0.006 |
aster | +0.006 |
ues | +0.006 |
bell | +0.006 |
Neg logit contributions | |
Bob | -0.005 |
Luis | -0.005 |
Andy | -0.005 |
strength | -0.005 |
iring | -0.005 |
Token | As |
Token ID | 1722 |
Feature activation | -3.00e-03 |
Pos logit contributions | |
aster | +0.015 |
iche | +0.015 |
ues | +0.015 |
bell | +0.015 |
use | +0.014 |
Neg logit contributions | |
Bob | -0.015 |
Luis | -0.015 |
Andy | -0.014 |
strength | -0.014 |
iring | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
Luis | +0.004 |
iring | +0.004 |
strength | +0.004 |
Bob | +0.004 |
Andy | +0.004 |
Neg logit contributions | |
aster | -0.005 |
iche | -0.005 |
bell | -0.004 |
use | -0.004 |
cheesy | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
aster | +0.041 |
ues | +0.041 |
bell | +0.040 |
iche | +0.040 |
use | +0.039 |
Neg logit contributions | |
Bob | -0.038 |
Luis | -0.037 |
iring | -0.036 |
Andy | -0.036 |
Zig | -0.034 |
Token | cloth |
Token ID | 16270 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
bell | +0.024 |
iche | +0.023 |
aster | +0.022 |
use | +0.022 |
ues | +0.021 |
Neg logit contributions | |
Luis | -0.041 |
Bob | -0.040 |
Andy | -0.037 |
Calvin | -0.037 |
Flash | -0.037 |
Token | onto |
Token ID | 4291 |
Feature activation | +8.23e-03 |
Pos logit contributions | |
bell | +0.018 |
ues | +0.017 |
iche | +0.017 |
aster | +0.017 |
use | +0.017 |
Neg logit contributions | |
Bob | -0.016 |
Luis | -0.016 |
Andy | -0.015 |
iring | -0.015 |
Zig | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
aster | +0.014 |
bell | +0.012 |
iche | +0.012 |
ues | +0.012 |
cheesy | +0.012 |
Neg logit contributions | |
iring | -0.011 |
Luis | -0.011 |
Bob | -0.010 |
fl | -0.010 |
Zig | -0.010 |
Token | ash |
Token ID | 12530 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
bell | +0.030 |
iche | +0.029 |
aster | +0.029 |
use | +0.028 |
cheesy | +0.026 |
Neg logit contributions | |
Luis | -0.055 |
Bob | -0.054 |
Andy | -0.051 |
Calvin | -0.050 |
Flash | -0.050 |
Token | tr |
Token ID | 2213 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
bell | +0.016 |
ues | +0.014 |
aster | +0.014 |
iche | +0.014 |
use | +0.014 |
Neg logit contributions | |
Bob | -0.035 |
Luis | -0.035 |
Andy | -0.033 |
iring | -0.033 |
strength | -0.033 |
Token | ay |
Token ID | 323 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
use | +0.125 |
iche | +0.124 |
aster | +0.119 |
ues | +0.116 |
wasteful | +0.116 |
Neg logit contributions | |
Bob | -0.062 |
Luis | -0.061 |
Andy | -0.060 |
iring | -0.057 |
strength | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | +5.27e-03 |
Pos logit contributions | |
aster | +0.017 |
bell | +0.017 |
iche | +0.016 |
ues | +0.016 |
use | +0.016 |
Neg logit contributions | |
Luis | -0.021 |
iring | -0.021 |
Bob | -0.021 |
strength | -0.020 |
Andy | -0.020 |
Token | He |
Token ID | 679 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
aster | +0.008 |
iche | +0.008 |
bell | +0.008 |
ues | +0.008 |
use | +0.008 |
Neg logit contributions | |
Luis | -0.007 |
Bob | -0.007 |
Andy | -0.007 |
iring | -0.007 |
strength | -0.007 |
Token | worked |
Token ID | 3111 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
bell | +0.014 |
iche | +0.014 |
aster | +0.014 |
ues | +0.014 |
use | +0.013 |
Neg logit contributions | |
Bob | -0.020 |
Luis | -0.020 |
Andy | -0.019 |
iring | -0.019 |
Zig | -0.018 |
Token | hard |
Token ID | 1327 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
iche | +0.028 |
use | +0.027 |
aster | +0.027 |
bell | +0.027 |
ues | +0.027 |
Neg logit contributions | |
Bob | -0.032 |
Luis | -0.031 |
Andy | -0.031 |
strength | -0.030 |
iring | -0.029 |
Token | ma |
Token ID | 2611 |
Feature activation | +9.56e-03 |
Pos logit contributions | |
iche | +0.007 |
use | +0.006 |
ues | +0.006 |
bell | +0.006 |
aster | +0.006 |
Neg logit contributions | |
Bob | -0.006 |
Luis | -0.006 |
Andy | -0.006 |
iring | -0.006 |
strength | -0.006 |
Token | shape |
Token ID | 5485 |
Feature activation | +9.08e-03 |
Pos logit contributions | |
aster | +0.014 |
iche | +0.014 |
bell | +0.013 |
ues | +0.013 |
use | +0.013 |
Neg logit contributions | |
Bob | -0.015 |
Luis | -0.015 |
Andy | -0.014 |
iring | -0.014 |
Zig | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
ues | +0.015 |
aster | +0.015 |
iche | +0.015 |
bell | +0.015 |
use | +0.014 |
Neg logit contributions | |
Luis | -0.011 |
Bob | -0.011 |
Andy | -0.011 |
iring | -0.010 |
Zig | -0.010 |
Token | dough |
Token ID | 15756 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
iche | +0.022 |
use | +0.020 |
aster | +0.020 |
cheesy | +0.019 |
bell | +0.019 |
Neg logit contributions | |
Luis | -0.027 |
Bob | -0.027 |
Zig | -0.027 |
Andy | -0.026 |
Flash | -0.025 |
Token | into |
Token ID | 656 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
Bob | +0.017 |
Luis | +0.017 |
Andy | +0.016 |
iring | +0.016 |
strength | +0.016 |
Neg logit contributions | |
iche | -0.018 |
ues | -0.018 |
bell | -0.018 |
use | -0.018 |
aster | -0.018 |
Token | lo |
Token ID | 2376 |
Feature activation | +6.16e-02 |
Pos logit contributions | |
aster | +0.030 |
iche | +0.029 |
ues | +0.029 |
bell | +0.028 |
use | +0.028 |
Neg logit contributions | |
Luis | -0.020 |
Bob | -0.020 |
iring | -0.019 |
Andy | -0.018 |
Zig | -0.018 |
Token | aves |
Token ID | 3080 |
Feature activation | -4.97e-03 |
Pos logit contributions | |
Amen | +0.081 |
bell | +0.070 |
Does | +0.070 |
Does | +0.068 |
use | +0.066 |
Neg logit contributions | |
strength | -0.109 |
Bob | -0.105 |
friends | -0.103 |
two | -0.100 |
ert | -0.099 |
Token | and |
Token ID | 290 |
Feature activation | +7.08e-03 |
Pos logit contributions | |
Luis | +0.008 |
Bob | +0.007 |
Andy | +0.007 |
Zig | +0.007 |
Flash | +0.007 |
Neg logit contributions | |
bell | -0.007 |
iche | -0.007 |
ues | -0.007 |
use | -0.006 |
aster | -0.006 |
Token | she |
Token ID | 673 |
Feature activation | +5.19e-03 |
Pos logit contributions | |
aster | +0.009 |
iche | +0.009 |
bell | +0.009 |
ues | +0.009 |
use | +0.009 |
Neg logit contributions | |
iring | -0.011 |
Luis | -0.011 |
Bob | -0.011 |
Flash | -0.010 |
Andy | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
iche | +0.007 |
use | +0.007 |
ues | +0.007 |
bell | +0.007 |
aster | +0.007 |
Neg logit contributions | |
Bob | -0.009 |
Luis | -0.008 |
Andy | -0.008 |
strength | -0.008 |
iring | -0.008 |
Token | so |
Token ID | 523 |
Feature activation | -3.61e-03 |
Pos logit contributions | |
iche | +0.020 |
aster | +0.019 |
ues | +0.019 |
bell | +0.019 |
use | +0.018 |
Neg logit contributions | |
Luis | -0.028 |
Bob | -0.028 |
Andy | -0.027 |
iring | -0.026 |
Zig | -0.026 |
Token | Can |
Token ID | 1680 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
Bob | +0.003 |
Luis | +0.003 |
Andy | +0.003 |
iring | +0.003 |
strength | +0.003 |
Neg logit contributions | |
iche | -0.003 |
use | -0.003 |
ues | -0.003 |
bell | -0.003 |
aster | -0.003 |
Token | I |
Token ID | 314 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
iche | +0.030 |
ues | +0.029 |
use | +0.029 |
aster | +0.028 |
bell | +0.028 |
Neg logit contributions | |
Bob | -0.026 |
Luis | -0.025 |
Andy | -0.024 |
strength | -0.023 |
Zig | -0.022 |
Token | play |
Token ID | 711 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
iche | +0.055 |
ues | +0.053 |
use | +0.052 |
aster | +0.052 |
bell | +0.051 |
Neg logit contributions | |
Bob | -0.055 |
Luis | -0.053 |
Andy | -0.052 |
strength | -0.050 |
friends | -0.049 |
Token | with |
Token ID | 351 |
Feature activation | +9.08e-03 |
Pos logit contributions | |
iche | +0.057 |
bell | +0.056 |
use | +0.056 |
wil | +0.054 |
rant | +0.054 |
Neg logit contributions | |
friends | -0.016 |
himself | -0.012 |
by | -0.011 |
toys | -0.011 |
animals | -0.011 |
Token | them |
Token ID | 606 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
iche | +0.016 |
ues | +0.015 |
bell | +0.015 |
use | +0.015 |
aster | +0.015 |
Neg logit contributions | |
Bob | -0.012 |
Andy | -0.011 |
Luis | -0.011 |
friends | -0.010 |
strength | -0.010 |
Token | again |
Token ID | 757 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
iche | +0.014 |
ues | +0.014 |
aster | +0.013 |
bell | +0.013 |
use | +0.013 |
Neg logit contributions | |
Bob | -0.021 |
friends | -0.020 |
Luis | -0.020 |
iring | -0.019 |
Andy | -0.019 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
iche | +0.065 |
ues | +0.064 |
bell | +0.063 |
dollar | +0.059 |
use | +0.057 |
Neg logit contributions | |
Bob | -0.122 |
friends | -0.115 |
Andy | -0.112 |
Luis | -0.111 |
iring | -0.107 |
Token |
|
Token ID | 198 |
Feature activation | +6.59e-03 |
Pos logit contributions | |
iche | +0.030 |
ues | +0.030 |
use | +0.029 |
bell | +0.029 |
aster | +0.028 |
Neg logit contributions | |
Bob | -0.015 |
Andy | -0.013 |
Luis | -0.013 |
himself | -0.012 |
Zig | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +8.36e-03 |
Pos logit contributions | |
iche | +0.014 |
use | +0.014 |
ues | +0.014 |
bell | +0.014 |
aster | +0.013 |
Neg logit contributions | |
Bob | -0.006 |
Andy | -0.006 |
Luis | -0.006 |
friends | -0.005 |
himself | -0.005 |
Token | L |
Token ID | 43 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
iche | +0.011 |
ues | +0.011 |
bell | +0.011 |
ours | +0.011 |
use | +0.011 |
Neg logit contributions | |
Bob | -0.013 |
friends | -0.013 |
himself | -0.013 |
Luis | -0.013 |
Andy | -0.013 |
Token | ily |
Token ID | 813 |
Feature activation | -2.91e-03 |
Pos logit contributions | |
bell | +0.048 |
use | +0.047 |
iche | +0.046 |
cheesy | +0.044 |
Amen | +0.044 |
Neg logit contributions | |
Bob | -0.041 |
himself | -0.040 |
iring | -0.039 |
friends | -0.038 |
Luis | -0.037 |
Token | face |
Token ID | 1986 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
use | +0.062 |
iche | +0.062 |
ues | +0.060 |
aster | +0.059 |
bell | +0.059 |
Neg logit contributions | |
Bob | -0.048 |
Luis | -0.046 |
strength | -0.045 |
friends | -0.045 |
branches | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
iche | +0.057 |
use | +0.056 |
ues | +0.055 |
aster | +0.055 |
bell | +0.055 |
Neg logit contributions | |
Bob | -0.045 |
Luis | -0.043 |
Andy | -0.042 |
strength | -0.040 |
iring | -0.040 |
Token | look |
Token ID | 804 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
iche | +0.019 |
use | +0.019 |
ues | +0.019 |
bell | +0.019 |
aster | +0.018 |
Neg logit contributions | |
Bob | -0.024 |
Luis | -0.023 |
Andy | -0.023 |
strength | -0.022 |
branches | -0.022 |
Token | in |
Token ID | 287 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
aster | +0.099 |
iche | +0.097 |
use | +0.096 |
Acc | +0.090 |
Does | +0.089 |
Neg logit contributions | |
friends | -0.052 |
Bob | -0.048 |
iring | -0.046 |
feet | -0.041 |
children | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
iche | +0.045 |
use | +0.045 |
ues | +0.044 |
bell | +0.044 |
aster | +0.044 |
Neg logit contributions | |
Bob | -0.028 |
Luis | -0.027 |
Andy | -0.026 |
strength | -0.025 |
iring | -0.025 |
Token | mirror |
Token ID | 10162 |
Feature activation | +6.10e-02 |
Pos logit contributions | |
ues | +0.037 |
aster | +0.032 |
iche | +0.032 |
use | +0.032 |
Amen | +0.032 |
Neg logit contributions | |
branches | -0.027 |
friends | -0.026 |
birds | -0.026 |
trees | -0.025 |
Bob | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +3.40e-03 |
Pos logit contributions | |
use | +0.112 |
iche | +0.109 |
ackers | +0.103 |
aster | +0.103 |
ues | +0.102 |
Neg logit contributions | |
Bob | -0.071 |
Luis | -0.068 |
iring | -0.067 |
friends | -0.067 |
branches | -0.066 |
Token | She |
Token ID | 1375 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
use | +0.005 |
iche | +0.005 |
ues | +0.005 |
bell | +0.005 |
aster | +0.005 |
Neg logit contributions | |
Bob | -0.006 |
Luis | -0.005 |
Andy | -0.005 |
branches | -0.005 |
Flash | -0.005 |
Token | thought |
Token ID | 1807 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
iche | +0.028 |
ues | +0.027 |
use | +0.027 |
aster | +0.026 |
wasteful | +0.025 |
Neg logit contributions | |
Bob | -0.027 |
Luis | -0.025 |
friends | -0.025 |
Andy | -0.025 |
strength | -0.024 |
Token | it |
Token ID | 340 |
Feature activation | +9.54e-03 |
Pos logit contributions | |
use | +0.025 |
iche | +0.024 |
Amen | +0.022 |
ues | +0.022 |
ackers | +0.022 |
Neg logit contributions | |
Bob | -0.017 |
Andy | -0.015 |
Luis | -0.015 |
strength | -0.014 |
friends | -0.014 |
Token | made |
Token ID | 925 |
Feature activation | -1.44e-03 |
Pos logit contributions | |
aster | +0.018 |
iche | +0.018 |
use | +0.018 |
ues | +0.017 |
wasteful | +0.016 |
Neg logit contributions | |
Bob | -0.012 |
Luis | -0.011 |
Andy | -0.011 |
strength | -0.010 |
Flash | -0.010 |
Token | water |
Token ID | 1660 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
iche | +0.036 |
use | +0.036 |
ues | +0.035 |
bell | +0.035 |
aster | +0.035 |
Neg logit contributions | |
Bob | -0.020 |
Luis | -0.019 |
Andy | -0.018 |
strength | -0.017 |
branches | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
iche | +0.027 |
use | +0.027 |
ues | +0.026 |
bell | +0.026 |
aster | +0.026 |
Neg logit contributions | |
Bob | -0.023 |
Luis | -0.021 |
Andy | -0.021 |
branches | -0.020 |
iring | -0.020 |
Token | make |
Token ID | 787 |
Feature activation | +7.57e-03 |
Pos logit contributions | |
ues | +0.042 |
iche | +0.041 |
bell | +0.041 |
use | +0.040 |
notebooks | +0.039 |
Neg logit contributions | |
Bob | -0.033 |
branches | -0.031 |
Andy | -0.031 |
Luis | -0.030 |
strength | -0.030 |
Token | it |
Token ID | 340 |
Feature activation | +5.26e-03 |
Pos logit contributions | |
aster | +0.009 |
iche | +0.009 |
ues | +0.009 |
wasteful | +0.008 |
bell | +0.008 |
Neg logit contributions | |
Luis | -0.013 |
Bob | -0.013 |
Andy | -0.012 |
Calvin | -0.012 |
Andy | -0.012 |
Token | clean |
Token ID | 3424 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
use | +0.008 |
iche | +0.008 |
ues | +0.008 |
aster | +0.008 |
bell | +0.008 |
Neg logit contributions | |
Bob | -0.008 |
strength | -0.007 |
Luis | -0.007 |
Andy | -0.007 |
branches | -0.007 |
Token | again |
Token ID | 757 |
Feature activation | +6.09e-02 |
Pos logit contributions | |
use | +0.020 |
iche | +0.020 |
aster | +0.020 |
ues | +0.020 |
bell | +0.019 |
Neg logit contributions | |
Bob | -0.016 |
Luis | -0.015 |
Andy | -0.015 |
branches | -0.015 |
strength | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -6.23e-03 |
Pos logit contributions | |
iche | +0.108 |
use | +0.105 |
ues | +0.105 |
bell | +0.102 |
ours | +0.101 |
Neg logit contributions | |
Bob | -0.079 |
Andy | -0.072 |
branches | -0.071 |
Luis | -0.071 |
friends | -0.069 |
Token | Sue |
Token ID | 26089 |
Feature activation | -7.97e-03 |
Pos logit contributions | |
Luis | +0.009 |
Andy | +0.008 |
Bob | +0.008 |
iring | +0.008 |
Calvin | +0.008 |
Neg logit contributions | |
bell | -0.010 |
iche | -0.010 |
ues | -0.010 |
aster | -0.009 |
use | -0.009 |
Token | learned |
Token ID | 4499 |
Feature activation | -2.17e-03 |
Pos logit contributions | |
iring | +0.015 |
Luis | +0.015 |
Bob | +0.015 |
Andy | +0.015 |
Roll | +0.014 |
Neg logit contributions | |
aster | -0.008 |
bell | -0.008 |
iche | -0.008 |
ues | -0.008 |
use | -0.008 |
Token | that |
Token ID | 326 |
Feature activation | +2.80e-03 |
Pos logit contributions | |
Luis | +0.004 |
Bob | +0.003 |
Andy | +0.003 |
Flash | +0.003 |
Calvin | +0.003 |
Neg logit contributions | |
aster | -0.003 |
bell | -0.003 |
ues | -0.003 |
wasteful | -0.003 |
iche | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | +8.60e-03 |
Pos logit contributions | |
iche | +0.003 |
aster | +0.003 |
Does | +0.003 |
use | +0.003 |
bell | +0.003 |
Neg logit contributions | |
Luis | -0.005 |
Bob | -0.005 |
Andy | -0.005 |
iring | -0.005 |
Flash | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
bell | +0.008 |
use | +0.007 |
arium | +0.007 |
aster | +0.007 |
ues | +0.007 |
Neg logit contributions | |
Luis | -0.009 |
iring | -0.008 |
Andy | -0.008 |
Kel | -0.008 |
strength | -0.008 |
Token | his |
Token ID | 465 |
Feature activation | -1.07e-03 |
Pos logit contributions | |
Luis | +0.011 |
Bob | +0.011 |
Andy | +0.010 |
iring | +0.010 |
strength | +0.010 |
Neg logit contributions | |
aster | -0.020 |
iche | -0.019 |
use | -0.019 |
bell | -0.019 |
ues | -0.019 |
Token | home |
Token ID | 1363 |
Feature activation | +7.52e-03 |
Pos logit contributions | |
Luis | +0.001 |
Bob | +0.001 |
Andy | +0.001 |
Kel | +0.001 |
Zig | +0.001 |
Neg logit contributions | |
bell | -0.002 |
iche | -0.002 |
use | -0.002 |
gallery | -0.002 |
aster | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | +8.43e-03 |
Pos logit contributions | |
bell | +0.010 |
ues | +0.009 |
aster | +0.009 |
iche | +0.009 |
use | +0.009 |
Neg logit contributions | |
Luis | -0.013 |
Bob | -0.012 |
Andy | -0.012 |
strength | -0.012 |
Zig | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
iche | +0.017 |
use | +0.017 |
ues | +0.017 |
bell | +0.016 |
aster | +0.016 |
Neg logit contributions | |
Bob | -0.009 |
Luis | -0.008 |
Andy | -0.008 |
strength | -0.007 |
branches | -0.007 |
Token | sav |
Token ID | 6799 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
Bob | +0.011 |
branches | +0.011 |
strength | +0.010 |
friends | +0.010 |
Andy | +0.010 |
Neg logit contributions | |
ues | -0.023 |
iche | -0.022 |
bell | -0.021 |
aster | -0.021 |
use | -0.021 |
Token | annah |
Token ID | 25761 |
Feature activation | +8.13e-03 |
Pos logit contributions | |
Amen | +0.098 |
Does | +0.092 |
Or | +0.090 |
Does | +0.090 |
cheesy | +0.088 |
Neg logit contributions | |
branches | -0.078 |
iring | -0.072 |
surroundings | -0.070 |
ert | -0.070 |
feet | -0.070 |
Token | . |
Token ID | 13 |
Feature activation | -9.94e-03 |
Pos logit contributions | |
iche | +0.010 |
bell | +0.010 |
use | +0.010 |
aster | +0.010 |
ues | +0.010 |
Neg logit contributions | |
Luis | -0.014 |
Bob | -0.014 |
Andy | -0.013 |
Zig | -0.013 |
iring | -0.013 |
Token | He |
Token ID | 679 |
Feature activation | -7.25e-03 |
Pos logit contributions | |
Luis | +0.014 |
Bob | +0.013 |
iring | +0.013 |
Andy | +0.013 |
strength | +0.012 |
Neg logit contributions | |
bell | -0.016 |
iche | -0.015 |
aster | -0.015 |
use | -0.015 |
ues | -0.015 |
Token | showed |
Token ID | 3751 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
Bob | +0.011 |
Luis | +0.011 |
Andy | +0.011 |
iring | +0.011 |
strength | +0.011 |
Neg logit contributions | |
iche | -0.010 |
use | -0.010 |
bell | -0.010 |
ues | -0.010 |
aster | -0.010 |
Token | his |
Token ID | 465 |
Feature activation | -5.62e-03 |
Pos logit contributions | |
Luis | +0.030 |
ert | +0.029 |
fl | +0.028 |
Andy | +0.028 |
iring | +0.028 |
Neg logit contributions | |
aster | -0.023 |
bell | -0.021 |
ues | -0.020 |
notebooks | -0.020 |
dollar | -0.020 |
Token | careful |
Token ID | 8161 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
Bob | +0.014 |
Luis | +0.014 |
Andy | +0.014 |
iring | +0.013 |
strength | +0.013 |
Neg logit contributions | |
iche | -0.014 |
use | -0.014 |
ues | -0.014 |
aster | -0.014 |
bell | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
Luis | +0.049 |
Bob | +0.048 |
Andy | +0.047 |
strength | +0.046 |
Zig | +0.045 |
Neg logit contributions | |
bell | -0.030 |
aster | -0.030 |
ues | -0.030 |
iche | -0.030 |
use | -0.028 |
Token | He |
Token ID | 679 |
Feature activation | +9.05e-03 |
Pos logit contributions | |
use | +0.005 |
iche | +0.005 |
bell | +0.005 |
ues | +0.005 |
aster | +0.005 |
Neg logit contributions | |
Bob | -0.003 |
Luis | -0.003 |
Andy | -0.003 |
strength | -0.003 |
iring | -0.003 |
Token | knocks |
Token ID | 36539 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
iche | +0.013 |
ues | +0.013 |
bell | +0.012 |
aster | +0.012 |
use | +0.012 |
Neg logit contributions | |
Bob | -0.015 |
Luis | -0.014 |
strength | -0.014 |
Andy | -0.013 |
branches | -0.013 |
Token | over |
Token ID | 625 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
iche | +0.040 |
ues | +0.040 |
bell | +0.039 |
use | +0.039 |
aster | +0.037 |
Neg logit contributions | |
Bob | -0.029 |
Luis | -0.027 |
Andy | -0.026 |
himself | -0.025 |
branches | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
aster | +0.045 |
use | +0.044 |
iche | +0.044 |
bell | +0.044 |
ues | +0.043 |
Neg logit contributions | |
Luis | -0.032 |
Bob | -0.030 |
Andy | -0.030 |
iring | -0.030 |
strength | -0.028 |
Token | glass |
Token ID | 5405 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
Acc | +0.099 |
use | +0.098 |
ues | +0.097 |
iche | +0.095 |
Amen | +0.092 |
Neg logit contributions | |
Bob | -0.078 |
branches | -0.077 |
strength | -0.071 |
friends | -0.070 |
tiger | -0.069 |
Token | of |
Token ID | 286 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
iche | +0.086 |
use | +0.084 |
Acc | +0.084 |
Amen | +0.082 |
ues | +0.081 |
Neg logit contributions | |
Bob | -0.036 |
branches | -0.034 |
strength | -0.030 |
friends | -0.030 |
legs | -0.029 |
Token | water |
Token ID | 1660 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
ues | +0.035 |
iche | +0.035 |
bell | +0.034 |
use | +0.034 |
aster | +0.033 |
Neg logit contributions | |
Bob | -0.028 |
branches | -0.025 |
Andy | -0.025 |
Luis | -0.025 |
strength | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +5.84e-03 |
Pos logit contributions | |
iche | +0.033 |
ues | +0.032 |
Amen | +0.032 |
use | +0.032 |
bell | +0.032 |
Neg logit contributions | |
Bob | -0.022 |
branches | -0.019 |
Andy | -0.018 |
Luis | -0.018 |
himself | -0.018 |
Token | The |
Token ID | 383 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
use | +0.011 |
iche | +0.010 |
bell | +0.010 |
ues | +0.010 |
aster | +0.010 |
Neg logit contributions | |
Bob | -0.007 |
Luis | -0.007 |
Andy | -0.007 |
strength | -0.006 |
Flash | -0.006 |
Token | need |
Token ID | 761 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
iche | +0.020 |
ues | +0.020 |
aster | +0.019 |
bell | +0.019 |
use | +0.019 |
Neg logit contributions | |
Bob | -0.032 |
Luis | -0.031 |
Andy | -0.030 |
strength | -0.030 |
friends | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | +5.79e-03 |
Pos logit contributions | |
use | +0.022 |
aster | +0.022 |
iche | +0.021 |
bell | +0.021 |
ues | +0.021 |
Neg logit contributions | |
Luis | -0.018 |
Bob | -0.018 |
iring | -0.017 |
Andy | -0.017 |
Zig | -0.017 |
Token | check |
Token ID | 2198 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
iche | +0.008 |
use | +0.007 |
ues | +0.007 |
bell | +0.007 |
aster | +0.007 |
Neg logit contributions | |
Bob | -0.010 |
Luis | -0.009 |
Andy | -0.009 |
strength | -0.009 |
iring | -0.009 |
Token | your |
Token ID | 534 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
iche | +0.033 |
use | +0.033 |
bell | +0.032 |
ues | +0.032 |
aster | +0.032 |
Neg logit contributions | |
Bob | -0.028 |
Luis | -0.027 |
Andy | -0.026 |
strength | -0.025 |
iring | -0.025 |
Token | fever |
Token ID | 17372 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
use | +0.033 |
bell | +0.033 |
iche | +0.032 |
ues | +0.032 |
aster | +0.031 |
Neg logit contributions | |
Bob | -0.027 |
Luis | -0.026 |
Andy | -0.026 |
Andy | -0.025 |
Kel | -0.024 |
Token | again |
Token ID | 757 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
iche | +0.049 |
use | +0.048 |
ues | +0.048 |
aster | +0.048 |
bell | +0.048 |
Neg logit contributions | |
Bob | -0.039 |
Luis | -0.037 |
Andy | -0.036 |
strength | -0.034 |
iring | -0.034 |
Token | ." |
Token ID | 526 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
iche | +0.100 |
ues | +0.097 |
use | +0.097 |
aster | +0.096 |
bell | +0.096 |
Neg logit contributions | |
Bob | -0.082 |
Luis | -0.076 |
Andy | -0.075 |
iring | -0.073 |
branches | -0.072 |
Token |
|
Token ID | 198 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
iche | +0.039 |
use | +0.039 |
ues | +0.038 |
bell | +0.038 |
aster | +0.038 |
Neg logit contributions | |
Bob | -0.024 |
Luis | -0.022 |
Andy | -0.022 |
friends | -0.020 |
strength | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
use | +0.027 |
iche | +0.027 |
ues | +0.026 |
bell | +0.026 |
aster | +0.026 |
Neg logit contributions | |
Bob | -0.014 |
Andy | -0.013 |
Luis | -0.013 |
friends | -0.012 |
iring | -0.012 |
Token | L |
Token ID | 43 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
iche | +0.028 |
ues | +0.026 |
use | +0.026 |
bell | +0.026 |
rant | +0.026 |
Neg logit contributions | |
friends | -0.028 |
Andy | -0.027 |
Luis | -0.027 |
Andy | -0.027 |
Bob | -0.027 |
Token | ily |
Token ID | 813 |
Feature activation | -5.06e-03 |
Pos logit contributions | |
use | +0.053 |
iche | +0.050 |
bell | +0.050 |
cheesy | +0.048 |
Amen | +0.048 |
Neg logit contributions | |
Bob | -0.046 |
iring | -0.045 |
friends | -0.044 |
Luis | -0.043 |
Andy | -0.043 |
Token | not |
Token ID | 407 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
use | +0.054 |
bell | +0.051 |
och | +0.050 |
iche | +0.047 |
auc | +0.046 |
Neg logit contributions | |
friends | -0.020 |
himself | -0.019 |
strength | -0.017 |
two | -0.015 |
Bob | -0.015 |
Token | touch |
Token ID | 3638 |
Feature activation | +6.34e-03 |
Pos logit contributions | |
Bob | +0.017 |
Andy | +0.015 |
friends | +0.015 |
Luis | +0.015 |
strength | +0.015 |
Neg logit contributions | |
ues | -0.015 |
ours | -0.014 |
iche | -0.014 |
bell | -0.014 |
Does | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
iche | +0.009 |
use | +0.009 |
aster | +0.009 |
ues | +0.009 |
bell | +0.009 |
Neg logit contributions | |
Bob | -0.010 |
Luis | -0.010 |
Andy | -0.010 |
iring | -0.009 |
strength | -0.009 |
Token | v |
Token ID | 410 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
iche | +0.030 |
ues | +0.029 |
use | +0.029 |
aster | +0.029 |
bell | +0.028 |
Neg logit contributions | |
Bob | -0.032 |
Luis | -0.031 |
strength | -0.031 |
branches | -0.031 |
Andy | -0.031 |
Token | ase |
Token ID | 589 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
use | +0.026 |
cheesy | +0.022 |
iche | +0.022 |
Does | +0.022 |
wasteful | +0.021 |
Neg logit contributions | |
iring | -0.030 |
Bob | -0.029 |
Luis | -0.029 |
fl | -0.029 |
friends | -0.028 |
Token | again |
Token ID | 757 |
Feature activation | +6.02e-02 |
Pos logit contributions | |
use | +0.025 |
iche | +0.025 |
ues | +0.024 |
Does | +0.023 |
Amen | +0.023 |
Neg logit contributions | |
Bob | -0.020 |
Andy | -0.018 |
Luis | -0.018 |
branches | -0.017 |
iring | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +4.15e-03 |
Pos logit contributions | |
iche | +0.095 |
use | +0.093 |
ues | +0.092 |
bell | +0.091 |
aster | +0.091 |
Neg logit contributions | |
Bob | -0.088 |
Luis | -0.084 |
Andy | -0.082 |
iring | -0.078 |
strength | -0.078 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.98e-03 |
Pos logit contributions | |
iche | +0.005 |
ues | +0.005 |
use | +0.005 |
bell | +0.005 |
aster | +0.005 |
Neg logit contributions | |
Bob | -0.007 |
Luis | -0.007 |
Andy | -0.007 |
iring | -0.007 |
strength | -0.007 |
Token | L |
Token ID | 43 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
Luis | +0.015 |
Bob | +0.015 |
Andy | +0.015 |
strength | +0.015 |
iring | +0.014 |
Neg logit contributions | |
iche | -0.014 |
use | -0.014 |
aster | -0.013 |
bell | -0.013 |
ues | -0.013 |
Token | ily |
Token ID | 813 |
Feature activation | +9.08e-03 |
Pos logit contributions | |
iche | +0.028 |
use | +0.027 |
bell | +0.027 |
ues | +0.026 |
aster | +0.026 |
Neg logit contributions | |
Bob | -0.032 |
Luis | -0.031 |
Andy | -0.031 |
strength | -0.029 |
iring | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -4.95e-03 |
Pos logit contributions | |
iche | +0.013 |
ues | +0.012 |
bell | +0.012 |
aster | +0.012 |
use | +0.011 |
Neg logit contributions | |
Bob | -0.015 |
Luis | -0.014 |
Andy | -0.014 |
strength | -0.014 |
friends | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
use | +0.010 |
iche | +0.010 |
ues | +0.010 |
bell | +0.010 |
aster | +0.010 |
Neg logit contributions | |
Bob | -0.005 |
Luis | -0.005 |
Andy | -0.005 |
strength | -0.004 |
branches | -0.004 |
Token | wall |
Token ID | 3355 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
iche | +0.047 |
use | +0.046 |
ues | +0.045 |
aster | +0.044 |
bell | +0.043 |
Neg logit contributions | |
Bob | -0.054 |
Luis | -0.053 |
Andy | -0.052 |
branches | -0.052 |
strength | -0.051 |
Token | in |
Token ID | 287 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
use | +0.047 |
iche | +0.046 |
ackers | +0.044 |
aster | +0.044 |
wasteful | +0.044 |
Neg logit contributions | |
Bob | -0.027 |
branches | -0.025 |
Andy | -0.024 |
friends | -0.024 |
strength | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
iche | +0.045 |
use | +0.044 |
ues | +0.044 |
bell | +0.043 |
aster | +0.043 |
Neg logit contributions | |
Bob | -0.025 |
Luis | -0.023 |
Andy | -0.023 |
strength | -0.022 |
branches | -0.021 |
Token | little |
Token ID | 1310 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
use | +0.076 |
ues | +0.073 |
ours | +0.072 |
iche | +0.071 |
Acc | +0.070 |
Neg logit contributions | |
friends | -0.031 |
branches | -0.030 |
way | -0.028 |
Bob | -0.028 |
birds | -0.026 |
Token | girl |
Token ID | 2576 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
iche | +0.025 |
use | +0.025 |
ues | +0.025 |
aster | +0.024 |
bell | +0.024 |
Neg logit contributions | |
Bob | -0.019 |
Luis | -0.018 |
Andy | -0.018 |
strength | -0.017 |
iring | -0.017 |
Token | 's |
Token ID | 338 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
wasteful | +0.097 |
cheesy | +0.097 |
iche | +0.095 |
ues | +0.095 |
aster | +0.093 |
Neg logit contributions | |
friends | -0.085 |
Bob | -0.079 |
feet | -0.076 |
branches | -0.076 |
legs | -0.075 |
Token | room |
Token ID | 2119 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
use | +0.033 |
iche | +0.033 |
aster | +0.032 |
ues | +0.032 |
bell | +0.032 |
Neg logit contributions | |
Bob | -0.021 |
Luis | -0.020 |
strength | -0.020 |
Andy | -0.020 |
branches | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +2.85e-03 |
Pos logit contributions | |
use | +0.035 |
iche | +0.034 |
ackers | +0.033 |
aster | +0.032 |
Acc | +0.032 |
Neg logit contributions | |
Bob | -0.017 |
friends | -0.017 |
branches | -0.015 |
iring | -0.015 |
birds | -0.015 |
Token | She |
Token ID | 1375 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
iche | +0.004 |
bell | +0.004 |
use | +0.004 |
aster | +0.004 |
ues | +0.004 |
Neg logit contributions | |
Luis | -0.004 |
Bob | -0.004 |
Andy | -0.004 |
strength | -0.004 |
iring | -0.004 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
iche | +0.025 |
use | +0.024 |
aster | +0.024 |
ues | +0.023 |
cheesy | +0.022 |
Neg logit contributions | |
Bob | -0.021 |
friends | -0.020 |
Luis | -0.020 |
Andy | -0.019 |
strength | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -6.89e-03 |
Pos logit contributions | |
iche | +0.036 |
ues | +0.036 |
use | +0.034 |
aster | +0.033 |
bell | +0.032 |
Neg logit contributions | |
Bob | -0.081 |
Luis | -0.076 |
Andy | -0.076 |
friends | -0.072 |
iring | -0.072 |
Token | play |
Token ID | 711 |
Feature activation | +7.78e-03 |
Pos logit contributions | |
Bob | +0.012 |
Luis | +0.012 |
Andy | +0.011 |
iring | +0.011 |
strength | +0.011 |
Neg logit contributions | |
iche | -0.009 |
use | -0.008 |
aster | -0.008 |
bell | -0.008 |
ues | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | -1.63e-03 |
Pos logit contributions | |
bell | +0.012 |
use | +0.012 |
ues | +0.012 |
iche | +0.012 |
aster | +0.011 |
Neg logit contributions | |
Bob | -0.012 |
friends | -0.011 |
Andy | -0.011 |
Luis | -0.011 |
Flash | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -9.62e-03 |
Pos logit contributions | |
Bob | +0.001 |
Andy | +0.001 |
Luis | +0.001 |
branches | +0.001 |
friends | +0.001 |
Neg logit contributions | |
ues | -0.004 |
iche | -0.004 |
use | -0.004 |
bell | -0.004 |
wasteful | -0.003 |
Token | snow |
Token ID | 6729 |
Feature activation | +8.48e-03 |
Pos logit contributions | |
Luis | +0.013 |
Bob | +0.012 |
Andy | +0.012 |
iring | +0.012 |
strength | +0.011 |
Neg logit contributions | |
iche | -0.016 |
aster | -0.016 |
bell | -0.016 |
use | -0.016 |
cheesy | -0.015 |
Token | again |
Token ID | 757 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
use | +0.011 |
iche | +0.011 |
ues | +0.011 |
aster | +0.011 |
bell | +0.011 |
Neg logit contributions | |
Bob | -0.014 |
Luis | -0.014 |
Andy | -0.014 |
iring | -0.013 |
branches | -0.013 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
ues | +0.060 |
iche | +0.059 |
bell | +0.058 |
use | +0.055 |
aster | +0.054 |
Neg logit contributions | |
Bob | -0.121 |
Andy | -0.113 |
Luis | -0.112 |
friends | -0.110 |
iring | -0.108 |
Token |
|
Token ID | 198 |
Feature activation | +5.31e-03 |
Pos logit contributions | |
ues | +0.026 |
use | +0.026 |
iche | +0.025 |
wasteful | +0.025 |
bell | +0.025 |
Neg logit contributions | |
Bob | -0.016 |
Andy | -0.015 |
Luis | -0.015 |
friends | -0.014 |
strength | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +8.91e-03 |
Pos logit contributions | |
iche | +0.008 |
use | +0.008 |
aster | +0.008 |
ues | +0.008 |
bell | +0.008 |
Neg logit contributions | |
Bob | -0.008 |
Luis | -0.008 |
Andy | -0.008 |
strength | -0.007 |
iring | -0.007 |
Token | " |
Token ID | 1 |
Feature activation | +2.96e-03 |
Pos logit contributions | |
iche | +0.011 |
use | +0.011 |
ues | +0.011 |
bell | +0.011 |
aster | +0.011 |
Neg logit contributions | |
Bob | -0.015 |
Luis | -0.015 |
Andy | -0.015 |
strength | -0.014 |
iring | -0.014 |
Token | Of |
Token ID | 5189 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
use | +0.004 |
iche | +0.004 |
ues | +0.004 |
bell | +0.004 |
aster | +0.004 |
Neg logit contributions | |
Bob | -0.005 |
Luis | -0.005 |
Andy | -0.005 |
strength | -0.005 |
iring | -0.005 |
Token | - |
Token ID | 12 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
iche | +0.041 |
use | +0.041 |
ues | +0.041 |
aster | +0.040 |
bell | +0.040 |
Neg logit contributions | |
Bob | -0.045 |
Luis | -0.045 |
Andy | -0.044 |
iring | -0.041 |
strength | -0.041 |
Token | three |
Token ID | 15542 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
iche | +0.016 |
use | +0.015 |
bell | +0.015 |
ues | +0.015 |
aster | +0.015 |
Neg logit contributions | |
Bob | -0.016 |
Luis | -0.015 |
Andy | -0.015 |
strength | -0.015 |
branches | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
iche | +0.085 |
bell | +0.085 |
Acc | +0.081 |
use | +0.080 |
ues | +0.080 |
Neg logit contributions | |
Bob | -0.058 |
Luis | -0.054 |
strength | -0.053 |
branches | -0.052 |
Andy | -0.051 |
Token | thirty |
Token ID | 12277 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
iche | +0.017 |
use | +0.017 |
aster | +0.017 |
ues | +0.017 |
bell | +0.017 |
Neg logit contributions | |
Luis | -0.016 |
Bob | -0.016 |
Andy | -0.015 |
iring | -0.015 |
strength | -0.015 |
Token | - |
Token ID | 12 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
iche | +0.038 |
use | +0.038 |
ues | +0.038 |
aster | +0.037 |
bell | +0.037 |
Neg logit contributions | |
Bob | -0.042 |
Luis | -0.041 |
Andy | -0.040 |
iring | -0.038 |
strength | -0.038 |
Token | four |
Token ID | 14337 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
iche | +0.016 |
use | +0.016 |
ues | +0.016 |
bell | +0.016 |
aster | +0.015 |
Neg logit contributions | |
Bob | -0.017 |
Luis | -0.017 |
Andy | -0.016 |
strength | -0.016 |
iring | -0.016 |
Token | ," |
Token ID | 553 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
iche | +0.105 |
bell | +0.104 |
use | +0.103 |
ues | +0.100 |
aster | +0.099 |
Neg logit contributions | |
Bob | -0.074 |
Luis | -0.069 |
strength | -0.069 |
friends | -0.069 |
Andy | -0.067 |
Token | Mia |
Token ID | 32189 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
aster | +0.016 |
bell | +0.014 |
ues | +0.014 |
use | +0.014 |
iche | +0.014 |
Neg logit contributions | |
iring | -0.021 |
Luis | -0.021 |
strength | -0.020 |
fl | -0.020 |
Andy | -0.020 |
Token | says |
Token ID | 1139 |
Feature activation | -2.89e-04 |
Pos logit contributions | |
ues | +0.011 |
use | +0.010 |
bell | +0.010 |
aster | +0.010 |
iche | +0.010 |
Neg logit contributions | |
Luis | -0.022 |
Andy | -0.022 |
iring | -0.022 |
Bob | -0.021 |
Kel | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e-03 |
Pos logit contributions | |
Luis | +0.000 |
Bob | +0.000 |
Andy | +0.000 |
iring | +0.000 |
strength | +0.000 |
Neg logit contributions | |
ues | -0.000 |
bell | -0.000 |
iche | -0.000 |
use | -0.000 |
aster | -0.000 |
Token | She |
Token ID | 1375 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
Luis | +0.002 |
Bob | +0.002 |
Andy | +0.002 |
strength | +0.002 |
iring | +0.002 |
Neg logit contributions | |
iche | -0.002 |
use | -0.002 |
ues | -0.002 |
aster | -0.001 |
bell | -0.001 |
Token | can |
Token ID | 460 |
Feature activation | +6.50e-03 |
Pos logit contributions | |
use | +0.008 |
iche | +0.007 |
bell | +0.007 |
ues | +0.007 |
aster | +0.007 |
Neg logit contributions | |
Bob | -0.013 |
Luis | -0.013 |
Andy | -0.013 |
iring | -0.013 |
Flash | -0.012 |
Token | make |
Token ID | 787 |
Feature activation | +4.16e-03 |
Pos logit contributions | |
bell | +0.009 |
use | +0.009 |
aster | +0.008 |
iche | +0.008 |
ues | +0.008 |
Neg logit contributions | |
Bob | -0.011 |
Luis | -0.010 |
Andy | -0.010 |
iring | -0.010 |
strength | -0.010 |
Token | it |
Token ID | 340 |
Feature activation | +3.14e-03 |
Pos logit contributions | |
iche | +0.006 |
aster | +0.006 |
ues | +0.005 |
bell | +0.005 |
use | +0.005 |
Neg logit contributions | |
Luis | -0.007 |
Bob | -0.007 |
Andy | -0.006 |
iring | -0.006 |
Flash | -0.006 |
Token | look |
Token ID | 804 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
use | +0.004 |
iche | +0.004 |
ues | +0.004 |
aster | +0.004 |
bell | +0.004 |
Neg logit contributions | |
Bob | -0.005 |
Luis | -0.005 |
Andy | -0.005 |
strength | -0.005 |
iring | -0.005 |
Token | new |
Token ID | 649 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
aster | +0.087 |
use | +0.084 |
iche | +0.084 |
ours | +0.078 |
ues | +0.077 |
Neg logit contributions | |
Bob | -0.045 |
strength | -0.045 |
friends | -0.045 |
iring | -0.043 |
himself | -0.041 |
Token | again |
Token ID | 757 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
bell | +0.016 |
ues | +0.016 |
use | +0.015 |
iche | +0.015 |
cheesy | +0.014 |
Neg logit contributions | |
Luis | -0.023 |
Bob | -0.022 |
Andy | -0.022 |
Kel | -0.021 |
Andy | -0.021 |
Token | ." |
Token ID | 526 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
iche | +0.086 |
use | +0.084 |
ues | +0.083 |
bell | +0.083 |
aster | +0.083 |
Neg logit contributions | |
Bob | -0.093 |
Luis | -0.090 |
Andy | -0.088 |
strength | -0.084 |
iring | -0.084 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
aster | +0.036 |
iche | +0.036 |
use | +0.036 |
bell | +0.035 |
ues | +0.035 |
Neg logit contributions | |
Bob | -0.029 |
Andy | -0.026 |
Luis | -0.026 |
branches | -0.024 |
Zig | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
iche | +0.019 |
use | +0.018 |
ues | +0.018 |
bell | +0.018 |
aster | +0.018 |
Neg logit contributions | |
Bob | -0.013 |
Luis | -0.012 |
Andy | -0.012 |
iring | -0.011 |
strength | -0.011 |
Token | They |
Token ID | 2990 |
Feature activation | -1.10e-03 |
Pos logit contributions | |
iche | +0.025 |
aster | +0.024 |
use | +0.024 |
bell | +0.023 |
ues | +0.023 |
Neg logit contributions | |
branches | -0.023 |
iring | -0.023 |
friends | -0.023 |
Bob | -0.023 |
Luis | -0.022 |
Token | went |
Token ID | 1816 |
Feature activation | +7.68e-03 |
Pos logit contributions | |
Bob | +0.002 |
Andy | +0.002 |
Luis | +0.002 |
strength | +0.002 |
branches | +0.002 |
Neg logit contributions | |
iche | -0.002 |
ues | -0.002 |
use | -0.002 |
Does | -0.002 |
aster | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
Bob | +0.028 |
Luis | +0.027 |
Andy | +0.027 |
iring | +0.026 |
strength | +0.026 |
Neg logit contributions | |
use | -0.022 |
aster | -0.022 |
bell | -0.021 |
iche | -0.021 |
ues | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -6.87e-03 |
Pos logit contributions | |
iring | +0.022 |
Luis | +0.020 |
strength | +0.020 |
branches | +0.020 |
plunge | +0.019 |
Neg logit contributions | |
use | -0.010 |
aster | -0.009 |
bell | -0.009 |
ues | -0.008 |
named | -0.008 |
Token | Kitty |
Token ID | 21168 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
hind | +0.013 |
iring | +0.013 |
plunge | +0.013 |
himself | +0.012 |
kel | +0.012 |
Neg logit contributions | |
named | -0.006 |
they | -0.006 |
much | -0.005 |
bell | -0.005 |
bs | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -8.07e-04 |
Pos logit contributions | |
iring | +0.039 |
Luis | +0.039 |
Andy | +0.037 |
Bob | +0.037 |
strength | +0.037 |
Neg logit contributions | |
use | -0.027 |
iche | -0.026 |
bell | -0.025 |
aster | -0.025 |
draws | -0.025 |
Token | Dog |
Token ID | 8532 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
iring | +0.001 |
ert | +0.001 |
sides | +0.001 |
strength | +0.001 |
plunge | +0.001 |
Neg logit contributions | |
use | -0.001 |
aster | -0.001 |
Amen | -0.001 |
Or | -0.001 |
Does | -0.001 |
Token | gy |
Token ID | 1360 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
Luis | +0.080 |
iring | +0.080 |
strength | +0.079 |
Bob | +0.077 |
Calvin | +0.074 |
Neg logit contributions | |
use | -0.075 |
bell | -0.074 |
iche | -0.066 |
ues | -0.064 |
pp | -0.063 |
Token | loved |
Token ID | 6151 |
Feature activation | +5.84e-03 |
Pos logit contributions | |
iring | +0.136 |
Luis | +0.132 |
Bob | +0.126 |
Andy | +0.125 |
Calvin | +0.123 |
Neg logit contributions | |
bell | -0.071 |
use | -0.068 |
aster | -0.068 |
iche | -0.065 |
ues | -0.062 |
Token | to |
Token ID | 284 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
aster | +0.009 |
iche | +0.008 |
ues | +0.008 |
bell | +0.008 |
use | +0.008 |
Neg logit contributions | |
iring | -0.008 |
Luis | -0.008 |
Bob | -0.008 |
strength | -0.008 |
Andy | -0.008 |
Token | play |
Token ID | 711 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
Bob | +0.018 |
Luis | +0.018 |
Andy | +0.017 |
iring | +0.017 |
strength | +0.016 |
Neg logit contributions | |
iche | -0.014 |
use | -0.014 |
ues | -0.014 |
bell | -0.013 |
aster | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -1.58e-03 |
Pos logit contributions | |
use | +0.027 |
iche | +0.026 |
bell | +0.026 |
aster | +0.025 |
ues | +0.025 |
Neg logit contributions | |
Bob | -0.018 |
Luis | -0.018 |
Andy | -0.017 |
friends | -0.017 |
strength | -0.016 |
Token | piano |
Token ID | 19132 |
Feature activation | +3.00e-03 |
Pos logit contributions | |
Bob | +0.003 |
Andy | +0.003 |
Luis | +0.003 |
Zig | +0.003 |
Owen | +0.003 |
Neg logit contributions | |
iche | -0.002 |
gallery | -0.002 |
pron | -0.002 |
aster | -0.001 |
bell | -0.001 |
Token | were |
Token ID | 547 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
iring | +0.052 |
Luis | +0.052 |
branches | +0.051 |
strength | +0.050 |
hind | +0.049 |
Neg logit contributions | |
bell | -0.033 |
use | -0.030 |
aster | -0.030 |
ackers | -0.030 |
iche | -0.029 |
Token | two |
Token ID | 734 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
Luis | +0.038 |
Calvin | +0.035 |
strength | +0.035 |
iring | +0.034 |
Owen | +0.033 |
Neg logit contributions | |
iche | -0.056 |
aster | -0.054 |
ackers | -0.053 |
bell | -0.053 |
cheesy | -0.052 |
Token | cats |
Token ID | 11875 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
Luis | +0.022 |
Bob | +0.019 |
Calvin | +0.018 |
Andy | +0.017 |
Flash | +0.017 |
Neg logit contributions | |
bell | -0.070 |
iche | -0.070 |
aster | -0.068 |
cheesy | -0.068 |
use | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | -8.38e-03 |
Pos logit contributions | |
Luis | +0.075 |
strength | +0.074 |
iring | +0.073 |
Bob | +0.072 |
Calvin | +0.070 |
Neg logit contributions | |
iche | -0.035 |
bell | -0.034 |
use | -0.034 |
aster | -0.034 |
ues | -0.034 |
Token | Tig |
Token ID | 14189 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
iring | +0.012 |
Luis | +0.011 |
strength | +0.011 |
Bob | +0.011 |
branches | +0.011 |
Neg logit contributions | |
aster | -0.012 |
use | -0.012 |
iche | -0.012 |
bell | -0.012 |
cheesy | -0.011 |
Token | gy |
Token ID | 1360 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
iring | +0.046 |
plunge | +0.044 |
Luis | +0.044 |
strength | +0.044 |
Bob | +0.043 |
Neg logit contributions | |
use | -0.037 |
aster | -0.033 |
rant | -0.031 |
ues | -0.031 |
heaven | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
Luis | +0.128 |
iring | +0.123 |
plunge | +0.119 |
Calvin | +0.118 |
Owen | +0.118 |
Neg logit contributions | |
named | -0.072 |
bell | -0.071 |
aster | -0.071 |
iche | -0.069 |
batch | -0.067 |
Token | Snow |
Token ID | 7967 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
iring | +0.023 |
branches | +0.019 |
strength | +0.019 |
Luis | +0.019 |
surroundings | +0.018 |
Neg logit contributions | |
aster | -0.024 |
use | -0.024 |
wasteful | -0.022 |
Does | -0.022 |
Amen | -0.022 |
Token | y |
Token ID | 88 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
strength | +0.040 |
Bob | +0.039 |
Luis | +0.039 |
branches | +0.039 |
Andy | +0.037 |
Neg logit contributions | |
iche | -0.013 |
bell | -0.012 |
ackers | -0.012 |
use | -0.012 |
ues | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
Luis | +0.067 |
Bob | +0.064 |
iring | +0.064 |
Andy | +0.062 |
strength | +0.062 |
Neg logit contributions | |
iche | -0.046 |
bell | -0.046 |
use | -0.045 |
ues | -0.044 |
aster | -0.043 |
Token | The |
Token ID | 383 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
iring | +0.041 |
Bob | +0.040 |
Luis | +0.040 |
Andy | +0.040 |
strength | +0.039 |
Neg logit contributions | |
use | -0.027 |
iche | -0.026 |
ues | -0.025 |
bell | -0.025 |
Does | -0.025 |
Token | day |
Token ID | 1110 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
Luis | +0.002 |
iring | +0.002 |
Bob | +0.002 |
Andy | +0.002 |
strength | +0.002 |
Neg logit contributions | |
aster | -0.003 |
iche | -0.003 |
bell | -0.003 |
use | -0.003 |
ues | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
iche | +0.019 |
use | +0.019 |
ues | +0.019 |
bell | +0.019 |
aster | +0.019 |
Neg logit contributions | |
Bob | -0.015 |
Luis | -0.015 |
Andy | -0.014 |
strength | -0.014 |
iring | -0.014 |
Token | Kitty |
Token ID | 21168 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
plunge | +0.020 |
ert | +0.020 |
strength | +0.020 |
iring | +0.020 |
Luis | +0.020 |
Neg logit contributions | |
iche | -0.011 |
Does | -0.011 |
bell | -0.011 |
Amen | -0.011 |
ours | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -9.52e-04 |
Pos logit contributions | |
Luis | +0.049 |
iring | +0.047 |
Kel | +0.046 |
plunge | +0.046 |
Andy | +0.045 |
Neg logit contributions | |
use | -0.030 |
bell | -0.029 |
drew | -0.028 |
draws | -0.028 |
iche | -0.027 |
Token | Dog |
Token ID | 8532 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
ert | +0.001 |
iring | +0.001 |
Luis | +0.001 |
strength | +0.001 |
Ricky | +0.001 |
Neg logit contributions | |
use | -0.002 |
aster | -0.002 |
bell | -0.002 |
wasteful | -0.002 |
Amen | -0.002 |
Token | gy |
Token ID | 1360 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
Luis | +0.072 |
iring | +0.070 |
Bob | +0.069 |
strength | +0.069 |
Calvin | +0.065 |
Neg logit contributions | |
use | -0.073 |
bell | -0.072 |
iche | -0.063 |
ues | -0.062 |
pp | -0.061 |
Token | learned |
Token ID | 4499 |
Feature activation | -5.00e-03 |
Pos logit contributions | |
Luis | +0.133 |
iring | +0.132 |
Bob | +0.126 |
Andy | +0.125 |
Calvin | +0.122 |
Neg logit contributions | |
bell | -0.068 |
use | -0.065 |
iche | -0.061 |
aster | -0.061 |
ues | -0.060 |
Token | that |
Token ID | 326 |
Feature activation | +1.02e-03 |
Pos logit contributions | |
Luis | +0.008 |
Bob | +0.008 |
Andy | +0.007 |
strength | +0.007 |
iring | +0.007 |
Neg logit contributions | |
bell | -0.007 |
ues | -0.007 |
iche | -0.007 |
aster | -0.007 |
use | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +2.66e-03 |
Pos logit contributions | |
iche | +0.001 |
use | +0.001 |
ues | +0.001 |
bell | +0.001 |
aster | +0.001 |
Neg logit contributions | |
Bob | -0.002 |
Luis | -0.002 |
Andy | -0.002 |
strength | -0.001 |
iring | -0.001 |
Token | coin |
Token ID | 10752 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
use | +0.004 |
iche | +0.003 |
bell | +0.003 |
aster | +0.003 |
Amen | +0.003 |
Neg logit contributions | |
Luis | -0.004 |
Andy | -0.004 |
Bob | -0.004 |
Owen | -0.004 |
Kel | -0.004 |
Token | 's |
Token ID | 338 |
Feature activation | -7.90e-03 |
Pos logit contributions | |
Luis | +0.023 |
Bob | +0.023 |
Andy | +0.022 |
Kel | +0.022 |
Owen | +0.022 |
Neg logit contributions | |
bell | -0.013 |
use | -0.013 |
ues | -0.013 |
iche | -0.013 |
wasteful | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -7.81e-04 |
Pos logit contributions | |
Bob | +0.003 |
Luis | +0.003 |
Andy | +0.003 |
strength | +0.003 |
iring | +0.003 |
Neg logit contributions | |
iche | -0.003 |
aster | -0.003 |
ues | -0.003 |
use | -0.003 |
bell | -0.003 |
Token | K |
Token ID | 42 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
Bob | +0.001 |
Luis | +0.001 |
Andy | +0.001 |
strength | +0.001 |
iring | +0.001 |
Neg logit contributions | |
aster | -0.001 |
iche | -0.001 |
use | -0.001 |
ues | -0.001 |
bell | -0.001 |
Token | itty |
Token ID | 9760 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
Luis | +0.018 |
Bob | +0.017 |
strength | +0.017 |
iring | +0.017 |
Andy | +0.017 |
Neg logit contributions | |
use | -0.014 |
bell | -0.014 |
aster | -0.013 |
iche | -0.013 |
ues | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +2.77e-03 |
Pos logit contributions | |
iring | +0.050 |
Luis | +0.047 |
Bob | +0.044 |
Andy | +0.044 |
strength | +0.044 |
Neg logit contributions | |
use | -0.034 |
bell | -0.034 |
ues | -0.032 |
iche | -0.032 |
aster | -0.032 |
Token | Dog |
Token ID | 8532 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
aster | +0.004 |
named | +0.004 |
use | +0.004 |
bell | +0.004 |
drew | +0.003 |
Neg logit contributions | |
iring | -0.004 |
strength | -0.004 |
ert | -0.004 |
plunge | -0.003 |
surroundings | -0.003 |
Token | gy |
Token ID | 1360 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
iring | +0.085 |
Luis | +0.078 |
strength | +0.076 |
Bob | +0.073 |
Calvin | +0.072 |
Neg logit contributions | |
use | -0.065 |
bell | -0.064 |
mary | -0.056 |
ues | -0.055 |
iche | -0.054 |
Token | played |
Token ID | 2826 |
Feature activation | -2.21e-03 |
Pos logit contributions | |
iring | +0.132 |
Luis | +0.126 |
Bob | +0.115 |
Calvin | +0.115 |
Andy | +0.115 |
Neg logit contributions | |
bell | -0.071 |
aster | -0.071 |
use | -0.069 |
iche | -0.063 |
drew | -0.062 |
Token | the |
Token ID | 262 |
Feature activation | -7.98e-03 |
Pos logit contributions | |
Luis | +0.004 |
Bob | +0.004 |
iring | +0.004 |
Andy | +0.004 |
strength | +0.004 |
Neg logit contributions | |
ues | -0.002 |
iche | -0.002 |
aster | -0.002 |
use | -0.002 |
bell | -0.002 |
Token | piano |
Token ID | 19132 |
Feature activation | +5.62e-03 |
Pos logit contributions | |
Bob | +0.012 |
iring | +0.011 |
Luis | +0.011 |
Andy | +0.011 |
Owen | +0.011 |
Neg logit contributions | |
iche | -0.012 |
aster | -0.012 |
pron | -0.011 |
use | -0.011 |
gallery | -0.011 |
Token | together |
Token ID | 1978 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
iche | +0.008 |
use | +0.008 |
aster | +0.008 |
ues | +0.008 |
bell | +0.008 |
Neg logit contributions | |
Bob | -0.009 |
Luis | -0.008 |
Andy | -0.008 |
strength | -0.008 |
branches | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +4.44e-03 |
Pos logit contributions | |
iche | +0.025 |
ues | +0.024 |
use | +0.024 |
aster | +0.024 |
bell | +0.024 |
Neg logit contributions | |
Bob | -0.022 |
Luis | -0.022 |
Andy | -0.022 |
iring | -0.021 |
strength | -0.021 |
Token | again |
Token ID | 757 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
Luis | +0.006 |
strength | +0.005 |
Calvin | +0.005 |
branches | +0.005 |
plunge | +0.005 |
Neg logit contributions | |
ues | -0.003 |
bell | -0.003 |
cheesy | -0.002 |
Acc | -0.002 |
iche | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -5.93e-03 |
Pos logit contributions | |
iche | +0.036 |
use | +0.036 |
ues | +0.035 |
aster | +0.035 |
bell | +0.035 |
Neg logit contributions | |
Bob | -0.040 |
Luis | -0.039 |
Andy | -0.038 |
strength | -0.037 |
iring | -0.036 |
Token | Kitty |
Token ID | 21168 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
plunge | +0.009 |
ert | +0.009 |
Luis | +0.009 |
strength | +0.009 |
iring | +0.008 |
Neg logit contributions | |
iche | -0.008 |
bell | -0.008 |
Does | -0.008 |
ours | -0.007 |
Amen | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +3.08e-03 |
Pos logit contributions | |
iring | +0.048 |
Luis | +0.047 |
Andy | +0.045 |
Bob | +0.044 |
Calvin | +0.043 |
Neg logit contributions | |
use | -0.028 |
bell | -0.027 |
iche | -0.026 |
draws | -0.025 |
Acc | -0.025 |
Token | Dog |
Token ID | 8532 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
aster | +0.005 |
named | +0.004 |
Amen | +0.004 |
use | +0.004 |
heaven | +0.004 |
Neg logit contributions | |
iring | -0.005 |
strength | -0.004 |
plunge | -0.004 |
ert | -0.004 |
sides | -0.004 |
Token | gy |
Token ID | 1360 |
Feature activation | -6.67e-02 |
Pos logit contributions | |
Luis | +0.076 |
iring | +0.075 |
strength | +0.073 |
Bob | +0.072 |
Calvin | +0.069 |
Neg logit contributions | |
use | -0.077 |
bell | -0.077 |
iche | -0.069 |
ues | -0.066 |
Amen | -0.066 |
Token | played |
Token ID | 2826 |
Feature activation | +1.91e-04 |
Pos logit contributions | |
iring | +0.129 |
Luis | +0.126 |
Bob | +0.118 |
Andy | +0.117 |
Calvin | +0.116 |
Neg logit contributions | |
aster | -0.070 |
bell | -0.070 |
use | -0.069 |
iche | -0.065 |
ues | -0.061 |
Token | together |
Token ID | 1978 |
Feature activation | +4.27e-03 |
Pos logit contributions | |
ues | +0.000 |
iche | +0.000 |
aster | +0.000 |
use | +0.000 |
bell | +0.000 |
Neg logit contributions | |
Luis | -0.000 |
Bob | -0.000 |
Andy | -0.000 |
iring | -0.000 |
strength | -0.000 |
Token | every |
Token ID | 790 |
Feature activation | +3.52e-03 |
Pos logit contributions | |
aster | +0.006 |
iche | +0.006 |
ues | +0.006 |
use | +0.006 |
bell | +0.006 |
Neg logit contributions | |
Luis | -0.006 |
Bob | -0.006 |
Andy | -0.006 |
iring | -0.006 |
strength | -0.006 |
Token | day |
Token ID | 1110 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
ues | +0.007 |
iche | +0.007 |
use | +0.007 |
bell | +0.006 |
aster | +0.006 |
Neg logit contributions | |
Bob | -0.004 |
Luis | -0.004 |
Andy | -0.004 |
strength | -0.003 |
branches | -0.003 |
Token | after |
Token ID | 706 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
ues | +0.018 |
bell | +0.018 |
aster | +0.018 |
iche | +0.018 |
use | +0.017 |
Neg logit contributions | |
Luis | -0.024 |
Bob | -0.023 |
Andy | -0.023 |
strength | -0.023 |
iring | -0.023 |
Token | board |
Token ID | 3096 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
Bob | +0.012 |
Luis | +0.012 |
Andy | +0.011 |
Zig | +0.011 |
Flash | +0.011 |
Neg logit contributions | |
aster | -0.010 |
iche | -0.010 |
use | -0.010 |
bell | -0.010 |
ues | -0.009 |
Token | far |
Token ID | 1290 |
Feature activation | +4.62e-04 |
Pos logit contributions | |
Bob | +0.024 |
Luis | +0.024 |
Andy | +0.023 |
strength | +0.022 |
iring | +0.022 |
Neg logit contributions | |
iche | -0.029 |
use | -0.028 |
ues | -0.028 |
bell | -0.028 |
aster | -0.028 |
Token | away |
Token ID | 1497 |
Feature activation | -9.88e-03 |
Pos logit contributions | |
use | +0.001 |
bell | +0.001 |
ues | +0.001 |
iche | +0.001 |
aster | +0.001 |
Neg logit contributions | |
Luis | -0.001 |
Bob | -0.001 |
Andy | -0.001 |
strength | -0.001 |
iring | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
Luis | +0.018 |
Bob | +0.017 |
Andy | +0.017 |
Roll | +0.017 |
Zig | +0.017 |
Neg logit contributions | |
bell | -0.011 |
ues | -0.010 |
use | -0.010 |
arium | -0.009 |
iche | -0.009 |
Token | Mag |
Token ID | 2944 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
Bob | +0.023 |
strength | +0.022 |
Luis | +0.022 |
iring | +0.022 |
Andy | +0.022 |
Neg logit contributions | |
bell | -0.029 |
ues | -0.026 |
use | -0.026 |
Does | -0.026 |
iche | -0.025 |
Token | gy |
Token ID | 1360 |
Feature activation | -6.42e-02 |
Pos logit contributions | |
Bob | +0.035 |
Luis | +0.033 |
strength | +0.033 |
branches | +0.032 |
Andy | +0.032 |
Neg logit contributions | |
bell | -0.040 |
use | -0.038 |
ues | -0.038 |
iche | -0.037 |
aster | -0.034 |
Token | was |
Token ID | 373 |
Feature activation | -9.89e-03 |
Pos logit contributions | |
iring | +0.118 |
Luis | +0.115 |
Bob | +0.107 |
Flash | +0.106 |
Andy | +0.105 |
Neg logit contributions | |
bell | -0.072 |
use | -0.067 |
aster | -0.066 |
drew | -0.064 |
ues | -0.063 |
Token | so |
Token ID | 523 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
Luis | +0.017 |
Bob | +0.016 |
Andy | +0.016 |
iring | +0.016 |
strength | +0.016 |
Neg logit contributions | |
bell | -0.012 |
iche | -0.012 |
aster | -0.012 |
ues | -0.011 |
cheesy | -0.010 |
Token | relieved |
Token ID | 22598 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
Bob | +0.033 |
Luis | +0.033 |
Andy | +0.032 |
strength | +0.030 |
branches | +0.030 |
Neg logit contributions | |
iche | -0.022 |
bell | -0.021 |
use | -0.021 |
ues | -0.021 |
aster | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -5.15e-03 |
Pos logit contributions | |
Luis | +0.023 |
strength | +0.022 |
Calvin | +0.021 |
branches | +0.021 |
Andy | +0.021 |
Neg logit contributions | |
bell | -0.013 |
use | -0.013 |
ues | -0.013 |
aster | -0.012 |
Does | -0.011 |
Token | she |
Token ID | 673 |
Feature activation | -3.84e-03 |
Pos logit contributions | |
Luis | +0.009 |
Bob | +0.009 |
Andy | +0.009 |
strength | +0.009 |
iring | +0.009 |
Neg logit contributions | |
bell | -0.006 |
use | -0.006 |
aster | -0.005 |
iche | -0.005 |
ues | -0.005 |
Token | So |
Token ID | 1406 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
iring | +0.020 |
plunge | +0.020 |
ert | +0.020 |
reflection | +0.018 |
kel | +0.018 |
Neg logit contributions | |
named | -0.018 |
bell | -0.017 |
Does | -0.017 |
Or | -0.016 |
mary | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
iger | +0.063 |
iring | +0.062 |
kel | +0.062 |
ert | +0.062 |
strengths | +0.062 |
Neg logit contributions | |
they | -0.022 |
named | -0.021 |
bell | -0.017 |
bs | -0.015 |
Or | -0.014 |
Token | Kitty |
Token ID | 21168 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
strengths | +0.022 |
ert | +0.021 |
iring | +0.021 |
strength | +0.020 |
iger | +0.020 |
Neg logit contributions | |
named | -0.012 |
they | -0.011 |
aster | -0.011 |
Does | -0.010 |
bell | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -2.26e-03 |
Pos logit contributions | |
iring | +0.046 |
Luis | +0.042 |
Kel | +0.040 |
Andy | +0.040 |
Calvin | +0.039 |
Neg logit contributions | |
bell | -0.025 |
use | -0.024 |
aster | -0.023 |
mary | -0.023 |
drew | -0.023 |
Token | Dog |
Token ID | 8532 |
Feature activation | -5.19e-02 |
Pos logit contributions | |
ert | +0.003 |
iring | +0.003 |
sides | +0.003 |
opher | +0.003 |
reflection | +0.003 |
Neg logit contributions | |
aster | -0.003 |
use | -0.003 |
named | -0.003 |
Amen | -0.003 |
heaven | -0.003 |
Token | gy |
Token ID | 1360 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
iring | +0.084 |
Luis | +0.080 |
strength | +0.080 |
Bob | +0.076 |
Calvin | +0.074 |
Neg logit contributions | |
use | -0.073 |
bell | -0.073 |
pp | -0.061 |
iche | -0.060 |
ues | -0.059 |
Token | curled |
Token ID | 41108 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
iring | +0.137 |
Luis | +0.127 |
Andy | +0.119 |
Calvin | +0.117 |
Bob | +0.116 |
Neg logit contributions | |
aster | -0.061 |
bell | -0.060 |
use | -0.057 |
ackers | -0.054 |
iche | -0.052 |
Token | up |
Token ID | 510 |
Feature activation | +7.03e-03 |
Pos logit contributions | |
Luis | +0.028 |
iring | +0.026 |
ert | +0.026 |
Calvin | +0.025 |
axter | +0.025 |
Neg logit contributions | |
mary | -0.019 |
cheesy | -0.019 |
rant | -0.019 |
ues | -0.018 |
sip | -0.018 |
Token | next |
Token ID | 1306 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
iche | +0.012 |
use | +0.012 |
bell | +0.011 |
ues | +0.011 |
aster | +0.011 |
Neg logit contributions | |
Bob | -0.009 |
Luis | -0.009 |
Andy | -0.009 |
strength | -0.008 |
iring | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
bell | +0.040 |
use | +0.038 |
ues | +0.037 |
aster | +0.037 |
iche | +0.036 |
Neg logit contributions | |
Luis | -0.035 |
Bob | -0.034 |
iring | -0.034 |
Andy | -0.033 |
Roll | -0.032 |
Token | each |
Token ID | 1123 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
Luis | +0.018 |
Bob | +0.017 |
iring | +0.017 |
Andy | +0.017 |
strength | +0.016 |
Neg logit contributions | |
aster | -0.024 |
use | -0.024 |
iche | -0.024 |
bell | -0.024 |
ues | -0.023 |
Token | before |
Token ID | 878 |
Feature activation | -1.64e-03 |
Pos logit contributions | |
iche | +0.019 |
use | +0.018 |
ues | +0.018 |
aster | +0.018 |
bell | +0.017 |
Neg logit contributions | |
Bob | -0.013 |
Andy | -0.012 |
Luis | -0.012 |
friends | -0.011 |
strength | -0.011 |
Token | dinner |
Token ID | 8073 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
Bob | +0.002 |
Luis | +0.002 |
Andy | +0.002 |
strength | +0.002 |
iring | +0.002 |
Neg logit contributions | |
iche | -0.002 |
use | -0.002 |
ues | -0.002 |
bell | -0.002 |
aster | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +5.91e-03 |
Pos logit contributions | |
iche | +0.029 |
use | +0.029 |
ues | +0.028 |
bell | +0.028 |
aster | +0.028 |
Neg logit contributions | |
Bob | -0.025 |
Luis | -0.023 |
Andy | -0.023 |
strength | -0.022 |
iring | -0.021 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -8.75e-03 |
Pos logit contributions | |
iche | +0.009 |
use | +0.009 |
ues | +0.009 |
aster | +0.008 |
bell | +0.008 |
Neg logit contributions | |
Bob | -0.009 |
Luis | -0.009 |
Andy | -0.009 |
strength | -0.008 |
iring | -0.008 |
Token | S |
Token ID | 50 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
Luis | +0.014 |
strength | +0.014 |
iring | +0.013 |
Andy | +0.013 |
Bob | +0.013 |
Neg logit contributions | |
iche | -0.012 |
use | -0.012 |
aster | -0.011 |
bell | -0.011 |
Does | -0.011 |
Token | aman |
Token ID | 10546 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
Bob | +0.020 |
Andy | +0.018 |
Luis | +0.018 |
iring | +0.018 |
Zig | +0.017 |
Neg logit contributions | |
ues | -0.016 |
iche | -0.016 |
wasteful | -0.016 |
Does | -0.016 |
use | -0.015 |
Token | tha |
Token ID | 12898 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
Luis | +0.099 |
strength | +0.099 |
motions | +0.088 |
textures | +0.088 |
branches | +0.088 |
Neg logit contributions | |
aster | -0.089 |
use | -0.086 |
bell | -0.083 |
ues | -0.082 |
iche | -0.081 |
Token | was |
Token ID | 373 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
Bob | +0.018 |
Luis | +0.017 |
Andy | +0.016 |
strength | +0.016 |
iring | +0.015 |
Neg logit contributions | |
iche | -0.022 |
use | -0.021 |
ues | -0.021 |
bell | -0.021 |
aster | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | -6.70e-03 |
Pos logit contributions | |
Bob | +0.017 |
Luis | +0.016 |
Andy | +0.016 |
strength | +0.015 |
iring | +0.015 |
Neg logit contributions | |
use | -0.020 |
ues | -0.020 |
iche | -0.020 |
bell | -0.020 |
aster | -0.019 |
Token | lazy |
Token ID | 16931 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
Bob | +0.005 |
Luis | +0.004 |
friends | +0.004 |
Andy | +0.004 |
Flash | +0.003 |
Neg logit contributions | |
ues | -0.016 |
use | -0.016 |
iche | -0.015 |
bell | -0.015 |
aster | -0.015 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
Bob | +0.021 |
Luis | +0.020 |
Andy | +0.020 |
strength | +0.019 |
iring | +0.019 |
Neg logit contributions | |
iche | -0.034 |
use | -0.034 |
bell | -0.034 |
aster | -0.034 |
ues | -0.033 |
Token | we |
Token ID | 356 |
Feature activation | +4.66e-03 |
Pos logit contributions | |
Luis | +0.019 |
strength | +0.018 |
Kel | +0.018 |
branches | +0.017 |
Calvin | +0.017 |
Neg logit contributions | |
ues | -0.013 |
use | -0.013 |
Does | -0.013 |
iche | -0.013 |
aster | -0.012 |
Token | are |
Token ID | 389 |
Feature activation | +1.14e-03 |
Pos logit contributions | |
iche | +0.006 |
ues | +0.006 |
aster | +0.006 |
bell | +0.006 |
use | +0.006 |
Neg logit contributions | |
Bob | -0.008 |
Luis | -0.008 |
Andy | -0.008 |
strength | -0.007 |
Zig | -0.007 |
Token | friends |
Token ID | 2460 |
Feature activation | -6.72e-03 |
Pos logit contributions | |
iche | +0.002 |
aster | +0.002 |
bell | +0.002 |
ues | +0.002 |
use | +0.002 |
Neg logit contributions | |
Luis | -0.002 |
Bob | -0.002 |
Andy | -0.002 |
strength | -0.002 |
iring | -0.002 |
Token | ." |
Token ID | 526 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
Bob | +0.010 |
Luis | +0.010 |
Andy | +0.010 |
strength | +0.009 |
iring | +0.009 |
Neg logit contributions | |
iche | -0.010 |
use | -0.010 |
aster | -0.010 |
ues | -0.010 |
bell | -0.010 |
Token | Bug |
Token ID | 15217 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
iring | +0.017 |
strength | +0.016 |
Luis | +0.015 |
branches | +0.015 |
courage | +0.015 |
Neg logit contributions | |
iche | -0.013 |
Does | -0.013 |
use | -0.013 |
aster | -0.012 |
ues | -0.012 |
Token | gy |
Token ID | 1360 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
Luis | +0.079 |
iring | +0.079 |
strength | +0.078 |
plunge | +0.076 |
Bob | +0.074 |
Neg logit contributions | |
bell | -0.054 |
mary | -0.053 |
use | -0.052 |
iche | -0.051 |
ackers | -0.049 |
Token | smiled |
Token ID | 13541 |
Feature activation | +1.33e-03 |
Pos logit contributions | |
iring | +0.119 |
Luis | +0.117 |
Andy | +0.109 |
Bob | +0.107 |
Calvin | +0.106 |
Neg logit contributions | |
bell | -0.069 |
aster | -0.068 |
use | -0.064 |
ues | -0.064 |
iche | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | -5.23e-03 |
Pos logit contributions | |
bell | +0.002 |
iche | +0.002 |
ues | +0.002 |
use | +0.002 |
aster | +0.002 |
Neg logit contributions | |
Bob | -0.002 |
Luis | -0.002 |
Andy | -0.002 |
strength | -0.002 |
iring | -0.002 |
Token | said |
Token ID | 531 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
Luis | +0.009 |
iring | +0.009 |
Andy | +0.009 |
Bob | +0.009 |
strength | +0.008 |
Neg logit contributions | |
iche | -0.006 |
aster | -0.005 |
ues | -0.005 |
use | -0.005 |
bell | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -3.31e-03 |
Pos logit contributions | |
Bob | +0.023 |
Luis | +0.022 |
Andy | +0.021 |
strength | +0.020 |
iring | +0.020 |
Neg logit contributions | |
iche | -0.026 |
use | -0.026 |
ues | -0.026 |
bell | -0.026 |
aster | -0.026 |
Token | " |
Token ID | 366 |
Feature activation | +1.14e-03 |
Pos logit contributions | |
Bob | +0.005 |
Luis | +0.005 |
Andy | +0.005 |
strength | +0.004 |
iring | +0.004 |
Neg logit contributions | |
iche | -0.005 |
use | -0.005 |
ues | -0.005 |
bell | -0.005 |
aster | -0.005 |
Token | bird |
Token ID | 6512 |
Feature activation | +7.05e-03 |
Pos logit contributions | |
Bob | +0.003 |
Luis | +0.003 |
Andy | +0.003 |
friends | +0.003 |
branches | +0.003 |
Neg logit contributions | |
ues | -0.006 |
iche | -0.006 |
use | -0.005 |
bell | -0.005 |
aster | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -8.48e-03 |
Pos logit contributions | |
ues | +0.008 |
use | +0.008 |
iche | +0.008 |
bell | +0.007 |
wasteful | +0.007 |
Neg logit contributions | |
Bob | -0.013 |
friends | -0.013 |
Andy | -0.013 |
iring | -0.013 |
Luis | -0.013 |
Token | The |
Token ID | 383 |
Feature activation | -2.37e-03 |
Pos logit contributions | |
Bob | +0.011 |
Luis | +0.010 |
Andy | +0.010 |
Zig | +0.009 |
Flash | +0.009 |
Neg logit contributions | |
use | -0.015 |
iche | -0.015 |
ues | -0.015 |
bell | -0.015 |
aster | -0.015 |
Token | bird |
Token ID | 6512 |
Feature activation | +8.95e-03 |
Pos logit contributions | |
Luis | +0.003 |
Bob | +0.003 |
Andy | +0.003 |
Calvin | +0.003 |
Owen | +0.003 |
Neg logit contributions | |
iche | -0.004 |
bell | -0.004 |
aster | -0.004 |
use | -0.004 |
slice | -0.004 |
Token | had |
Token ID | 550 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
ues | +0.016 |
aster | +0.016 |
use | +0.015 |
iche | +0.015 |
bell | +0.015 |
Neg logit contributions | |
Bob | -0.011 |
Andy | -0.011 |
friends | -0.010 |
Luis | -0.010 |
branches | -0.010 |
Token | gray |
Token ID | 12768 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
Luis | +0.024 |
Calvin | +0.023 |
Owen | +0.022 |
Andy | +0.022 |
ert | +0.022 |
Neg logit contributions | |
iche | -0.013 |
wil | -0.013 |
drew | -0.013 |
bell | -0.012 |
aster | -0.012 |
Token | feathers |
Token ID | 27400 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
Luis | +0.063 |
Bob | +0.057 |
Andy | +0.054 |
iring | +0.054 |
Calvin | +0.054 |
Neg logit contributions | |
iche | -0.127 |
bell | -0.125 |
use | -0.123 |
aster | -0.121 |
ues | -0.119 |
Token | and |
Token ID | 290 |
Feature activation | -5.65e-03 |
Pos logit contributions | |
Bob | +0.040 |
Luis | +0.040 |
Andy | +0.039 |
strength | +0.037 |
iring | +0.036 |
Neg logit contributions | |
iche | -0.040 |
use | -0.039 |
bell | -0.039 |
ues | -0.039 |
aster | -0.039 |
Token | was |
Token ID | 373 |
Feature activation | +4.68e-03 |
Pos logit contributions | |
Bob | +0.008 |
Luis | +0.008 |
Andy | +0.008 |
iring | +0.008 |
strength | +0.008 |
Neg logit contributions | |
iche | -0.008 |
use | -0.008 |
bell | -0.008 |
aster | -0.008 |
ues | -0.008 |
Token | very |
Token ID | 845 |
Feature activation | -3.09e-03 |
Pos logit contributions | |
iche | +0.006 |
bell | +0.005 |
ues | +0.005 |
aster | +0.005 |
use | +0.005 |
Neg logit contributions | |
Luis | -0.008 |
Bob | -0.008 |
Andy | -0.008 |
strength | -0.008 |
iring | -0.008 |
Token | fragile |
Token ID | 21049 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
Bob | +0.004 |
Luis | +0.004 |
Andy | +0.004 |
strength | +0.004 |
iring | +0.004 |
Neg logit contributions | |
iche | -0.005 |
use | -0.005 |
ues | -0.005 |
aster | -0.005 |
bell | -0.005 |
Token | happy |
Token ID | 3772 |
Feature activation | -3.94e-03 |
Pos logit contributions | |
use | +0.006 |
ues | +0.006 |
iche | +0.006 |
aster | +0.006 |
bell | +0.006 |
Neg logit contributions | |
Bob | -0.007 |
friends | -0.007 |
strength | -0.007 |
Luis | -0.007 |
Andy | -0.007 |
Token | !" |
Token ID | 2474 |
Feature activation | -8.20e-03 |
Pos logit contributions | |
Bob | +0.006 |
Luis | +0.006 |
Andy | +0.006 |
strength | +0.005 |
iring | +0.005 |
Neg logit contributions | |
iche | -0.006 |
use | -0.006 |
ues | -0.006 |
bell | -0.006 |
aster | -0.005 |
Token | Kitty |
Token ID | 21168 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
iring | +0.011 |
ert | +0.010 |
plunge | +0.010 |
strength | +0.010 |
reflection | +0.010 |
Neg logit contributions | |
named | -0.013 |
batch | -0.013 |
aster | -0.012 |
bell | -0.012 |
Does | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -1.92e-03 |
Pos logit contributions | |
iring | +0.049 |
Luis | +0.047 |
plunge | +0.046 |
Kel | +0.045 |
strength | +0.044 |
Neg logit contributions | |
bell | -0.027 |
mary | -0.024 |
drew | -0.024 |
forg | -0.024 |
use | -0.024 |
Token | Dog |
Token ID | 8532 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
ert | +0.002 |
iring | +0.002 |
strength | +0.002 |
Luis | +0.002 |
Ricky | +0.002 |
Neg logit contributions | |
aster | -0.003 |
use | -0.003 |
Amen | -0.003 |
named | -0.003 |
Or | -0.003 |
Token | gy |
Token ID | 1360 |
Feature activation | -6.25e-02 |
Pos logit contributions | |
iring | +0.076 |
Luis | +0.075 |
strength | +0.073 |
Bob | +0.071 |
Calvin | +0.068 |
Neg logit contributions | |
bell | -0.070 |
use | -0.070 |
ues | -0.060 |
iche | -0.059 |
pp | -0.059 |
Token | were |
Token ID | 547 |
Feature activation | +4.93e-03 |
Pos logit contributions | |
iring | +0.124 |
Luis | +0.122 |
Bob | +0.115 |
Andy | +0.115 |
Flash | +0.112 |
Neg logit contributions | |
bell | -0.063 |
use | -0.057 |
ues | -0.056 |
aster | -0.056 |
drew | -0.054 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
bell | +0.004 |
iche | +0.003 |
ues | +0.003 |
Amen | +0.003 |
cheesy | +0.003 |
Neg logit contributions | |
Luis | -0.010 |
ert | -0.010 |
Andy | -0.010 |
iring | -0.010 |
Bob | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
Luis | +0.021 |
Bob | +0.019 |
Andy | +0.019 |
Kel | +0.019 |
strength | +0.019 |
Neg logit contributions | |
bell | -0.019 |
ues | -0.019 |
use | -0.019 |
iche | -0.019 |
aster | -0.019 |
Token | They |
Token ID | 1119 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
plunge | +0.045 |
ert | +0.044 |
footing | +0.044 |
strength | +0.043 |
reflection | +0.042 |
Neg logit contributions | |
bell | -0.004 |
ours | -0.002 |
mary | -0.002 |
iche | -0.002 |
Amen | -0.002 |
Token | took |
Token ID | 1718 |
Feature activation | -6.99e-03 |
Pos logit contributions | |
Bob | +0.021 |
Luis | +0.021 |
Andy | +0.021 |
iring | +0.020 |
strength | +0.020 |
Neg logit contributions | |
iche | -0.015 |
use | -0.015 |
bell | -0.015 |
ues | -0.015 |
aster | -0.015 |
Token | Raven |
Token ID | 12552 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
iche | +0.014 |
aster | +0.014 |
bell | +0.014 |
use | +0.013 |
slice | +0.012 |
Neg logit contributions | |
iring | -0.018 |
strength | -0.017 |
surroundings | -0.016 |
directions | -0.016 |
Luis | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
iche | +0.024 |
use | +0.024 |
ues | +0.023 |
bell | +0.023 |
aster | +0.023 |
Neg logit contributions | |
Bob | -0.024 |
Luis | -0.023 |
Andy | -0.023 |
iring | -0.022 |
strength | -0.022 |
Token | Raven |
Token ID | 12552 |
Feature activation | +8.00e-03 |
Pos logit contributions | |
Luis | +0.017 |
ert | +0.016 |
Andy | +0.016 |
strength | +0.015 |
iring | +0.015 |
Neg logit contributions | |
bell | -0.031 |
use | -0.031 |
Amen | -0.030 |
iche | -0.030 |
Does | -0.030 |
Token | had |
Token ID | 550 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
iche | +0.014 |
ues | +0.013 |
aster | +0.013 |
bell | +0.013 |
use | +0.013 |
Neg logit contributions | |
Bob | -0.011 |
friends | -0.010 |
Andy | -0.010 |
Luis | -0.010 |
Zig | -0.009 |
Token | shiny |
Token ID | 22441 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
Luis | +0.019 |
iring | +0.018 |
Calvin | +0.018 |
Owen | +0.018 |
Andy | +0.018 |
Neg logit contributions | |
iche | -0.011 |
drew | -0.011 |
aster | -0.011 |
draws | -0.010 |
wrote | -0.010 |
Token | black |
Token ID | 2042 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
Luis | +0.031 |
Bob | +0.027 |
Andy | +0.027 |
Calvin | +0.027 |
Andy | +0.027 |
Neg logit contributions | |
use | -0.044 |
notebooks | -0.044 |
iche | -0.043 |
bell | -0.043 |
ues | -0.043 |
Token | feathers |
Token ID | 27400 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
Luis | +0.071 |
Bob | +0.064 |
Andy | +0.063 |
Calvin | +0.061 |
iring | +0.061 |
Neg logit contributions | |
bell | -0.115 |
use | -0.113 |
iche | -0.113 |
aster | -0.109 |
ues | -0.109 |
Token | and |
Token ID | 290 |
Feature activation | +4.60e-03 |
Pos logit contributions | |
Luis | +0.051 |
Bob | +0.049 |
Andy | +0.049 |
Calvin | +0.046 |
Kel | +0.045 |
Neg logit contributions | |
iche | -0.038 |
bell | -0.038 |
ues | -0.037 |
use | -0.037 |
aster | -0.036 |
Token | a |
Token ID | 257 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
iche | +0.006 |
bell | +0.006 |
use | +0.006 |
aster | +0.006 |
ues | +0.006 |
Neg logit contributions | |
Luis | -0.007 |
Bob | -0.007 |
Andy | -0.007 |
iring | -0.007 |
strength | -0.007 |
Token | cheerful |
Token ID | 37999 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
Bob | +0.014 |
Luis | +0.014 |
Andy | +0.013 |
strength | +0.013 |
branches | +0.013 |
Neg logit contributions | |
iche | -0.019 |
use | -0.019 |
ues | -0.019 |
aster | -0.019 |
bell | -0.019 |
Token | song |
Token ID | 3496 |
Feature activation | +3.31e-04 |
Pos logit contributions | |
Luis | +0.030 |
Bob | +0.030 |
Andy | +0.029 |
iring | +0.028 |
strength | +0.027 |
Neg logit contributions | |
iche | -0.046 |
bell | -0.045 |
use | -0.044 |
ues | -0.044 |
aster | -0.044 |
Token | outside |
Token ID | 2354 |
Feature activation | -3.04e-03 |
Pos logit contributions | |
Luis | +0.037 |
strength | +0.035 |
Andy | +0.034 |
Zig | +0.034 |
Calvin | +0.034 |
Neg logit contributions | |
use | -0.024 |
iche | -0.024 |
bell | -0.024 |
aster | -0.023 |
cheesy | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +3.31e-03 |
Pos logit contributions | |
Luis | +0.004 |
Bob | +0.004 |
Andy | +0.004 |
strength | +0.004 |
iring | +0.004 |
Neg logit contributions | |
iche | -0.004 |
use | -0.004 |
bell | -0.004 |
aster | -0.004 |
ues | -0.004 |
Token | Kitty |
Token ID | 21168 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
iche | +0.005 |
bell | +0.005 |
aster | +0.005 |
use | +0.005 |
ues | +0.004 |
Neg logit contributions | |
Luis | -0.005 |
Bob | -0.005 |
iring | -0.005 |
strength | -0.005 |
Andy | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -2.52e-04 |
Pos logit contributions | |
Luis | +0.029 |
iring | +0.029 |
Bob | +0.028 |
strength | +0.028 |
Andy | +0.028 |
Neg logit contributions | |
use | -0.020 |
bell | -0.019 |
iche | -0.019 |
aster | -0.018 |
ackers | -0.018 |
Token | Dog |
Token ID | 8532 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
iring | +0.000 |
ert | +0.000 |
strength | +0.000 |
surroundings | +0.000 |
plunge | +0.000 |
Neg logit contributions | |
aster | -0.000 |
named | -0.000 |
heaven | -0.000 |
use | -0.000 |
wasteful | -0.000 |
Token | gy |
Token ID | 1360 |
Feature activation | -6.18e-02 |
Pos logit contributions | |
iring | +0.075 |
Luis | +0.074 |
Bob | +0.070 |
strength | +0.070 |
Andy | +0.068 |
Neg logit contributions | |
use | -0.055 |
bell | -0.053 |
iche | -0.049 |
ues | -0.046 |
aster | -0.045 |
Token | were |
Token ID | 547 |
Feature activation | -2.44e-03 |
Pos logit contributions | |
iring | +0.112 |
Luis | +0.112 |
Bob | +0.105 |
Andy | +0.103 |
Calvin | +0.101 |
Neg logit contributions | |
aster | -0.070 |
bell | -0.070 |
use | -0.070 |
iche | -0.068 |
ues | -0.062 |
Token | inside |
Token ID | 2641 |
Feature activation | -3.85e-03 |
Pos logit contributions | |
Luis | +0.004 |
ert | +0.004 |
Calvin | +0.004 |
strength | +0.004 |
Bob | +0.004 |
Neg logit contributions | |
iche | -0.003 |
wasteful | -0.002 |
cheesy | -0.002 |
ackers | -0.002 |
bell | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +9.44e-03 |
Pos logit contributions | |
Luis | +0.005 |
Bob | +0.005 |
Andy | +0.005 |
iring | +0.005 |
strength | +0.005 |
Neg logit contributions | |
iche | -0.006 |
use | -0.006 |
aster | -0.006 |
bell | -0.006 |
ues | -0.006 |
Token | house |
Token ID | 2156 |
Feature activation | +9.92e-03 |
Pos logit contributions | |
iche | +0.015 |
use | +0.015 |
bell | +0.014 |
aster | +0.014 |
ues | +0.014 |
Neg logit contributions | |
Bob | -0.013 |
Luis | -0.013 |
Andy | -0.013 |
strength | -0.012 |
iring | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +1.15e-03 |
Pos logit contributions | |
iche | +0.015 |
use | +0.015 |
ues | +0.015 |
bell | +0.015 |
aster | +0.014 |
Neg logit contributions | |
Bob | -0.015 |
Luis | -0.014 |
Andy | -0.014 |
strength | -0.013 |
iring | -0.013 |
Token | together |
Token ID | 1978 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
Bob | +0.013 |
Luis | +0.013 |
Andy | +0.013 |
strength | +0.012 |
iring | +0.012 |
Neg logit contributions | |
iche | -0.014 |
use | -0.014 |
ues | -0.014 |
bell | -0.014 |
aster | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
iche | +0.025 |
ues | +0.025 |
use | +0.025 |
aster | +0.024 |
bell | +0.024 |
Neg logit contributions | |
Luis | -0.028 |
Bob | -0.028 |
Andy | -0.028 |
strength | -0.027 |
iring | -0.027 |
Token | Kitty |
Token ID | 21168 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
ert | +0.028 |
iring | +0.025 |
reflection | +0.023 |
plunge | +0.023 |
himself | +0.023 |
Neg logit contributions | |
bell | -0.026 |
named | -0.026 |
Does | -0.025 |
mary | -0.023 |
use | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +1.60e-03 |
Pos logit contributions | |
iring | +0.033 |
Luis | +0.032 |
strength | +0.030 |
Andy | +0.030 |
plunge | +0.029 |
Neg logit contributions | |
use | -0.020 |
bell | -0.018 |
iche | -0.017 |
mary | -0.017 |
drew | -0.017 |
Token | Dog |
Token ID | 8532 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
use | +0.003 |
aster | +0.003 |
Amen | +0.003 |
named | +0.002 |
bell | +0.002 |
Neg logit contributions | |
iring | -0.002 |
ert | -0.002 |
strength | -0.002 |
sides | -0.002 |
reflection | -0.002 |
Token | gy |
Token ID | 1360 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
iring | +0.063 |
Luis | +0.062 |
Bob | +0.059 |
strength | +0.059 |
Calvin | +0.056 |
Neg logit contributions | |
use | -0.068 |
bell | -0.067 |
iche | -0.061 |
ues | -0.061 |
rant | -0.057 |
Token | were |
Token ID | 547 |
Feature activation | +3.26e-03 |
Pos logit contributions | |
iring | +0.114 |
Luis | +0.113 |
Bob | +0.106 |
Andy | +0.105 |
Flash | +0.103 |
Neg logit contributions | |
use | -0.068 |
bell | -0.068 |
aster | -0.066 |
iche | -0.064 |
ues | -0.062 |
Token | very |
Token ID | 845 |
Feature activation | -3.73e-03 |
Pos logit contributions | |
iche | +0.003 |
wasteful | +0.003 |
named | +0.002 |
cheesy | +0.002 |
ues | +0.002 |
Neg logit contributions | |
ert | -0.006 |
Luis | -0.006 |
iring | -0.006 |
strength | -0.006 |
Andy | -0.006 |
Token | happy |
Token ID | 3772 |
Feature activation | -7.80e-03 |
Pos logit contributions | |
Luis | +0.007 |
Bob | +0.007 |
Andy | +0.006 |
strength | +0.006 |
branches | +0.006 |
Neg logit contributions | |
iche | -0.004 |
bell | -0.004 |
ues | -0.004 |
use | -0.004 |
aster | -0.004 |
Token | when |
Token ID | 618 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
Luis | +0.015 |
Kel | +0.015 |
Calvin | +0.015 |
strength | +0.015 |
plunge | +0.014 |
Neg logit contributions | |
ues | -0.007 |
arium | -0.006 |
iche | -0.006 |
heaven | -0.006 |
bell | -0.006 |
Token | they |
Token ID | 484 |
Feature activation | +3.50e-03 |
Pos logit contributions | |
iring | +0.068 |
Luis | +0.067 |
ert | +0.066 |
strength | +0.066 |
se | +0.066 |
Neg logit contributions | |
bell | -0.009 |
aster | -0.008 |
use | -0.007 |
iche | -0.006 |
cheesy | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -3.76e-04 |
Pos logit contributions | |
iche | +0.001 |
use | +0.001 |
aster | +0.001 |
ues | +0.001 |
bell | +0.001 |
Neg logit contributions | |
Bob | -0.001 |
Luis | -0.001 |
Andy | -0.000 |
strength | -0.000 |
iring | -0.000 |
Token | The |
Token ID | 464 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
Bob | +0.001 |
Luis | +0.000 |
Andy | +0.000 |
strength | +0.000 |
iring | +0.000 |
Neg logit contributions | |
iche | -0.001 |
use | -0.001 |
ues | -0.001 |
aster | -0.001 |
bell | -0.001 |
Token | little |
Token ID | 1310 |
Feature activation | +7.00e-03 |
Pos logit contributions | |
bell | +0.033 |
iche | +0.032 |
use | +0.032 |
aster | +0.032 |
ues | +0.031 |
Neg logit contributions | |
Bob | -0.012 |
Luis | -0.012 |
Andy | -0.011 |
iring | -0.010 |
Zig | -0.010 |
Token | girl |
Token ID | 2576 |
Feature activation | -5.20e-03 |
Pos logit contributions | |
use | +0.009 |
bell | +0.009 |
iche | +0.008 |
aster | +0.008 |
ues | +0.008 |
Neg logit contributions | |
Bob | -0.012 |
Luis | -0.012 |
iring | -0.011 |
Zig | -0.011 |
Andy | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -2.87e-03 |
Pos logit contributions | |
iring | +0.010 |
Luis | +0.009 |
Andy | +0.009 |
Bob | +0.009 |
strength | +0.009 |
Neg logit contributions | |
bell | -0.006 |
aster | -0.005 |
ues | -0.005 |
use | -0.005 |
slice | -0.005 |
Token | truck |
Token ID | 7779 |
Feature activation | -6.14e-02 |
Pos logit contributions | |
iring | +0.005 |
strength | +0.004 |
plunge | +0.004 |
hind | +0.004 |
ert | +0.004 |
Neg logit contributions | |
aster | -0.004 |
folder | -0.003 |
batch | -0.003 |
named | -0.003 |
heaven | -0.003 |
Token | waved |
Token ID | 26834 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
iring | +0.117 |
Luis | +0.111 |
strength | +0.107 |
Bob | +0.107 |
Andy | +0.106 |
Neg logit contributions | |
bell | -0.067 |
aster | -0.055 |
ues | -0.054 |
glued | -0.052 |
drew | -0.051 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
bell | +0.016 |
ues | +0.016 |
use | +0.015 |
aster | +0.014 |
cheesy | +0.014 |
Neg logit contributions | |
Luis | -0.028 |
Andy | -0.027 |
iring | -0.027 |
Andy | -0.027 |
Bob | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -6.54e-04 |
Pos logit contributions | |
Luis | +0.019 |
Andy | +0.018 |
Calvin | +0.018 |
Owen | +0.018 |
iring | +0.017 |
Neg logit contributions | |
ues | -0.014 |
bell | -0.014 |
use | -0.013 |
iche | -0.012 |
cheesy | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
Luis | +0.001 |
iring | +0.001 |
Bob | +0.001 |
Andy | +0.001 |
strength | +0.001 |
Neg logit contributions | |
bell | -0.001 |
aster | -0.001 |
iche | -0.001 |
ues | -0.001 |
use | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -3.47e-03 |
Pos logit contributions | |
iring | +0.025 |
Luis | +0.023 |
strength | +0.023 |
iger | +0.022 |
Calvin | +0.022 |
Neg logit contributions | |
aster | -0.016 |
bell | -0.016 |
use | -0.014 |
drew | -0.014 |
gallery | -0.014 |
Token | Tom |
Token ID | 13787 |
Feature activation | +8.40e-03 |
Pos logit contributions | |
Luis | +0.019 |
Bob | +0.018 |
Andy | +0.018 |
strength | +0.018 |
iring | +0.018 |
Neg logit contributions | |
iche | -0.017 |
use | -0.017 |
aster | -0.016 |
bell | -0.016 |
ues | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -5.65e-03 |
Pos logit contributions | |
ues | +0.013 |
iche | +0.012 |
bell | +0.012 |
use | +0.012 |
aster | +0.012 |
Neg logit contributions | |
Bob | -0.013 |
Luis | -0.012 |
Andy | -0.012 |
strength | -0.012 |
friends | -0.011 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.17e-03 |
Pos logit contributions | |
Luis | +0.008 |
Bob | +0.008 |
Andy | +0.007 |
iring | +0.007 |
strength | +0.007 |
Neg logit contributions | |
iche | -0.009 |
use | -0.009 |
aster | -0.009 |
bell | -0.009 |
ues | -0.009 |
Token | were |
Token ID | 547 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
ues | +0.004 |
iche | +0.004 |
bell | +0.004 |
use | +0.004 |
aster | +0.004 |
Neg logit contributions | |
Bob | -0.005 |
Luis | -0.005 |
Andy | -0.005 |
strength | -0.005 |
branches | -0.005 |
Token | squirrel |
Token ID | 33039 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
Bob | +0.017 |
friends | +0.016 |
Luis | +0.016 |
Andy | +0.016 |
iring | +0.015 |
Neg logit contributions | |
use | -0.039 |
ues | -0.038 |
bell | -0.038 |
iche | -0.038 |
aster | -0.037 |
Token | s |
Token ID | 82 |
Feature activation | -6.13e-02 |
Pos logit contributions | |
Luis | +0.057 |
Bob | +0.057 |
strength | +0.056 |
Andy | +0.055 |
iring | +0.053 |
Neg logit contributions | |
iche | -0.037 |
bell | -0.036 |
use | -0.035 |
ues | -0.035 |
aster | -0.035 |
Token | who |
Token ID | 508 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
Luis | +0.107 |
strength | +0.104 |
Kel | +0.098 |
Andy | +0.098 |
Owen | +0.097 |
Neg logit contributions | |
iche | -0.067 |
bell | -0.066 |
Amen | -0.062 |
slice | -0.062 |
aster | -0.062 |
Token | lived |
Token ID | 5615 |
Feature activation | -7.12e-03 |
Pos logit contributions | |
Luis | +0.026 |
Bob | +0.025 |
iring | +0.025 |
Andy | +0.025 |
strength | +0.024 |
Neg logit contributions | |
use | -0.015 |
iche | -0.014 |
bell | -0.014 |
aster | -0.014 |
ues | -0.013 |
Token | in |
Token ID | 287 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
Luis | +0.009 |
Bob | +0.009 |
Andy | +0.009 |
strength | +0.008 |
Owen | +0.008 |
Neg logit contributions | |
iche | -0.012 |
use | -0.012 |
ues | -0.011 |
bell | -0.011 |
aster | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -8.24e-03 |
Pos logit contributions | |
iring | +0.029 |
Luis | +0.028 |
strength | +0.027 |
Bob | +0.026 |
ert | +0.026 |
Neg logit contributions | |
aster | -0.031 |
iche | -0.029 |
heaven | -0.028 |
bell | -0.028 |
use | -0.028 |
Token | big |
Token ID | 1263 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
Bob | +0.009 |
Luis | +0.008 |
branches | +0.008 |
Andy | +0.008 |
friends | +0.008 |
Neg logit contributions | |
ues | -0.016 |
iche | -0.016 |
use | -0.016 |
aster | -0.016 |
bell | -0.016 |
Token | So |
Token ID | 1406 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
ert | +0.021 |
plunge | +0.021 |
iring | +0.021 |
reflection | +0.020 |
footing | +0.020 |
Neg logit contributions | |
named | -0.011 |
bell | -0.010 |
Does | -0.009 |
bs | -0.009 |
Or | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
ert | +0.070 |
iring | +0.069 |
strengths | +0.068 |
reflection | +0.068 |
kel | +0.068 |
Neg logit contributions | |
they | -0.017 |
named | -0.017 |
bell | -0.013 |
use | -0.010 |
much | -0.010 |
Token | Kitty |
Token ID | 21168 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
strengths | +0.023 |
ert | +0.023 |
iring | +0.022 |
strength | +0.022 |
surroundings | +0.022 |
Neg logit contributions | |
named | -0.006 |
they | -0.006 |
Does | -0.005 |
aster | -0.005 |
bell | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +4.82e-03 |
Pos logit contributions | |
iring | +0.041 |
Luis | +0.037 |
Flash | +0.036 |
Andy | +0.036 |
Calvin | +0.036 |
Neg logit contributions | |
bell | -0.021 |
aster | -0.021 |
drew | -0.021 |
added | -0.020 |
use | -0.020 |
Token | Dog |
Token ID | 8532 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
named | +0.007 |
aster | +0.007 |
use | +0.006 |
Amen | +0.006 |
talked | +0.006 |
Neg logit contributions | |
ert | -0.007 |
iring | -0.007 |
sides | -0.006 |
opher | -0.006 |
reflection | -0.006 |
Token | gy |
Token ID | 1360 |
Feature activation | -6.13e-02 |
Pos logit contributions | |
iring | +0.072 |
Luis | +0.069 |
strength | +0.066 |
Bob | +0.066 |
Calvin | +0.063 |
Neg logit contributions | |
use | -0.070 |
bell | -0.070 |
ues | -0.062 |
iche | -0.060 |
drew | -0.058 |
Token | took |
Token ID | 1718 |
Feature activation | -1.79e-03 |
Pos logit contributions | |
iring | +0.125 |
Luis | +0.118 |
Flash | +0.111 |
Calvin | +0.111 |
Andy | +0.109 |
Neg logit contributions | |
aster | -0.063 |
bell | -0.063 |
ues | -0.056 |
use | -0.055 |
iche | -0.054 |
Token | turns |
Token ID | 4962 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
iring | +0.004 |
ert | +0.003 |
Luis | +0.003 |
axter | +0.003 |
Andy | +0.003 |
Neg logit contributions | |
aster | -0.002 |
sip | -0.002 |
bs | -0.002 |
iche | -0.002 |
dollar | -0.002 |
Token | sliding |
Token ID | 22292 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
Luis | +0.028 |
iring | +0.027 |
Andy | +0.027 |
strength | +0.026 |
Calvin | +0.026 |
Neg logit contributions | |
aster | -0.028 |
ues | -0.027 |
bell | -0.027 |
iche | -0.026 |
ours | -0.025 |
Token | with |
Token ID | 351 |
Feature activation | -9.71e-03 |
Pos logit contributions | |
bell | +0.019 |
ues | +0.019 |
aster | +0.018 |
use | +0.017 |
iche | +0.017 |
Neg logit contributions | |
Luis | -0.022 |
Andy | -0.021 |
Bob | -0.021 |
strength | -0.021 |
iring | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +2.09e-04 |
Pos logit contributions | |
iring | +0.018 |
ert | +0.016 |
unn | +0.015 |
axter | +0.015 |
surroundings | +0.015 |
Neg logit contributions | |
aster | -0.012 |
sip | -0.010 |
slice | -0.010 |
bell | -0.009 |
heaven | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -3.62e-03 |
Pos logit contributions | |
Luis | +0.009 |
strength | +0.008 |
Bob | +0.008 |
iring | +0.008 |
branches | +0.008 |
Neg logit contributions | |
use | -0.008 |
aster | -0.008 |
bell | -0.007 |
iche | -0.007 |
ues | -0.007 |
Token | K |
Token ID | 42 |
Feature activation | -2.71e-03 |
Pos logit contributions | |
Luis | +0.005 |
strength | +0.005 |
Bob | +0.004 |
courage | +0.004 |
ert | +0.004 |
Neg logit contributions | |
use | -0.006 |
bell | -0.006 |
Or | -0.005 |
aster | -0.005 |
Amen | -0.005 |
Token | itty |
Token ID | 9760 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
Bob | +0.004 |
Luis | +0.004 |
Andy | +0.004 |
strength | +0.004 |
iring | +0.004 |
Neg logit contributions | |
use | -0.004 |
iche | -0.004 |
bell | -0.004 |
ues | -0.004 |
aster | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +2.63e-03 |
Pos logit contributions | |
Luis | +0.040 |
iring | +0.040 |
Bob | +0.038 |
strength | +0.037 |
Andy | +0.037 |
Neg logit contributions | |
bell | -0.027 |
use | -0.027 |
iche | -0.026 |
ues | -0.026 |
aster | -0.025 |
Token | Dog |
Token ID | 8532 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
use | +0.004 |
named | +0.004 |
Amen | +0.004 |
aster | +0.004 |
mean | +0.003 |
Neg logit contributions | |
iring | -0.004 |
ert | -0.004 |
strength | -0.003 |
sides | -0.003 |
footing | -0.003 |
Token | gy |
Token ID | 1360 |
Feature activation | -6.11e-02 |
Pos logit contributions | |
iring | +0.072 |
Luis | +0.070 |
strength | +0.068 |
Bob | +0.065 |
Calvin | +0.063 |
Neg logit contributions | |
use | -0.069 |
bell | -0.067 |
iche | -0.057 |
ues | -0.057 |
rant | -0.056 |
Token | thought |
Token ID | 1807 |
Feature activation | +6.17e-04 |
Pos logit contributions | |
iring | +0.118 |
Luis | +0.117 |
Bob | +0.109 |
Calvin | +0.108 |
Flash | +0.108 |
Neg logit contributions | |
bell | -0.063 |
aster | -0.061 |
use | -0.061 |
ues | -0.057 |
iche | -0.056 |
Token | hard |
Token ID | 1327 |
Feature activation | +3.75e-03 |
Pos logit contributions | |
aster | +0.001 |
bell | +0.001 |
ues | +0.001 |
use | +0.001 |
ours | +0.001 |
Neg logit contributions | |
iring | -0.001 |
Luis | -0.001 |
fl | -0.001 |
Calvin | -0.001 |
Andy | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
bell | +0.004 |
use | +0.004 |
ues | +0.004 |
iche | +0.004 |
aster | +0.004 |
Neg logit contributions | |
Luis | -0.007 |
Bob | -0.006 |
branches | -0.006 |
iring | -0.006 |
Andy | -0.006 |
Token | They |
Token ID | 1119 |
Feature activation | -8.51e-03 |
Pos logit contributions | |
ert | +0.043 |
plunge | +0.040 |
iring | +0.040 |
Luis | +0.040 |
reflection | +0.039 |
Neg logit contributions | |
bell | -0.010 |
ues | -0.006 |
Does | -0.006 |
Or | -0.006 |
ours | -0.005 |
Token | decided |
Token ID | 3066 |
Feature activation | +5.19e-03 |
Pos logit contributions | |
Bob | +0.015 |
Luis | +0.015 |
Andy | +0.014 |
iring | +0.014 |
strength | +0.014 |
Neg logit contributions | |
iche | -0.011 |
use | -0.010 |
bell | -0.010 |
ues | -0.010 |
aster | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +2.58e-03 |
Pos logit contributions | |
branches | +0.024 |
strength | +0.024 |
legs | +0.024 |
feet | +0.024 |
plunge | +0.024 |
Neg logit contributions | |
iche | -0.014 |
ues | -0.013 |
aster | -0.012 |
ours | -0.012 |
?'" | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +2.94e-03 |
Pos logit contributions | |
iche | +0.004 |
aster | +0.004 |
ues | +0.004 |
use | +0.004 |
bell | +0.004 |
Neg logit contributions | |
Bob | -0.004 |
Luis | -0.004 |
Andy | -0.003 |
strength | -0.003 |
iring | -0.003 |
Token | When |
Token ID | 2215 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
iche | +0.005 |
aster | +0.005 |
ues | +0.004 |
use | +0.004 |
bell | +0.004 |
Neg logit contributions | |
Bob | -0.004 |
Luis | -0.004 |
Andy | -0.004 |
strength | -0.004 |
iring | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -8.55e-04 |
Pos logit contributions | |
Luis | +0.054 |
Bob | +0.053 |
iring | +0.052 |
Andy | +0.052 |
strength | +0.051 |
Neg logit contributions | |
aster | -0.043 |
iche | -0.043 |
use | -0.041 |
bell | -0.041 |
ues | -0.040 |
Token | sun |
Token ID | 4252 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
Luis | +0.001 |
Kel | +0.001 |
Bob | +0.001 |
Zig | +0.001 |
iring | +0.001 |
Neg logit contributions | |
iche | -0.001 |
aster | -0.001 |
bell | -0.001 |
use | -0.001 |
cheesy | -0.001 |
Token | started |
Token ID | 2067 |
Feature activation | -6.11e-02 |
Pos logit contributions | |
Luis | +0.067 |
strength | +0.066 |
hind | +0.065 |
Andy | +0.065 |
Kel | +0.063 |
Neg logit contributions | |
bell | -0.030 |
iche | -0.023 |
aster | -0.022 |
added | -0.022 |
smelled | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
Luis | +0.096 |
Calvin | +0.091 |
strength | +0.089 |
Kel | +0.086 |
Flash | +0.085 |
Neg logit contributions | |
bell | -0.088 |
iche | -0.078 |
use | -0.074 |
aster | -0.071 |
cheesy | -0.071 |
Token | set |
Token ID | 900 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
Bob | +0.040 |
Andy | +0.037 |
Luis | +0.037 |
branches | +0.035 |
strength | +0.034 |
Neg logit contributions | |
ues | -0.052 |
iche | -0.050 |
use | -0.050 |
bell | -0.049 |
wasteful | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
Luis | +0.046 |
strength | +0.042 |
iring | +0.042 |
Bob | +0.041 |
Andy | +0.041 |
Neg logit contributions | |
bell | -0.033 |
use | -0.032 |
aster | -0.031 |
iche | -0.031 |
ues | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -6.88e-03 |
Pos logit contributions | |
Luis | +0.017 |
iger | +0.016 |
ert | +0.016 |
axter | +0.016 |
ippy | +0.016 |
Neg logit contributions | |
aster | -0.012 |
cheesy | -0.011 |
iche | -0.011 |
Does | -0.010 |
arium | -0.010 |
Token | bear |
Token ID | 6842 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
Kel | +0.010 |
Luis | +0.010 |
Zig | +0.010 |
Bob | +0.010 |
ert | +0.009 |
Neg logit contributions | |
iche | -0.010 |
aster | -0.010 |
cheesy | -0.010 |
wasteful | -0.010 |
use | -0.010 |
Token | The |
Token ID | 464 |
Feature activation | +5.00e-03 |
Pos logit contributions | |
iche | +0.013 |
use | +0.013 |
ues | +0.013 |
bell | +0.013 |
aster | +0.012 |
Neg logit contributions | |
Bob | -0.008 |
Luis | -0.008 |
Andy | -0.008 |
iring | -0.007 |
strength | -0.007 |
Token | mummy |
Token ID | 38567 |
Feature activation | -1.40e-03 |
Pos logit contributions | |
use | +0.007 |
iche | +0.007 |
bell | +0.007 |
aster | +0.007 |
ues | +0.007 |
Neg logit contributions | |
Bob | -0.008 |
Luis | -0.007 |
Andy | -0.007 |
iring | -0.007 |
Zig | -0.007 |
Token | pig |
Token ID | 12967 |
Feature activation | -4.59e-02 |
Pos logit contributions | |
Luis | +0.002 |
Bob | +0.002 |
iring | +0.002 |
Andy | +0.002 |
Zig | +0.002 |
Neg logit contributions | |
bell | -0.002 |
iche | -0.002 |
use | -0.002 |
aster | -0.002 |
ues | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +4.86e-03 |
Pos logit contributions | |
Luis | +0.077 |
iring | +0.075 |
Bob | +0.073 |
Andy | +0.071 |
strength | +0.071 |
Neg logit contributions | |
bell | -0.057 |
use | -0.056 |
iche | -0.056 |
aster | -0.055 |
ues | -0.054 |
Token | daddy |
Token ID | 35822 |
Feature activation | -7.36e-03 |
Pos logit contributions | |
aster | +0.007 |
use | +0.006 |
notebooks | +0.006 |
iche | +0.006 |
slice | +0.006 |
Neg logit contributions | |
iring | -0.008 |
Luis | -0.007 |
Zig | -0.007 |
strength | -0.007 |
Flash | -0.007 |
Token | pig |
Token ID | 12967 |
Feature activation | -6.11e-02 |
Pos logit contributions | |
Bob | +0.013 |
Luis | +0.013 |
Andy | +0.012 |
iring | +0.012 |
strength | +0.012 |
Neg logit contributions | |
use | -0.009 |
iche | -0.009 |
bell | -0.009 |
aster | -0.009 |
ues | -0.009 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | +7.14e-03 |
Pos logit contributions | |
Luis | +0.112 |
iring | +0.111 |
Calvin | +0.104 |
Bob | +0.103 |
strength | +0.101 |
Neg logit contributions | |
use | -0.067 |
bell | -0.065 |
iche | -0.062 |
aster | -0.062 |
ues | -0.061 |
Token | their |
Token ID | 511 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
iche | +0.012 |
use | +0.011 |
ues | +0.011 |
bell | +0.011 |
aster | +0.011 |
Neg logit contributions | |
Bob | -0.010 |
Luis | -0.010 |
Andy | -0.009 |
strength | -0.009 |
iring | -0.009 |
Token | milk |
Token ID | 7545 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
Luis | +0.032 |
Bob | +0.031 |
Andy | +0.030 |
iring | +0.029 |
Zig | +0.029 |
Neg logit contributions | |
iche | -0.030 |
use | -0.030 |
aster | -0.029 |
bell | -0.029 |
ues | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | -9.52e-03 |
Pos logit contributions | |
Luis | +0.042 |
Bob | +0.041 |
Andy | +0.040 |
Zig | +0.039 |
Flash | +0.039 |
Neg logit contributions | |
iche | -0.032 |
use | -0.031 |
bell | -0.031 |
ues | -0.030 |
aster | -0.030 |
Token | were |
Token ID | 547 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
Luis | +0.017 |
iring | +0.016 |
Bob | +0.016 |
Andy | +0.016 |
strength | +0.015 |
Neg logit contributions | |
aster | -0.011 |
iche | -0.011 |
cheesy | -0.010 |
use | -0.010 |
bell | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +8.22e-04 |
Pos logit contributions | |
aster | +0.058 |
bell | +0.057 |
ues | +0.056 |
iche | +0.056 |
use | +0.053 |
Neg logit contributions | |
Luis | -0.057 |
Bob | -0.055 |
Andy | -0.055 |
Zig | -0.051 |
strength | -0.051 |
Token | The |
Token ID | 383 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
iche | +0.002 |
use | +0.002 |
ues | +0.002 |
bell | +0.002 |
aster | +0.002 |
Neg logit contributions | |
Bob | -0.001 |
Luis | -0.001 |
Andy | -0.001 |
strength | -0.001 |
iring | -0.001 |
Token | doctor |
Token ID | 6253 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
iche | +0.030 |
aster | +0.030 |
use | +0.030 |
bell | +0.030 |
ues | +0.029 |
Neg logit contributions | |
Bob | -0.033 |
Luis | -0.032 |
Andy | -0.031 |
iring | -0.030 |
strength | -0.029 |
Token | turns |
Token ID | 4962 |
Feature activation | -3.29e-03 |
Pos logit contributions | |
iche | +0.045 |
use | +0.043 |
ues | +0.042 |
aster | +0.041 |
bell | +0.041 |
Neg logit contributions | |
Bob | -0.059 |
Luis | -0.058 |
strength | -0.056 |
Andy | -0.055 |
Flash | -0.054 |
Token | on |
Token ID | 319 |
Feature activation | +9.55e-03 |
Pos logit contributions | |
Bob | +0.004 |
Luis | +0.004 |
Andy | +0.004 |
iring | +0.004 |
strength | +0.004 |
Neg logit contributions | |
iche | -0.005 |
use | -0.005 |
aster | -0.005 |
bell | -0.005 |
ues | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
aster | +0.016 |
bell | +0.015 |
iche | +0.015 |
use | +0.015 |
ues | +0.015 |
Neg logit contributions | |
Luis | -0.012 |
iring | -0.012 |
Andy | -0.012 |
Bob | -0.011 |
strength | -0.011 |
Token | machine |
Token ID | 4572 |
Feature activation | +3.23e-03 |
Pos logit contributions | |
bell | +0.047 |
aster | +0.047 |
iche | +0.047 |
use | +0.047 |
ues | +0.045 |
Neg logit contributions | |
Bob | -0.055 |
Luis | -0.054 |
Andy | -0.053 |
iring | -0.051 |
Zig | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +6.13e-03 |
Pos logit contributions | |
iche | +0.005 |
use | +0.005 |
ues | +0.005 |
aster | +0.005 |
bell | +0.005 |
Neg logit contributions | |
Bob | -0.004 |
Luis | -0.004 |
Andy | -0.004 |
strength | -0.004 |
branches | -0.004 |
Token | He |
Token ID | 679 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
use | +0.012 |
iche | +0.011 |
ues | +0.011 |
bell | +0.011 |
aster | +0.011 |
Neg logit contributions | |
Bob | -0.007 |
Luis | -0.007 |
Andy | -0.006 |
Flash | -0.006 |
strength | -0.006 |
Token | sees |
Token ID | 7224 |
Feature activation | +9.68e-03 |
Pos logit contributions | |
iche | +0.024 |
use | +0.023 |
ues | +0.023 |
aster | +0.022 |
bell | +0.022 |
Neg logit contributions | |
Bob | -0.031 |
Luis | -0.030 |
strength | -0.029 |
Andy | -0.029 |
branches | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
aster | +0.016 |
iche | +0.015 |
bell | +0.015 |
ues | +0.015 |
use | +0.015 |
Neg logit contributions | |
Luis | -0.013 |
Bob | -0.012 |
Andy | -0.012 |
iring | -0.012 |
strength | -0.012 |
Token | is |
Token ID | 318 |
Feature activation | +8.97e-03 |
Pos logit contributions | |
iche | +0.003 |
aster | +0.002 |
ues | +0.002 |
use | +0.002 |
bell | +0.002 |
Neg logit contributions | |
Bob | -0.003 |
Luis | -0.003 |
Andy | -0.003 |
strength | -0.003 |
branches | -0.003 |
Token | soft |
Token ID | 2705 |
Feature activation | -2.93e-03 |
Pos logit contributions | |
use | +0.014 |
iche | +0.014 |
ues | +0.014 |
bell | +0.014 |
aster | +0.014 |
Neg logit contributions | |
Bob | -0.013 |
Luis | -0.012 |
Andy | -0.012 |
strength | -0.012 |
branches | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
Bob | +0.003 |
Luis | +0.003 |
Andy | +0.003 |
branches | +0.003 |
strength | +0.003 |
Neg logit contributions | |
iche | -0.006 |
aster | -0.005 |
ues | -0.005 |
use | -0.005 |
bell | -0.005 |
Token | warm |
Token ID | 5814 |
Feature activation | -2.20e-03 |
Pos logit contributions | |
ues | +0.036 |
iche | +0.036 |
aster | +0.035 |
bell | +0.035 |
use | +0.034 |
Neg logit contributions | |
Bob | -0.022 |
strength | -0.020 |
branches | -0.020 |
Andy | -0.019 |
Luis | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +9.03e-03 |
Pos logit contributions | |
Bob | +0.003 |
Andy | +0.003 |
Luis | +0.003 |
branches | +0.003 |
strength | +0.003 |
Neg logit contributions | |
iche | -0.004 |
ues | -0.004 |
aster | -0.004 |
bell | -0.003 |
use | -0.003 |
Token | Maybe |
Token ID | 6674 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
use | +0.013 |
iche | +0.013 |
aster | +0.013 |
bell | +0.012 |
ues | +0.012 |
Neg logit contributions | |
Bob | -0.015 |
Luis | -0.014 |
Andy | -0.014 |
Flash | -0.013 |
Zig | -0.013 |
Token | our |
Token ID | 674 |
Feature activation | -6.76e-03 |
Pos logit contributions | |
use | +0.048 |
iche | +0.048 |
aster | +0.048 |
bell | +0.047 |
ues | +0.047 |
Neg logit contributions | |
Luis | -0.057 |
Bob | -0.057 |
Andy | -0.055 |
iring | -0.054 |
strength | -0.053 |
Token | blanket |
Token ID | 18447 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
Luis | +0.009 |
Bob | +0.009 |
Andy | +0.009 |
iring | +0.008 |
Zig | +0.008 |
Neg logit contributions | |
use | -0.011 |
iche | -0.011 |
bell | -0.011 |
ues | -0.011 |
aster | -0.011 |
Token | provides |
Token ID | 3769 |
Feature activation | -5.52e-03 |
Pos logit contributions | |
Bob | +0.017 |
strength | +0.016 |
branches | +0.016 |
Andy | +0.016 |
friends | +0.016 |
Neg logit contributions | |
iche | -0.016 |
aster | -0.015 |
ues | -0.015 |
use | -0.014 |
bell | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +9.75e-03 |
Pos logit contributions | |
Bob | +0.008 |
friends | +0.007 |
Andy | +0.007 |
Luis | +0.007 |
strength | +0.007 |
Neg logit contributions | |
bell | -0.009 |
iche | -0.009 |
use | -0.009 |
ues | -0.009 |
aster | -0.009 |
Token | home |
Token ID | 1363 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
use | +0.018 |
ues | +0.018 |
aster | +0.018 |
iche | +0.018 |
bell | +0.018 |
Neg logit contributions | |
Bob | -0.011 |
friends | -0.011 |
Luis | -0.010 |
branches | -0.010 |
Andy | -0.010 |
Token | is |
Token ID | 318 |
Feature activation | +1.31e-03 |
Pos logit contributions | |
iche | +0.009 |
ues | +0.009 |
aster | +0.009 |
use | +0.009 |
Acc | +0.008 |
Neg logit contributions | |
Bob | -0.016 |
Andy | -0.015 |
Luis | -0.015 |
strength | -0.015 |
friends | -0.015 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
ues | +0.001 |
iche | +0.001 |
bell | +0.001 |
use | +0.001 |
aster | +0.001 |
Neg logit contributions | |
Bob | -0.002 |
Andy | -0.002 |
Luis | -0.002 |
strength | -0.002 |
friends | -0.002 |
Token | |
Token ID | 220 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
ues | +0.050 |
iche | +0.048 |
use | +0.048 |
ours | +0.045 |
prise | +0.045 |
Neg logit contributions | |
Bob | -0.042 |
Andy | -0.038 |
Luis | -0.035 |
friends | -0.034 |
Kel | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
iche | +0.017 |
ues | +0.016 |
aster | +0.016 |
use | +0.016 |
bell | +0.016 |
Neg logit contributions | |
Bob | -0.014 |
Luis | -0.014 |
Andy | -0.014 |
strength | -0.013 |
branches | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
iche | +0.042 |
ues | +0.042 |
use | +0.042 |
aster | +0.041 |
wasteful | +0.041 |
Neg logit contributions | |
Bob | -0.019 |
Andy | -0.017 |
Luis | -0.017 |
friends | -0.016 |
Zig | -0.015 |
Token | L |
Token ID | 43 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
iche | +0.035 |
ours | +0.035 |
ues | +0.034 |
use | +0.033 |
aster | +0.033 |
Neg logit contributions | |
Bob | -0.033 |
Andy | -0.033 |
Andy | -0.033 |
friends | -0.033 |
Luis | -0.033 |
Token | ily |
Token ID | 813 |
Feature activation | -2.54e-03 |
Pos logit contributions | |
use | +0.056 |
iche | +0.054 |
cheesy | +0.054 |
bell | +0.053 |
aster | +0.052 |
Neg logit contributions | |
Bob | -0.046 |
iring | -0.046 |
himself | -0.043 |
friends | -0.043 |
Luis | -0.042 |
Token | 's |
Token ID | 338 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
Bob | +0.004 |
Luis | +0.004 |
Andy | +0.004 |
iring | +0.004 |
strength | +0.004 |
Neg logit contributions | |
bell | -0.003 |
use | -0.003 |
iche | -0.003 |
ues | -0.003 |
aster | -0.003 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.38e-03 |
Pos logit contributions | |
Luis | +0.020 |
Bob | +0.020 |
Andy | +0.019 |
iring | +0.018 |
Flash | +0.018 |
Neg logit contributions | |
bell | -0.027 |
iche | -0.026 |
ues | -0.026 |
aster | -0.026 |
use | -0.026 |
Token | replied |
Token ID | 8712 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
iche | +0.006 |
use | +0.006 |
ues | +0.006 |
aster | +0.006 |
bell | +0.006 |
Neg logit contributions | |
Bob | -0.007 |
Luis | -0.007 |
Andy | -0.007 |
strength | -0.007 |
iring | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +3.32e-03 |
Pos logit contributions | |
Bob | +0.015 |
Andy | +0.013 |
Luis | +0.013 |
friends | +0.012 |
iring | +0.012 |
Neg logit contributions | |
iche | -0.026 |
use | -0.026 |
aster | -0.026 |
ues | -0.025 |
bell | -0.025 |
Token | dad |
Token ID | 9955 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
use | +0.035 |
aster | +0.035 |
iche | +0.034 |
bell | +0.034 |
ues | +0.034 |
Neg logit contributions | |
Luis | -0.036 |
Bob | -0.036 |
iring | -0.035 |
Andy | -0.035 |
Zig | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +4.02e-03 |
Pos logit contributions | |
iche | +0.028 |
use | +0.028 |
bell | +0.028 |
ues | +0.028 |
aster | +0.028 |
Neg logit contributions | |
Bob | -0.030 |
Luis | -0.030 |
Andy | -0.029 |
iring | -0.028 |
strength | -0.028 |
Token | They |
Token ID | 1119 |
Feature activation | +3.90e-03 |
Pos logit contributions | |
iche | +0.007 |
use | +0.007 |
ues | +0.007 |
bell | +0.007 |
aster | +0.007 |
Neg logit contributions | |
Bob | -0.005 |
Luis | -0.005 |
Andy | -0.005 |
Zig | -0.005 |
Flash | -0.005 |
Token | always |
Token ID | 1464 |
Feature activation | +8.78e-03 |
Pos logit contributions | |
iche | +0.006 |
ues | +0.006 |
aster | +0.006 |
use | +0.006 |
cheesy | +0.005 |
Neg logit contributions | |
Bob | -0.006 |
Luis | -0.006 |
Andy | -0.005 |
friends | -0.005 |
strength | -0.005 |
Token | cl |
Token ID | 537 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
iche | +0.013 |
aster | +0.013 |
ues | +0.013 |
bell | +0.012 |
ackers | +0.012 |
Neg logit contributions | |
Bob | -0.014 |
strength | -0.013 |
Luis | -0.013 |
friends | -0.013 |
Andy | -0.013 |
Token | apped |
Token ID | 6320 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
use | +0.039 |
aster | +0.038 |
bell | +0.037 |
iche | +0.036 |
wasteful | +0.035 |
Neg logit contributions | |
Bob | -0.046 |
Luis | -0.046 |
iring | -0.046 |
friends | -0.045 |
Andy | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | +4.21e-03 |
Pos logit contributions | |
ues | +0.055 |
iche | +0.055 |
bell | +0.054 |
use | +0.054 |
aster | +0.053 |
Neg logit contributions | |
Bob | -0.057 |
Luis | -0.057 |
Andy | -0.055 |
iring | -0.052 |
strength | -0.052 |
Token | smiled |
Token ID | 13541 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
iche | +0.005 |
use | +0.005 |
bell | +0.005 |
ues | +0.005 |
aster | +0.005 |
Neg logit contributions | |
Bob | -0.007 |
Luis | -0.007 |
iring | -0.007 |
Andy | -0.007 |
strength | -0.007 |
Token | when |
Token ID | 618 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
ues | +0.026 |
bell | +0.026 |
iche | +0.025 |
use | +0.024 |
aster | +0.024 |
Neg logit contributions | |
Luis | -0.033 |
Bob | -0.032 |
Andy | -0.032 |
strength | -0.031 |
branches | -0.030 |
Token | he |
Token ID | 339 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
Luis | +0.028 |
iring | +0.028 |
strength | +0.027 |
Bob | +0.027 |
branches | +0.027 |
Neg logit contributions | |
aster | -0.017 |
bell | -0.016 |
iche | -0.016 |
use | -0.015 |
ues | -0.015 |
Token | played |
Token ID | 2826 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
iche | +0.019 |
ues | +0.019 |
aster | +0.019 |
use | +0.019 |
cheesy | +0.018 |
Neg logit contributions | |
Bob | -0.019 |
Luis | -0.018 |
friends | -0.017 |
strength | -0.017 |
Andy | -0.017 |
Token | Do |
Token ID | 5211 |
Feature activation | -5.42e-03 |
Pos logit contributions | |
ues | +0.017 |
bell | +0.016 |
iche | +0.016 |
aster | +0.015 |
cheesy | +0.015 |
Neg logit contributions | |
Bob | -0.021 |
Luis | -0.021 |
Andy | -0.020 |
fl | -0.020 |
Andy | -0.020 |
Token | you |
Token ID | 345 |
Feature activation | -6.85e-04 |
Pos logit contributions | |
Bob | +0.008 |
Luis | +0.008 |
Andy | +0.007 |
iring | +0.007 |
strength | +0.007 |
Neg logit contributions | |
iche | -0.008 |
use | -0.008 |
aster | -0.008 |
ues | -0.008 |
bell | -0.008 |
Token | want |
Token ID | 765 |
Feature activation | +2.30e-03 |
Pos logit contributions | |
Bob | +0.001 |
strength | +0.001 |
friends | +0.001 |
Andy | +0.001 |
himself | +0.001 |
Neg logit contributions | |
ues | -0.001 |
ours | -0.001 |
bell | -0.001 |
batch | -0.001 |
iche | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -9.87e-03 |
Pos logit contributions | |
use | +0.004 |
aster | +0.004 |
iche | +0.004 |
bell | +0.004 |
ues | +0.004 |
Neg logit contributions | |
Luis | -0.003 |
iring | -0.003 |
Bob | -0.003 |
Andy | -0.003 |
strength | -0.003 |
Token | play |
Token ID | 711 |
Feature activation | -1.01e-04 |
Pos logit contributions | |
Luis | +0.018 |
Bob | +0.018 |
iring | +0.018 |
Andy | +0.017 |
strength | +0.017 |
Neg logit contributions | |
use | -0.011 |
aster | -0.011 |
bell | -0.011 |
iche | -0.011 |
ues | -0.010 |
Token | hide |
Token ID | 7808 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
Bob | +0.000 |
Luis | +0.000 |
Andy | +0.000 |
friends | +0.000 |
Zig | +0.000 |
Neg logit contributions | |
bell | -0.000 |
iche | -0.000 |
use | -0.000 |
ues | -0.000 |
aster | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | +8.36e-04 |
Pos logit contributions | |
iche | +0.069 |
aster | +0.067 |
bell | +0.067 |
use | +0.066 |
ues | +0.064 |
Neg logit contributions | |
Bob | -0.058 |
Luis | -0.054 |
Andy | -0.053 |
iring | -0.052 |
friends | -0.052 |
Token | seek |
Token ID | 5380 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
use | +0.001 |
iche | +0.001 |
aster | +0.001 |
bell | +0.001 |
cheesy | +0.001 |
Neg logit contributions | |
Luis | -0.001 |
Bob | -0.001 |
iring | -0.001 |
Andy | -0.001 |
strength | -0.001 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.17e-03 |
Pos logit contributions | |
iche | +0.021 |
aster | +0.020 |
use | +0.019 |
bell | +0.019 |
ues | +0.019 |
Neg logit contributions | |
Bob | -0.037 |
Luis | -0.036 |
Andy | -0.035 |
iring | -0.034 |
friends | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | -3.39e-03 |
Pos logit contributions | |
iche | +0.004 |
use | +0.004 |
aster | +0.003 |
Does | +0.003 |
bell | +0.003 |
Neg logit contributions | |
Luis | -0.003 |
iring | -0.003 |
strength | -0.003 |
Bob | -0.003 |
Andy | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -6.17e-04 |
Pos logit contributions | |
Luis | +0.005 |
strength | +0.005 |
Bob | +0.005 |
Andy | +0.005 |
branches | +0.005 |
Neg logit contributions | |
use | -0.005 |
iche | -0.005 |
aster | -0.005 |
bell | -0.004 |
ues | -0.004 |
Token | far |
Token ID | 1290 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
iche | +0.012 |
use | +0.012 |
ues | +0.012 |
bell | +0.012 |
aster | +0.012 |
Neg logit contributions | |
Bob | -0.009 |
Luis | -0.008 |
Andy | -0.008 |
strength | -0.008 |
iring | -0.008 |
Token | away |
Token ID | 1497 |
Feature activation | +8.22e-03 |
Pos logit contributions | |
use | +0.038 |
iche | +0.038 |
ues | +0.037 |
aster | +0.037 |
bell | +0.037 |
Neg logit contributions | |
Bob | -0.043 |
Luis | -0.042 |
Andy | -0.041 |
strength | -0.039 |
iring | -0.039 |
Token | ." |
Token ID | 526 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
use | +0.009 |
ues | +0.009 |
bell | +0.009 |
aster | +0.009 |
iche | +0.009 |
Neg logit contributions | |
Luis | -0.015 |
Andy | -0.015 |
Bob | -0.014 |
Andy | -0.014 |
Kel | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +5.93e-03 |
Pos logit contributions | |
iche | +0.022 |
ues | +0.022 |
use | +0.021 |
aster | +0.021 |
bell | +0.021 |
Neg logit contributions | |
Bob | -0.012 |
Andy | -0.011 |
Luis | -0.011 |
friends | -0.010 |
strength | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
iche | +0.012 |
ues | +0.012 |
use | +0.012 |
bell | +0.012 |
aster | +0.011 |
Neg logit contributions | |
Bob | -0.006 |
Andy | -0.006 |
Luis | -0.006 |
iring | -0.005 |
Zig | -0.005 |
Token | L |
Token ID | 43 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
iche | +0.016 |
ues | +0.015 |
use | +0.015 |
bell | +0.014 |
rant | +0.014 |
Neg logit contributions | |
Bob | -0.018 |
Andy | -0.018 |
Luis | -0.018 |
Andy | -0.017 |
iring | -0.017 |
Token | ily |
Token ID | 813 |
Feature activation | -7.13e-03 |
Pos logit contributions | |
use | +0.043 |
iche | +0.042 |
bell | +0.041 |
ues | +0.039 |
aster | +0.039 |
Neg logit contributions | |
Bob | -0.046 |
iring | -0.044 |
Luis | -0.043 |
Andy | -0.043 |
strength | -0.042 |
Token | nodded |
Token ID | 14464 |
Feature activation | +6.17e-03 |
Pos logit contributions | |
Luis | +0.013 |
Bob | +0.012 |
Andy | +0.012 |
iring | +0.012 |
Zig | +0.012 |
Neg logit contributions | |
bell | -0.008 |
iche | -0.008 |
use | -0.008 |
ues | -0.008 |
aster | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -7.51e-03 |
Pos logit contributions | |
iche | +0.015 |
ues | +0.014 |
aster | +0.014 |
ours | +0.014 |
gallery | +0.014 |
Neg logit contributions | |
Bob | -0.005 |
himself | -0.005 |
friends | -0.004 |
birds | -0.004 |
children | -0.004 |
Token | wiped |
Token ID | 21122 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
Luis | +0.013 |
Bob | +0.013 |
Andy | +0.013 |
iring | +0.013 |
Flash | +0.012 |
Neg logit contributions | |
aster | -0.009 |
use | -0.009 |
ues | -0.008 |
iche | -0.008 |
bell | -0.008 |
Token | her |
Token ID | 607 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
iche | +0.015 |
use | +0.015 |
aster | +0.015 |
bell | +0.015 |
ues | +0.015 |
Neg logit contributions | |
Bob | -0.016 |
Luis | -0.016 |
Andy | -0.015 |
iring | -0.015 |
strength | -0.015 |
Token | Can |
Token ID | 1680 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
Bob | +0.001 |
Luis | +0.000 |
Andy | +0.000 |
Flash | +0.000 |
Zig | +0.000 |
Neg logit contributions | |
ues | -0.001 |
iche | -0.001 |
use | -0.000 |
cheesy | -0.000 |
bell | -0.000 |
Token | I |
Token ID | 314 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
iche | +0.025 |
ues | +0.024 |
use | +0.024 |
aster | +0.023 |
bell | +0.023 |
Neg logit contributions | |
Bob | -0.019 |
Andy | -0.018 |
Luis | -0.018 |
Zig | -0.016 |
strength | -0.016 |
Token | come |
Token ID | 1282 |
Feature activation | -9.86e-03 |
Pos logit contributions | |
iche | +0.041 |
ues | +0.040 |
use | +0.039 |
aster | +0.039 |
bell | +0.038 |
Neg logit contributions | |
Bob | -0.045 |
Luis | -0.044 |
Andy | -0.043 |
strength | -0.041 |
iring | -0.040 |
Token | in |
Token ID | 287 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
Bob | +0.011 |
Andy | +0.011 |
Luis | +0.010 |
friends | +0.010 |
iring | +0.009 |
Neg logit contributions | |
iche | -0.019 |
ues | -0.019 |
wasteful | -0.018 |
aster | -0.018 |
cheesy | -0.018 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
iche | +0.033 |
ues | +0.031 |
use | +0.030 |
bell | +0.030 |
aster | +0.029 |
Neg logit contributions | |
Bob | -0.041 |
Luis | -0.039 |
Andy | -0.038 |
friends | -0.036 |
iring | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
iche | +0.022 |
use | +0.022 |
ues | +0.022 |
bell | +0.022 |
aster | +0.022 |
Neg logit contributions | |
Bob | -0.019 |
Luis | -0.019 |
Andy | -0.018 |
strength | -0.018 |
iring | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
iche | +0.023 |
use | +0.023 |
ues | +0.023 |
bell | +0.022 |
aster | +0.022 |
Neg logit contributions | |
Bob | -0.013 |
Luis | -0.012 |
Andy | -0.012 |
Zig | -0.011 |
Flash | -0.011 |
Token | L |
Token ID | 43 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
iche | +0.014 |
ues | +0.014 |
use | +0.014 |
bell | +0.013 |
aster | +0.013 |
Neg logit contributions | |
Bob | -0.027 |
Luis | -0.026 |
Andy | -0.026 |
iring | -0.025 |
strength | -0.025 |
Token | ily |
Token ID | 813 |
Feature activation | +5.05e-03 |
Pos logit contributions | |
use | +0.052 |
iche | +0.051 |
cheesy | +0.050 |
bell | +0.050 |
Amen | +0.048 |
Neg logit contributions | |
himself | -0.038 |
iring | -0.037 |
Bob | -0.037 |
friends | -0.036 |
children | -0.034 |
Token | was |
Token ID | 373 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
iche | +0.006 |
use | +0.006 |
bell | +0.006 |
ues | +0.006 |
aster | +0.006 |
Neg logit contributions | |
Bob | -0.009 |
Luis | -0.008 |
Andy | -0.008 |
iring | -0.008 |
strength | -0.008 |
Token | scared |
Token ID | 12008 |
Feature activation | -5.35e-03 |
Pos logit contributions | |
iche | +0.012 |
bell | +0.012 |
ues | +0.012 |
aster | +0.012 |
use | +0.011 |
Neg logit contributions | |
Luis | -0.021 |
Bob | -0.021 |
Andy | -0.021 |
strength | -0.020 |
iring | -0.020 |
Token | need |
Token ID | 761 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
iche | +0.017 |
use | +0.017 |
ues | +0.017 |
aster | +0.017 |
bell | +0.016 |
Neg logit contributions | |
Bob | -0.030 |
Luis | -0.029 |
Andy | -0.028 |
strength | -0.028 |
iring | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
use | +0.023 |
aster | +0.023 |
iche | +0.022 |
bell | +0.022 |
ues | +0.022 |
Neg logit contributions | |
Luis | -0.018 |
Bob | -0.018 |
iring | -0.017 |
Andy | -0.017 |
Zig | -0.017 |
Token | put |
Token ID | 1234 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
iche | +0.017 |
use | +0.016 |
ues | +0.016 |
bell | +0.016 |
aster | +0.016 |
Neg logit contributions | |
Bob | -0.018 |
Luis | -0.018 |
Andy | -0.017 |
strength | -0.017 |
branches | -0.016 |
Token | your |
Token ID | 534 |
Feature activation | +2.89e-03 |
Pos logit contributions | |
iche | +0.036 |
use | +0.035 |
bell | +0.035 |
ues | +0.035 |
aster | +0.035 |
Neg logit contributions | |
Bob | -0.029 |
Luis | -0.028 |
Andy | -0.027 |
strength | -0.026 |
branches | -0.025 |
Token | toys |
Token ID | 14958 |
Feature activation | +2.00e-04 |
Pos logit contributions | |
use | +0.006 |
bell | +0.006 |
iche | +0.005 |
notebooks | +0.005 |
folder | +0.005 |
Neg logit contributions | |
Bob | -0.003 |
Luis | -0.003 |
Andy | -0.003 |
iring | -0.003 |
Flash | -0.003 |
Token | in |
Token ID | 287 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
iche | +0.000 |
use | +0.000 |
ues | +0.000 |
bell | +0.000 |
aster | +0.000 |
Neg logit contributions | |
Bob | -0.000 |
Luis | -0.000 |
Andy | -0.000 |
strength | -0.000 |
iring | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
iche | +0.021 |
use | +0.021 |
ues | +0.020 |
bell | +0.020 |
aster | +0.020 |
Neg logit contributions | |
Bob | -0.013 |
Luis | -0.013 |
Andy | -0.012 |
strength | -0.012 |
iring | -0.012 |
Token | box |
Token ID | 3091 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
ues | +0.023 |
iche | +0.023 |
use | +0.023 |
bell | +0.023 |
aster | +0.022 |
Neg logit contributions | |
Bob | -0.023 |
Luis | -0.022 |
strength | -0.021 |
branches | -0.021 |
Andy | -0.021 |
Token | ." |
Token ID | 526 |
Feature activation | +6.62e-03 |
Pos logit contributions | |
iche | +0.025 |
use | +0.025 |
aster | +0.025 |
ues | +0.025 |
bell | +0.024 |
Neg logit contributions | |
Bob | -0.021 |
Luis | -0.021 |
Andy | -0.020 |
strength | -0.019 |
iring | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -1.48e-03 |
Pos logit contributions | |
iche | +0.011 |
use | +0.011 |
aster | +0.011 |
ues | +0.011 |
bell | +0.011 |
Neg logit contributions | |
Bob | -0.009 |
Luis | -0.009 |
Andy | -0.008 |
strength | -0.008 |
iring | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -8.16e-04 |
Pos logit contributions | |
Bob | +0.002 |
Luis | +0.002 |
Andy | +0.002 |
strength | +0.002 |
iring | +0.002 |
Neg logit contributions | |
iche | -0.002 |
use | -0.002 |
ues | -0.002 |
aster | -0.002 |
bell | -0.002 |
Token | she |
Token ID | 673 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
Luis | +0.003 |
Bob | +0.003 |
strength | +0.003 |
iring | +0.003 |
Andy | +0.003 |
Neg logit contributions | |
aster | -0.003 |
bell | -0.003 |
iche | -0.003 |
ues | -0.003 |
use | -0.003 |
Token | sque |
Token ID | 35776 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
iche | +0.031 |
ues | +0.030 |
aster | +0.030 |
use | +0.029 |
bell | +0.028 |
Neg logit contributions | |
Bob | -0.036 |
Luis | -0.035 |
Andy | -0.034 |
strength | -0.033 |
Zig | -0.032 |
Token | aked |
Token ID | 4335 |
Feature activation | -2.99e-03 |
Pos logit contributions | |
bell | +0.082 |
cheesy | +0.079 |
aster | +0.077 |
use | +0.076 |
Does | +0.076 |
Neg logit contributions | |
friends | -0.029 |
strength | -0.023 |
iring | -0.023 |
ped | -0.022 |
courage | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -7.27e-04 |
Pos logit contributions | |
Luis | +0.005 |
iring | +0.004 |
Bob | +0.004 |
Andy | +0.004 |
strength | +0.004 |
Neg logit contributions | |
bell | -0.004 |
aster | -0.004 |
ues | -0.004 |
use | -0.004 |
iche | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
Luis | +0.001 |
iring | +0.001 |
Bob | +0.001 |
Andy | +0.001 |
strength | +0.001 |
Neg logit contributions | |
bell | -0.001 |
iche | -0.001 |
use | -0.001 |
aster | -0.001 |
ues | -0.001 |
Token | Welcome |
Token ID | 14618 |
Feature activation | -1.62e-03 |
Pos logit contributions | |
iche | +0.014 |
use | +0.014 |
ues | +0.014 |
bell | +0.014 |
aster | +0.014 |
Neg logit contributions | |
Bob | -0.019 |
Luis | -0.018 |
Andy | -0.018 |
strength | -0.017 |
iring | -0.017 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.30e-03 |
Pos logit contributions | |
Luis | +0.002 |
strength | +0.002 |
iring | +0.002 |
Bob | +0.002 |
branches | +0.002 |
Neg logit contributions | |
use | -0.003 |
bell | -0.003 |
ues | -0.003 |
iche | -0.003 |
aster | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -3.89e-03 |
Pos logit contributions | |
aster | +0.002 |
bell | +0.002 |
iche | +0.002 |
use | +0.002 |
Does | +0.002 |
Neg logit contributions | |
iring | -0.002 |
Luis | -0.002 |
ert | -0.002 |
strength | -0.002 |
Andy | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +1.84e-03 |
Pos logit contributions | |
strength | +0.007 |
Luis | +0.006 |
Bob | +0.006 |
iring | +0.006 |
Andy | +0.006 |
Neg logit contributions | |
aster | -0.005 |
bell | -0.005 |
iche | -0.005 |
use | -0.005 |
ues | -0.005 |
Token | The |
Token ID | 464 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
aster | +0.002 |
bell | +0.002 |
use | +0.002 |
iche | +0.002 |
ues | +0.002 |
Neg logit contributions | |
Bob | -0.003 |
Luis | -0.003 |
Andy | -0.003 |
strength | -0.003 |
iring | -0.003 |
Token | house |
Token ID | 2156 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
bell | +0.028 |
iche | +0.028 |
use | +0.027 |
aster | +0.027 |
ues | +0.026 |
Neg logit contributions | |
Bob | -0.015 |
Luis | -0.014 |
Andy | -0.013 |
Zig | -0.013 |
strength | -0.012 |
Token | soup |
Token ID | 17141 |
Feature activation | +8.78e-03 |
Pos logit contributions | |
Luis | +0.015 |
Bob | +0.015 |
Andy | +0.014 |
iring | +0.014 |
Zig | +0.013 |
Neg logit contributions | |
iche | -0.015 |
aster | -0.015 |
ues | -0.014 |
bell | -0.014 |
use | -0.014 |
Token | in |
Token ID | 287 |
Feature activation | +6.23e-03 |
Pos logit contributions | |
use | +0.014 |
bell | +0.014 |
iche | +0.014 |
aster | +0.014 |
ues | +0.014 |
Neg logit contributions | |
Bob | -0.012 |
Luis | -0.011 |
Andy | -0.011 |
iring | -0.011 |
strength | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
iche | +0.012 |
use | +0.012 |
ues | +0.012 |
bell | +0.012 |
aster | +0.012 |
Neg logit contributions | |
Bob | -0.006 |
Luis | -0.006 |
Andy | -0.006 |
strength | -0.006 |
iring | -0.006 |
Token | kitchen |
Token ID | 9592 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
ues | +0.016 |
bell | +0.015 |
use | +0.014 |
iche | +0.014 |
aster | +0.013 |
Neg logit contributions | |
Bob | -0.019 |
branches | -0.019 |
strength | -0.018 |
Andy | -0.018 |
friends | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
use | +0.042 |
iche | +0.041 |
bell | +0.040 |
ues | +0.040 |
aster | +0.040 |
Neg logit contributions | |
Bob | -0.036 |
Luis | -0.033 |
Andy | -0.033 |
branches | -0.032 |
strength | -0.032 |
Token | Lily |
Token ID | 20037 |
Feature activation | +8.53e-03 |
Pos logit contributions | |
use | +0.015 |
ues | +0.015 |
iche | +0.015 |
bell | +0.015 |
aster | +0.014 |
Neg logit contributions | |
Bob | -0.018 |
Andy | -0.017 |
Luis | -0.016 |
strength | -0.016 |
branches | -0.016 |
Token | could |
Token ID | 714 |
Feature activation | -2.52e-04 |
Pos logit contributions | |
iche | +0.013 |
use | +0.012 |
ues | +0.012 |
bell | +0.012 |
aster | +0.012 |
Neg logit contributions | |
Bob | -0.013 |
Luis | -0.013 |
Andy | -0.012 |
strength | -0.012 |
branches | -0.012 |
Token | smell |
Token ID | 8508 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
Bob | +0.000 |
Andy | +0.000 |
Luis | +0.000 |
strength | +0.000 |
himself | +0.000 |
Neg logit contributions | |
use | -0.000 |
ues | -0.000 |
iche | -0.000 |
bell | -0.000 |
wasteful | -0.000 |
Token | it |
Token ID | 340 |
Feature activation | +3.37e-03 |
Pos logit contributions | |
use | +0.022 |
bell | +0.022 |
ues | +0.021 |
iche | +0.021 |
aster | +0.020 |
Neg logit contributions | |
Bob | -0.018 |
Andy | -0.016 |
Luis | -0.016 |
strength | -0.016 |
friends | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +8.02e-03 |
Pos logit contributions | |
use | +0.006 |
ues | +0.006 |
aster | +0.006 |
iche | +0.006 |
bell | +0.006 |
Neg logit contributions | |
Bob | -0.005 |
Andy | -0.004 |
Luis | -0.004 |
strength | -0.004 |
iring | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
iche | +0.012 |
use | +0.012 |
ues | +0.011 |
bell | +0.011 |
aster | +0.011 |
Neg logit contributions | |
Bob | -0.012 |
Luis | -0.012 |
Andy | -0.012 |
strength | -0.011 |
iring | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
Luis | +0.021 |
strength | +0.021 |
Calvin | +0.020 |
iring | +0.020 |
branches | +0.020 |
Neg logit contributions | |
ues | -0.012 |
bell | -0.011 |
aster | -0.011 |
use | -0.010 |
Does | -0.010 |
Token | hear |
Token ID | 3285 |
Feature activation | +3.99e-03 |
Pos logit contributions | |
Bob | +0.021 |
Luis | +0.020 |
Andy | +0.020 |
strength | +0.019 |
Zig | +0.019 |
Neg logit contributions | |
iche | -0.014 |
use | -0.014 |
ues | -0.013 |
aster | -0.013 |
bell | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +2.90e-03 |
Pos logit contributions | |
iche | +0.006 |
use | +0.006 |
ues | +0.006 |
bell | +0.006 |
aster | +0.006 |
Neg logit contributions | |
Bob | -0.005 |
Luis | -0.005 |
Andy | -0.005 |
iring | -0.005 |
strength | -0.005 |
Token | music |
Token ID | 2647 |
Feature activation | -3.72e-03 |
Pos logit contributions | |
bell | +0.004 |
iche | +0.004 |
Amen | +0.004 |
aster | +0.004 |
gallery | +0.004 |
Neg logit contributions | |
Bob | -0.005 |
Andy | -0.004 |
Zig | -0.004 |
Luis | -0.004 |
iring | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -2.52e-03 |
Pos logit contributions | |
Bob | +0.005 |
Luis | +0.005 |
Andy | +0.005 |
iring | +0.005 |
strength | +0.005 |
Neg logit contributions | |
iche | -0.006 |
bell | -0.005 |
use | -0.005 |
ues | -0.005 |
aster | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -3.66e-03 |
Pos logit contributions | |
Bob | +0.004 |
Luis | +0.004 |
Andy | +0.004 |
iring | +0.003 |
strength | +0.003 |
Neg logit contributions | |
bell | -0.004 |
iche | -0.004 |
aster | -0.004 |
ues | -0.004 |
use | -0.003 |
Token | she |
Token ID | 673 |
Feature activation | -7.01e-03 |
Pos logit contributions | |
Luis | +0.006 |
Bob | +0.006 |
iring | +0.006 |
Andy | +0.006 |
strength | +0.006 |
Neg logit contributions | |
bell | -0.005 |
aster | -0.004 |
ues | -0.004 |
use | -0.004 |
iche | -0.004 |
Token | started |
Token ID | 2067 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
Bob | +0.012 |
Luis | +0.012 |
Andy | +0.012 |
iring | +0.012 |
strength | +0.011 |
Neg logit contributions | |
bell | -0.009 |
ues | -0.008 |
use | -0.008 |
iche | -0.008 |
aster | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
Bob | +0.035 |
iring | +0.035 |
Luis | +0.035 |
Andy | +0.034 |
Flash | +0.032 |
Neg logit contributions | |
bell | -0.037 |
aster | -0.036 |
ues | -0.036 |
iche | -0.036 |
use | -0.034 |
Token | dance |
Token ID | 9280 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
iring | +0.044 |
Bob | +0.043 |
Luis | +0.041 |
Andy | +0.040 |
strength | +0.039 |
Neg logit contributions | |
bell | -0.026 |
use | -0.025 |
aster | -0.025 |
iche | -0.025 |
ues | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -4.54e-03 |
Pos logit contributions | |
iche | +0.020 |
use | +0.020 |
ues | +0.020 |
bell | +0.019 |
aster | +0.019 |
Neg logit contributions | |
Bob | -0.019 |
Luis | -0.019 |
Andy | -0.018 |
strength | -0.017 |
iring | -0.017 |
Token | made |
Token ID | 925 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
Bob | +0.029 |
Luis | +0.028 |
iring | +0.028 |
Andy | +0.027 |
Roll | +0.026 |
Neg logit contributions | |
bell | -0.023 |
iche | -0.021 |
use | -0.020 |
Does | -0.019 |
aster | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
fl | +0.051 |
iring | +0.047 |
unn | +0.047 |
Luis | +0.047 |
axter | +0.046 |
Neg logit contributions | |
aster | -0.031 |
ores | -0.023 |
iche | -0.023 |
bell | -0.021 |
cheesy | -0.020 |
Token | loud |
Token ID | 7812 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
Bob | +0.023 |
Luis | +0.023 |
Andy | +0.022 |
strength | +0.021 |
iring | +0.021 |
Neg logit contributions | |
iche | -0.023 |
use | -0.023 |
ues | -0.023 |
bell | -0.023 |
aster | -0.022 |
Token | noise |
Token ID | 7838 |
Feature activation | -8.46e-03 |
Pos logit contributions | |
Bob | +0.017 |
Luis | +0.016 |
Andy | +0.016 |
strength | +0.015 |
iring | +0.015 |
Neg logit contributions | |
iche | -0.030 |
use | -0.029 |
ues | -0.029 |
bell | -0.029 |
aster | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -3.61e-03 |
Pos logit contributions | |
Luis | +0.013 |
Bob | +0.013 |
iring | +0.013 |
strength | +0.012 |
Andy | +0.012 |
Neg logit contributions | |
bell | -0.012 |
aster | -0.011 |
ues | -0.011 |
use | -0.011 |
iche | -0.011 |
Token | Ted |
Token ID | 11396 |
Feature activation | -7.96e-03 |
Pos logit contributions | |
Luis | +0.005 |
iring | +0.005 |
Bob | +0.005 |
Andy | +0.005 |
Calvin | +0.005 |
Neg logit contributions | |
aster | -0.005 |
bell | -0.005 |
iche | -0.005 |
wasteful | -0.005 |
use | -0.005 |
Token | felt |
Token ID | 2936 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
iring | +0.014 |
Luis | +0.014 |
Bob | +0.013 |
Andy | +0.013 |
Kel | +0.013 |
Neg logit contributions | |
bell | -0.009 |
use | -0.009 |
iche | -0.008 |
ues | -0.008 |
aster | -0.008 |
Token | embarrassed |
Token ID | 21100 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
iche | +0.017 |
aster | +0.017 |
bell | +0.016 |
use | +0.016 |
wasteful | +0.016 |
Neg logit contributions | |
Luis | -0.022 |
Bob | -0.022 |
Andy | -0.021 |
iring | -0.021 |
ert | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e-03 |
Pos logit contributions | |
Luis | +0.018 |
Bob | +0.017 |
Andy | +0.017 |
strength | +0.017 |
branches | +0.016 |
Neg logit contributions | |
ues | -0.012 |
bell | -0.012 |
iche | -0.012 |
aster | -0.012 |
use | -0.012 |
Token | He |
Token ID | 679 |
Feature activation | -5.15e-03 |
Pos logit contributions | |
Does | +0.001 |
iche | +0.001 |
bell | +0.001 |
aster | +0.001 |
Amen | +0.001 |
Neg logit contributions | |
iring | -0.002 |
plunge | -0.002 |
Luis | -0.002 |
strength | -0.002 |
babies | -0.002 |
Token | covered |
Token ID | 5017 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
Bob | +0.009 |
Luis | +0.009 |
Andy | +0.009 |
iring | +0.008 |
strength | +0.008 |
Neg logit contributions | |
bell | -0.006 |
use | -0.006 |
iche | -0.006 |
ues | -0.006 |
aster | -0.006 |
Token | ish |
Token ID | 680 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
Bob | +0.038 |
Luis | +0.038 |
Andy | +0.037 |
Zig | +0.036 |
Flash | +0.036 |
Neg logit contributions | |
use | -0.030 |
iche | -0.029 |
ues | -0.027 |
bell | -0.027 |
aster | -0.027 |
Token | ! |
Token ID | 0 |
Feature activation | -9.24e-04 |
Pos logit contributions | |
Bob | +0.020 |
Luis | +0.019 |
Andy | +0.019 |
strength | +0.018 |
branches | +0.018 |
Neg logit contributions | |
bell | -0.019 |
iche | -0.019 |
ues | -0.019 |
use | -0.019 |
aster | -0.018 |
Token | It |
Token ID | 632 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
Luis | +0.001 |
Bob | +0.001 |
iring | +0.001 |
Andy | +0.001 |
strength | +0.001 |
Neg logit contributions | |
iche | -0.001 |
use | -0.001 |
aster | -0.001 |
ues | -0.001 |
bell | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -7.52e-04 |
Pos logit contributions | |
Bob | +0.028 |
Luis | +0.028 |
Andy | +0.027 |
iring | +0.026 |
Zig | +0.025 |
Neg logit contributions | |
iche | -0.025 |
use | -0.024 |
bell | -0.024 |
ues | -0.024 |
aster | -0.023 |
Token | so |
Token ID | 523 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
Bob | +0.001 |
Luis | +0.001 |
Andy | +0.001 |
strength | +0.001 |
iring | +0.001 |
Neg logit contributions | |
use | -0.001 |
iche | -0.001 |
ues | -0.001 |
bell | -0.001 |
aster | -0.001 |
Token | delicious |
Token ID | 12625 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
Bob | +0.026 |
Luis | +0.024 |
Andy | +0.024 |
strength | +0.023 |
iring | +0.023 |
Neg logit contributions | |
use | -0.026 |
ues | -0.025 |
iche | -0.025 |
bell | -0.025 |
aster | -0.025 |
Token | !' |
Token ID | 13679 |
Feature activation | +7.31e-03 |
Pos logit contributions | |
Luis | +0.017 |
Bob | +0.017 |
Andy | +0.017 |
strength | +0.016 |
Zig | +0.016 |
Neg logit contributions | |
use | -0.018 |
iche | -0.018 |
ues | -0.018 |
aster | -0.018 |
bell | -0.018 |
Token | He |
Token ID | 679 |
Feature activation | -5.39e-03 |
Pos logit contributions | |
aster | +0.010 |
iche | +0.010 |
use | +0.010 |
ues | +0.010 |
Does | +0.010 |
Neg logit contributions | |
Luis | -0.011 |
iring | -0.011 |
Andy | -0.010 |
Bob | -0.010 |
Kel | -0.010 |
Token | hopped |
Token ID | 45230 |
Feature activation | -2.12e-03 |
Pos logit contributions | |
Luis | +0.009 |
Bob | +0.009 |
Andy | +0.009 |
iring | +0.009 |
strength | +0.008 |
Neg logit contributions | |
iche | -0.007 |
bell | -0.007 |
aster | -0.007 |
ues | -0.007 |
use | -0.007 |
Token | away |
Token ID | 1497 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
Luis | +0.003 |
Bob | +0.003 |
Andy | +0.003 |
iring | +0.003 |
strength | +0.003 |
Neg logit contributions | |
use | -0.003 |
iche | -0.003 |
aster | -0.003 |
bell | -0.003 |
ues | -0.003 |
Token | happy |
Token ID | 3772 |
Feature activation | -9.03e-03 |
Pos logit contributions | |
Luis | +0.022 |
Andy | +0.020 |
Bob | +0.020 |
Andy | +0.020 |
Zig | +0.019 |
Neg logit contributions | |
bell | -0.019 |
ues | -0.019 |
iche | -0.018 |
aster | -0.018 |
use | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
Bob | +0.019 |
Luis | +0.019 |
Andy | +0.019 |
strength | +0.018 |
iring | +0.018 |
Neg logit contributions | |
iche | -0.014 |
use | -0.014 |
ues | -0.013 |
aster | -0.013 |
bell | -0.013 |
Token | very |
Token ID | 845 |
Feature activation | +3.57e-03 |
Pos logit contributions | |
use | +0.017 |
ues | +0.017 |
iche | +0.017 |
bell | +0.016 |
aster | +0.016 |
Neg logit contributions | |
Bob | -0.022 |
Luis | -0.021 |
Andy | -0.021 |
friends | -0.020 |
iring | -0.020 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.42e-03 |
Pos logit contributions | |
use | +0.005 |
ues | +0.005 |
aster | +0.005 |
iche | +0.005 |
bell | +0.005 |
Neg logit contributions | |
Bob | -0.006 |
friends | -0.005 |
Luis | -0.005 |
iring | -0.005 |
Andy | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -5.61e-03 |
Pos logit contributions | |
Luis | +0.002 |
Kel | +0.002 |
Zig | +0.002 |
strength | +0.002 |
branches | +0.002 |
Neg logit contributions | |
ues | -0.002 |
aster | -0.002 |
iche | -0.002 |
bell | -0.002 |
use | -0.002 |
Token | have |
Token ID | 423 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
Bob | +0.010 |
Andy | +0.009 |
Luis | +0.009 |
himself | +0.009 |
friends | +0.008 |
Neg logit contributions | |
iche | -0.008 |
ues | -0.008 |
ours | -0.007 |
use | -0.007 |
cheesy | -0.007 |
Token | him |
Token ID | 683 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
aster | +0.020 |
iche | +0.019 |
use | +0.018 |
cheesy | +0.018 |
ues | +0.017 |
Neg logit contributions | |
iring | -0.020 |
Luis | -0.020 |
Kel | -0.018 |
Bob | -0.018 |
Andy | -0.018 |
Token | home |
Token ID | 1363 |
Feature activation | -4.17e-03 |
Pos logit contributions | |
Luis | +0.036 |
Bob | +0.036 |
Andy | +0.035 |
iring | +0.034 |
Flash | +0.033 |
Neg logit contributions | |
use | -0.037 |
aster | -0.037 |
iche | -0.037 |
bell | -0.036 |
ues | -0.036 |
Token | more |
Token ID | 517 |
Feature activation | +2.71e-03 |
Pos logit contributions | |
Bob | +0.006 |
Luis | +0.006 |
Andy | +0.006 |
strength | +0.005 |
iring | +0.005 |
Neg logit contributions | |
iche | -0.007 |
use | -0.006 |
ues | -0.006 |
bell | -0.006 |
aster | -0.006 |
Token | often |
Token ID | 1690 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
iche | +0.004 |
use | +0.004 |
aster | +0.004 |
bell | +0.004 |
ues | +0.004 |
Neg logit contributions | |
Luis | -0.004 |
Bob | -0.004 |
Andy | -0.004 |
Zig | -0.004 |
Andy | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
iche | +0.017 |
use | +0.017 |
ues | +0.017 |
bell | +0.017 |
aster | +0.017 |
Neg logit contributions | |
Bob | -0.018 |
Luis | -0.017 |
Andy | -0.017 |
strength | -0.016 |
iring | -0.016 |
Token | They |
Token ID | 1119 |
Feature activation | -6.33e-03 |
Pos logit contributions | |
Luis | +0.022 |
Bob | +0.021 |
iring | +0.021 |
Andy | +0.020 |
strength | +0.020 |
Neg logit contributions | |
bell | -0.017 |
iche | -0.017 |
ues | -0.017 |
use | -0.016 |
aster | -0.016 |
Token | would |
Token ID | 561 |
Feature activation | +7.99e-03 |
Pos logit contributions | |
ues | +0.012 |
iche | +0.011 |
cheesy | +0.011 |
aster | +0.011 |
wasteful | +0.011 |
Neg logit contributions | |
Bob | -0.013 |
friends | -0.012 |
Luis | -0.012 |
fl | -0.012 |
strength | -0.012 |
Token | go |
Token ID | 467 |
Feature activation | +3.96e-03 |
Pos logit contributions | |
wasteful | +0.013 |
iche | +0.013 |
cheesy | +0.012 |
ues | +0.012 |
use | +0.012 |
Neg logit contributions | |
Bob | -0.011 |
Luis | -0.011 |
friends | -0.011 |
birds | -0.010 |
Flash | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -6.64e-03 |
Pos logit contributions | |
wasteful | +0.009 |
iche | +0.009 |
cheesy | +0.008 |
ues | +0.008 |
aster | +0.008 |
Neg logit contributions | |
friends | -0.003 |
Bob | -0.003 |
Luis | -0.003 |
Andy | -0.003 |
Zig | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -2.43e-03 |
Pos logit contributions | |
Bob | +0.008 |
Luis | +0.008 |
Andy | +0.007 |
strength | +0.007 |
iring | +0.007 |
Neg logit contributions | |
iche | -0.012 |
use | -0.012 |
ues | -0.012 |
bell | -0.012 |
aster | -0.012 |
Token | park |
Token ID | 3952 |
Feature activation | +4.59e-03 |
Pos logit contributions | |
Bob | +0.003 |
Luis | +0.003 |
Andy | +0.003 |
iring | +0.003 |
branches | +0.003 |
Neg logit contributions | |
ues | -0.004 |
use | -0.004 |
iche | -0.004 |
aster | -0.004 |
bell | -0.004 |
Token | with |
Token ID | 351 |
Feature activation | -9.84e-03 |
Pos logit contributions | |
use | +0.010 |
iche | +0.010 |
wasteful | +0.010 |
ues | +0.009 |
aster | +0.009 |
Neg logit contributions | |
Bob | -0.005 |
Andy | -0.004 |
Luis | -0.004 |
friends | -0.004 |
branches | -0.004 |
Token | her |
Token ID | 607 |
Feature activation | -5.09e-03 |
Pos logit contributions | |
Luis | +0.018 |
iring | +0.018 |
Bob | +0.018 |
Andy | +0.017 |
strength | +0.017 |
Neg logit contributions | |
aster | -0.011 |
bell | -0.011 |
iche | -0.010 |
use | -0.010 |
notebooks | -0.009 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
himself | +0.008 |
iring | +0.008 |
Kel | +0.008 |
Andy | +0.008 |
Luis | +0.008 |
Neg logit contributions | |
folder | -0.007 |
notebooks | -0.006 |
bell | -0.006 |
pron | -0.006 |
album | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
iche | +0.045 |
ues | +0.045 |
use | +0.044 |
aster | +0.044 |
bell | +0.043 |
Neg logit contributions | |
Bob | -0.036 |
Luis | -0.034 |
Andy | -0.034 |
friends | -0.032 |
iring | -0.031 |
Token | sing |
Token ID | 1702 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
use | +0.029 |
aster | +0.029 |
bell | +0.028 |
iche | +0.027 |
gallery | +0.026 |
Neg logit contributions | |
iring | -0.039 |
Luis | -0.039 |
Bob | -0.038 |
strength | -0.037 |
branches | -0.037 |
Token | her |
Token ID | 607 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
ues | +0.022 |
iche | +0.022 |
bell | +0.022 |
aster | +0.022 |
use | +0.021 |
Neg logit contributions | |
Luis | -0.019 |
Bob | -0.019 |
Andy | -0.019 |
iring | -0.018 |
strength | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +1.87e-03 |
Pos logit contributions | |
iring | +0.002 |
strength | +0.002 |
fl | +0.002 |
Luis | +0.002 |
plunge | +0.002 |
Neg logit contributions | |
iche | -0.001 |
ues | -0.001 |
bell | -0.001 |
aster | -0.001 |
Does | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +5.84e-03 |
Pos logit contributions | |
aster | +0.003 |
iche | +0.003 |
ues | +0.003 |
use | +0.002 |
bell | +0.002 |
Neg logit contributions | |
Luis | -0.003 |
strength | -0.003 |
Bob | -0.003 |
iring | -0.003 |
branches | -0.003 |
Token | When |
Token ID | 2215 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
aster | +0.009 |
iche | +0.008 |
use | +0.008 |
ues | +0.008 |
bell | +0.008 |
Neg logit contributions | |
Bob | -0.009 |
Luis | -0.009 |
Andy | -0.008 |
strength | -0.008 |
iring | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -2.31e-03 |
Pos logit contributions | |
iring | +0.035 |
Luis | +0.035 |
strength | +0.033 |
Bob | +0.033 |
Kel | +0.032 |
Neg logit contributions | |
aster | -0.039 |
iche | -0.035 |
use | -0.035 |
cheesy | -0.034 |
bell | -0.034 |
Token | race |
Token ID | 3234 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
Luis | +0.003 |
Calvin | +0.003 |
Andy | +0.003 |
Bob | +0.003 |
Owen | +0.003 |
Neg logit contributions | |
bell | -0.004 |
aster | -0.003 |
iche | -0.003 |
use | -0.003 |
wedding | -0.003 |
Token | started |
Token ID | 2067 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
iring | +0.055 |
hind | +0.054 |
Luis | +0.054 |
strength | +0.053 |
Flash | +0.051 |
Neg logit contributions | |
bell | -0.034 |
aster | -0.031 |
use | -0.028 |
ues | -0.028 |
gallery | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +6.75e-04 |
Pos logit contributions | |
iring | +0.067 |
Luis | +0.064 |
Andy | +0.063 |
strength | +0.063 |
Bob | +0.062 |
Neg logit contributions | |
bell | -0.044 |
ues | -0.043 |
aster | -0.041 |
iche | -0.039 |
ours | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | -2.68e-03 |
Pos logit contributions | |
aster | +0.001 |
Does | +0.001 |
Does | +0.001 |
cheesy | +0.001 |
iche | +0.001 |
Neg logit contributions | |
iring | -0.001 |
axter | -0.001 |
ert | -0.001 |
Luis | -0.001 |
fl | -0.001 |
Token | ostr |
Token ID | 42387 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
Luis | +0.004 |
Calvin | +0.004 |
Andy | +0.004 |
Bob | +0.003 |
Owen | +0.003 |
Neg logit contributions | |
bell | -0.004 |
aster | -0.004 |
iche | -0.004 |
use | -0.004 |
slice | -0.004 |
Token | ich |
Token ID | 488 |
Feature activation | -8.40e-03 |
Pos logit contributions | |
Bob | +0.054 |
Luis | +0.053 |
Andy | +0.052 |
strength | +0.050 |
Calvin | +0.050 |
Neg logit contributions | |
ues | -0.044 |
iche | -0.043 |
bell | -0.042 |
use | -0.040 |
ours | -0.040 |
Token | ran |
Token ID | 4966 |
Feature activation | -6.20e-03 |
Pos logit contributions | |
Bob | +0.015 |
Luis | +0.015 |
iring | +0.015 |
Andy | +0.015 |
Kel | +0.014 |
Neg logit contributions | |
bell | -0.009 |
iche | -0.009 |
use | -0.009 |
aster | -0.009 |
ues | -0.009 |
Token | And |
Token ID | 843 |
Feature activation | -5.88e-03 |
Pos logit contributions | |
iche | +0.003 |
aster | +0.003 |
Does | +0.003 |
ues | +0.003 |
bell | +0.003 |
Neg logit contributions | |
iring | -0.004 |
fl | -0.004 |
Luis | -0.004 |
plunge | -0.003 |
strength | -0.003 |
Token | just |
Token ID | 655 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
Luis | +0.009 |
iger | +0.009 |
iring | +0.009 |
Andy | +0.009 |
fl | +0.009 |
Neg logit contributions | |
aster | -0.007 |
wasteful | -0.006 |
Does | -0.006 |
cheesy | -0.006 |
ues | -0.006 |
Token | as |
Token ID | 355 |
Feature activation | -4.88e-03 |
Pos logit contributions | |
Luis | +0.035 |
iring | +0.034 |
Bob | +0.032 |
Zig | +0.032 |
Flash | +0.032 |
Neg logit contributions | |
aster | -0.028 |
use | -0.028 |
bell | -0.027 |
iche | -0.026 |
wasteful | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -4.39e-03 |
Pos logit contributions | |
Luis | +0.007 |
iring | +0.007 |
fl | +0.007 |
Kel | +0.007 |
strength | +0.007 |
Neg logit contributions | |
aster | -0.007 |
cheesy | -0.006 |
bell | -0.006 |
use | -0.006 |
iche | -0.006 |
Token | sunrise |
Token ID | 40048 |
Feature activation | -8.48e-03 |
Pos logit contributions | |
Bob | +0.006 |
Luis | +0.006 |
iring | +0.006 |
Zig | +0.006 |
Kel | +0.006 |
Neg logit contributions | |
bell | -0.006 |
aster | -0.006 |
iche | -0.006 |
use | -0.006 |
wasteful | -0.006 |
Token | came |
Token ID | 1625 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
iring | +0.014 |
Luis | +0.014 |
Bob | +0.014 |
Andy | +0.014 |
strength | +0.013 |
Neg logit contributions | |
aster | -0.010 |
bell | -0.010 |
iche | -0.010 |
use | -0.010 |
ues | -0.009 |
Token | up |
Token ID | 510 |
Feature activation | +2.82e-03 |
Pos logit contributions | |
Luis | +0.067 |
Calvin | +0.063 |
Bob | +0.061 |
strength | +0.060 |
Stev | +0.060 |
Neg logit contributions | |
bell | -0.047 |
use | -0.039 |
ues | -0.036 |
iche | -0.036 |
iner | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | +1.38e-03 |
Pos logit contributions | |
iche | +0.004 |
use | +0.004 |
bell | +0.004 |
aster | +0.004 |
ues | +0.004 |
Neg logit contributions | |
Luis | -0.004 |
Bob | -0.004 |
Andy | -0.004 |
strength | -0.004 |
iring | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +1.14e-03 |
Pos logit contributions | |
aster | +0.002 |
iche | +0.002 |
Does | +0.002 |
bell | +0.002 |
use | +0.002 |
Neg logit contributions | |
Luis | -0.002 |
iring | -0.002 |
strength | -0.002 |
ert | -0.002 |
fl | -0.002 |
Token | famous |
Token ID | 5863 |
Feature activation | +4.84e-03 |
Pos logit contributions | |
iche | +0.002 |
bell | +0.002 |
aster | +0.002 |
cheesy | +0.002 |
use | +0.002 |
Neg logit contributions | |
Luis | -0.002 |
Bob | -0.002 |
iring | -0.002 |
Kel | -0.002 |
Zig | -0.001 |
Token | tiger |
Token ID | 26241 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
bell | +0.008 |
iche | +0.008 |
aster | +0.007 |
ues | +0.007 |
use | +0.007 |
Neg logit contributions | |
Luis | -0.007 |
Bob | -0.006 |
iring | -0.006 |
himself | -0.006 |
Zig | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -6.39e-03 |
Pos logit contributions | |
iche | +0.005 |
use | +0.004 |
aster | +0.004 |
ues | +0.004 |
bell | +0.004 |
Neg logit contributions | |
Bob | -0.003 |
Luis | -0.003 |
Andy | -0.003 |
strength | -0.002 |
iring | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | +7.59e-03 |
Pos logit contributions | |
iring | +0.012 |
Luis | +0.012 |
ert | +0.011 |
strength | +0.011 |
fl | +0.011 |
Neg logit contributions | |
aster | -0.006 |
bell | -0.005 |
heaven | -0.005 |
ven | -0.005 |
Or | -0.005 |
Token | friend |
Token ID | 1545 |
Feature activation | +6.01e-03 |
Pos logit contributions | |
bell | +0.013 |
ues | +0.013 |
folder | +0.013 |
named | +0.012 |
iche | +0.012 |
Neg logit contributions | |
Luis | -0.009 |
Kel | -0.008 |
Bob | -0.008 |
plunge | -0.008 |
Andy | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -8.50e-05 |
Pos logit contributions | |
iche | +0.008 |
use | +0.008 |
aster | +0.008 |
bell | +0.008 |
ues | +0.008 |
Neg logit contributions | |
Luis | -0.009 |
iring | -0.009 |
strength | -0.009 |
branches | -0.009 |
Bob | -0.009 |
Token | Dog |
Token ID | 8532 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
iring | +0.000 |
strength | +0.000 |
Luis | +0.000 |
branches | +0.000 |
ert | +0.000 |
Neg logit contributions | |
aster | -0.000 |
iche | -0.000 |
use | -0.000 |
bell | -0.000 |
Does | -0.000 |
Token | gy |
Token ID | 1360 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
iring | +0.032 |
strength | +0.031 |
Luis | +0.031 |
branches | +0.029 |
Bob | +0.029 |
Neg logit contributions | |
use | -0.032 |
bell | -0.032 |
iche | -0.030 |
ues | -0.030 |
aster | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
Luis | +0.069 |
iring | +0.067 |
Bob | +0.065 |
strength | +0.063 |
Andy | +0.063 |
Neg logit contributions | |
bell | -0.053 |
iche | -0.053 |
use | -0.053 |
aster | -0.053 |
ues | -0.052 |
Token | Dog |
Token ID | 8532 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
ert | +0.027 |
iring | +0.025 |
Luis | +0.024 |
strength | +0.024 |
plunge | +0.024 |
Neg logit contributions | |
bell | -0.029 |
Does | -0.027 |
Amen | -0.026 |
use | -0.026 |
ues | -0.025 |
Token | gy |
Token ID | 1360 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
iring | +0.042 |
Luis | +0.041 |
strength | +0.041 |
plunge | +0.039 |
branches | +0.038 |
Neg logit contributions | |
bell | -0.036 |
use | -0.036 |
mary | -0.032 |
iche | -0.031 |
ues | -0.031 |
Token | said |
Token ID | 531 |
Feature activation | -4.85e-03 |
Pos logit contributions | |
Luis | +0.075 |
iring | +0.072 |
Bob | +0.071 |
Andy | +0.069 |
Flash | +0.069 |
Neg logit contributions | |
bell | -0.054 |
use | -0.053 |
iche | -0.053 |
ues | -0.052 |
aster | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | +1.42e-03 |
Pos logit contributions | |
Bob | +0.006 |
Luis | +0.006 |
Andy | +0.006 |
strength | +0.006 |
Zig | +0.006 |
Neg logit contributions | |
iche | -0.009 |
use | -0.008 |
ues | -0.008 |
aster | -0.008 |
bell | -0.008 |
Token | really |
Token ID | 1107 |
Feature activation | +7.11e-04 |
Pos logit contributions | |
aster | +0.004 |
ues | +0.004 |
bell | +0.004 |
iche | +0.004 |
use | +0.004 |
Neg logit contributions | |
Luis | -0.004 |
Bob | -0.004 |
iring | -0.004 |
Andy | -0.004 |
fl | -0.004 |
Token | hard |
Token ID | 1327 |
Feature activation | +5.56e-03 |
Pos logit contributions | |
iche | +0.001 |
use | +0.001 |
bell | +0.001 |
ues | +0.001 |
aster | +0.001 |
Neg logit contributions | |
Bob | -0.001 |
Luis | -0.001 |
Andy | -0.001 |
strength | -0.001 |
Flash | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.30e-03 |
Pos logit contributions | |
ues | +0.007 |
bell | +0.007 |
use | +0.007 |
aster | +0.007 |
iche | +0.006 |
Neg logit contributions | |
Luis | -0.009 |
Bob | -0.009 |
Andy | -0.009 |
iring | -0.009 |
Kel | -0.009 |
Token | Finally |
Token ID | 9461 |
Feature activation | +7.46e-03 |
Pos logit contributions | |
Does | +0.002 |
iche | +0.002 |
aster | +0.002 |
bell | +0.002 |
use | +0.001 |
Neg logit contributions | |
iring | -0.002 |
Luis | -0.002 |
fl | -0.002 |
strength | -0.002 |
plunge | -0.002 |
Token | he |
Token ID | 339 |
Feature activation | +8.92e-04 |
Pos logit contributions | |
use | +0.012 |
iche | +0.012 |
aster | +0.012 |
ues | +0.012 |
bell | +0.012 |
Neg logit contributions | |
Bob | -0.010 |
Luis | -0.010 |
Andy | -0.010 |
iring | -0.010 |
strength | -0.009 |
Token | came |
Token ID | 1625 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
iche | +0.001 |
use | +0.001 |
bell | +0.001 |
aster | +0.001 |
ues | +0.001 |
Neg logit contributions | |
Bob | -0.002 |
Luis | -0.002 |
Andy | -0.002 |
iring | -0.002 |
strength | -0.002 |
Token | back |
Token ID | 736 |
Feature activation | +5.20e-03 |
Pos logit contributions | |
Luis | +0.074 |
Kel | +0.073 |
Stev | +0.073 |
Ced | +0.070 |
Andy | +0.068 |
Neg logit contributions | |
bell | -0.035 |
ues | -0.033 |
use | -0.033 |
Does | -0.030 |
aves | -0.030 |
Token | with |
Token ID | 351 |
Feature activation | -3.23e-03 |
Pos logit contributions | |
bell | +0.007 |
aster | +0.007 |
use | +0.006 |
ues | +0.006 |
heaven | +0.006 |
Neg logit contributions | |
Luis | -0.008 |
strength | -0.008 |
branches | -0.008 |
plunge | -0.008 |
Zig | -0.008 |
Token | Daddy |
Token ID | 26926 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
Luis | +0.004 |
Bob | +0.004 |
iring | +0.004 |
Andy | +0.004 |
Zig | +0.004 |
Neg logit contributions | |
aster | -0.005 |
use | -0.005 |
iche | -0.005 |
bell | -0.005 |
ues | -0.005 |
Token | 's |
Token ID | 338 |
Feature activation | -8.25e-03 |
Pos logit contributions | |
use | +0.013 |
bell | +0.013 |
aster | +0.013 |
ues | +0.013 |
iche | +0.013 |
Neg logit contributions | |
Luis | -0.016 |
Bob | -0.016 |
iring | -0.016 |
strength | -0.015 |
branches | -0.015 |
Token | iron |
Token ID | 6953 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
Bob | +0.011 |
Luis | +0.011 |
iring | +0.011 |
Andy | +0.011 |
Zig | +0.010 |
Neg logit contributions | |
use | -0.013 |
bell | -0.013 |
aster | -0.013 |
iche | -0.013 |
ues | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
Kel | +0.043 |
Luis | +0.043 |
Andy | +0.043 |
iring | +0.042 |
Stev | +0.041 |
Neg logit contributions | |
ues | -0.030 |
use | -0.028 |
aster | -0.028 |
iche | -0.027 |
arium | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -2.33e-03 |
Pos logit contributions | |
iring | +0.015 |
Luis | +0.015 |
fl | +0.014 |
Kel | +0.014 |
Bob | +0.014 |
Neg logit contributions | |
aster | -0.018 |
iche | -0.017 |
use | -0.016 |
ues | -0.016 |
bell | -0.015 |
Token | new |
Token ID | 649 |
Feature activation | -9.63e-03 |
Pos logit contributions | |
Luis | +0.003 |
Bob | +0.003 |
Andy | +0.003 |
Kel | +0.003 |
iring | +0.003 |
Neg logit contributions | |
iche | -0.004 |
aster | -0.004 |
use | -0.004 |
bell | -0.004 |
ues | -0.004 |
Token | pond |
Token ID | 16723 |
Feature activation | -2.73e-03 |
Pos logit contributions | |
Luis | +0.013 |
Andy | +0.013 |
Kel | +0.012 |
Bob | +0.012 |
iring | +0.012 |
Neg logit contributions | |
ues | -0.015 |
iche | -0.015 |
use | -0.014 |
arium | -0.014 |
aster | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
Bob | +0.004 |
Luis | +0.004 |
Andy | +0.003 |
strength | +0.003 |
branches | +0.003 |
Neg logit contributions | |
iche | -0.005 |
use | -0.004 |
aster | -0.004 |
bell | -0.004 |
ues | -0.004 |
Token | There |
Token ID | 1318 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
Luis | +0.037 |
Kel | +0.034 |
strength | +0.034 |
iring | +0.034 |
ert | +0.033 |
Neg logit contributions | |
iche | -0.025 |
ues | -0.023 |
use | -0.022 |
ours | -0.022 |
Does | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -7.34e-03 |
Pos logit contributions | |
Luis | +0.068 |
iring | +0.066 |
Kel | +0.066 |
branches | +0.063 |
Calvin | +0.062 |
Neg logit contributions | |
use | -0.040 |
arium | -0.039 |
iche | -0.038 |
ues | -0.037 |
aster | -0.037 |
Token | he |
Token ID | 339 |
Feature activation | -6.29e-04 |
Pos logit contributions | |
Luis | +0.014 |
Kel | +0.014 |
Jo | +0.014 |
Stev | +0.014 |
axter | +0.014 |
Neg logit contributions | |
arium | -0.006 |
cheesy | -0.006 |
wasteful | -0.005 |
iche | -0.005 |
aster | -0.005 |
Token | made |
Token ID | 925 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
Bob | +0.001 |
Luis | +0.001 |
Andy | +0.001 |
iring | +0.001 |
strength | +0.001 |
Neg logit contributions | |
iche | -0.001 |
use | -0.001 |
ues | -0.001 |
bell | -0.001 |
aster | -0.001 |
Token | new |
Token ID | 649 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
Luis | +0.041 |
Kel | +0.040 |
iring | +0.038 |
Stev | +0.038 |
Calvin | +0.037 |
Neg logit contributions | |
iche | -0.033 |
aster | -0.033 |
ues | -0.031 |
cheesy | -0.031 |
ackers | -0.028 |
Token | friends |
Token ID | 2460 |
Feature activation | +5.39e-04 |
Pos logit contributions | |
Kel | +0.022 |
Andy | +0.020 |
Luis | +0.020 |
Stev | +0.019 |
Andy | +0.019 |
Neg logit contributions | |
ues | -0.039 |
arium | -0.038 |
notebooks | -0.037 |
decide | -0.036 |
agree | -0.036 |