Token | the |
Token ID | 262 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
off | +0.030 |
adoes | +0.030 |
ags | +0.027 |
< | +0.027 |
asuring | +0.027 |
Neg logit contributions | |
ho | -0.094 |
ited | -0.086 |
solar | -0.084 |
mer | -0.080 |
wished | -0.079 |
Token | mess |
Token ID | 2085 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
off | +0.032 |
Zip | +0.030 |
our | +0.029 |
Buddy | +0.029 |
Kitty | +0.029 |
Neg logit contributions | |
ho | -0.037 |
ited | -0.034 |
mer | -0.030 |
solar | -0.029 |
thank | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
off | +0.012 |
our | +0.011 |
two | +0.010 |
some | +0.010 |
Zip | +0.010 |
Neg logit contributions | |
ho | -0.043 |
ited | -0.039 |
mer | -0.036 |
solar | -0.036 |
years | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
off | +0.017 |
adoes | +0.016 |
icle | +0.015 |
ags | +0.015 |
Buddy | +0.015 |
Neg logit contributions | |
ho | -0.062 |
ited | -0.055 |
solar | -0.054 |
years | -0.052 |
wished | -0.051 |
Token | qu |
Token ID | 627 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
off | +0.023 |
our | +0.021 |
some | +0.020 |
Zip | +0.020 |
two | +0.020 |
Neg logit contributions | |
ho | -0.034 |
ited | -0.031 |
solar | -0.028 |
mer | -0.027 |
lifetime | -0.026 |
Token | arre |
Token ID | 9624 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
off | +0.076 |
Spot | +0.074 |
Zip | +0.074 |
what | +0.072 |
Buddy | +0.072 |
Neg logit contributions | |
ho | -0.070 |
ited | -0.066 |
mer | -0.058 |
solar | -0.052 |
thank | -0.049 |
Token | ling |
Token ID | 1359 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Spot | +0.138 |
Zip | +0.135 |
Rex | +0.134 |
off | +0.134 |
Buddy | +0.133 |
Neg logit contributions | |
ho | -0.131 |
ited | -0.126 |
mer | -0.110 |
solar | -0.100 |
thank | -0.096 |
Token | twins |
Token ID | 20345 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
off | +0.058 |
our | +0.056 |
Zip | +0.056 |
what | +0.054 |
Spot | +0.053 |
Neg logit contributions | |
ho | -0.107 |
ited | -0.095 |
mer | -0.089 |
solar | -0.085 |
thank | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
off | +0.022 |
two | +0.020 |
some | +0.020 |
our | +0.020 |
what | +0.019 |
Neg logit contributions | |
ho | -0.044 |
ited | -0.041 |
solar | -0.038 |
mer | -0.037 |
lifetime | -0.036 |
Token | She |
Token ID | 1375 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
off | +0.030 |
our | +0.027 |
two | +0.027 |
some | +0.027 |
adoes | +0.027 |
Neg logit contributions | |
ho | -0.040 |
solar | -0.032 |
ited | -0.032 |
mer | -0.030 |
commented | -0.028 |
Token | is |
Token ID | 318 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
off | +0.047 |
adoes | +0.047 |
icle | +0.046 |
icles | +0.045 |
Buddy | +0.044 |
Neg logit contributions | |
ho | -0.058 |
ited | -0.048 |
solar | -0.046 |
years | -0.043 |
wished | -0.043 |
Token | says |
Token ID | 1139 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
off | +0.055 |
adoes | +0.051 |
some | +0.051 |
two | +0.050 |
our | +0.050 |
Neg logit contributions | |
ho | -0.072 |
ited | -0.066 |
solar | -0.060 |
mer | -0.056 |
years | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
ags | +0.031 |
snowball | +0.029 |
adoes | +0.028 |
icle | +0.028 |
< | +0.028 |
Neg logit contributions | |
ho | -0.028 |
solar | -0.015 |
years | -0.015 |
wished | -0.015 |
spe | -0.015 |
Token | " |
Token ID | 366 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
off | +0.013 |
ags | +0.012 |
our | +0.012 |
adoes | +0.012 |
snowball | +0.011 |
Neg logit contributions | |
ho | -0.019 |
solar | -0.013 |
wished | -0.013 |
wishing | -0.013 |
ven | -0.013 |
Token | Stop |
Token ID | 19485 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
off | +0.029 |
about | +0.026 |
some | +0.026 |
our | +0.025 |
adoes | +0.025 |
Neg logit contributions | |
ho | -0.040 |
ited | -0.038 |
mer | -0.032 |
thank | -0.031 |
solar | -0.031 |
Token | qu |
Token ID | 627 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ags | +0.005 |
off | +0.005 |
adoes | +0.004 |
< | +0.004 |
two | +0.004 |
Neg logit contributions | |
ho | -0.009 |
ited | -0.008 |
wished | -0.007 |
mer | -0.007 |
commented | -0.007 |
Token | arre |
Token ID | 9624 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
off | +0.052 |
some | +0.051 |
Spot | +0.051 |
two | +0.051 |
Zip | +0.050 |
Neg logit contributions | |
ho | -0.064 |
ited | -0.064 |
mer | -0.053 |
solar | -0.052 |
years | -0.049 |
Token | ling |
Token ID | 1359 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
off | +0.126 |
two | +0.122 |
some | +0.122 |
Spot | +0.122 |
Zip | +0.119 |
Neg logit contributions | |
ho | -0.142 |
ited | -0.133 |
mer | -0.117 |
solar | -0.114 |
years | -0.107 |
Token | , |
Token ID | 11 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
off | +0.030 |
two | +0.028 |
some | +0.027 |
our | +0.027 |
what | +0.026 |
Neg logit contributions | |
ho | -0.067 |
ited | -0.061 |
solar | -0.057 |
mer | -0.056 |
lifetime | -0.053 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
off | +0.008 |
adoes | +0.007 |
some | +0.007 |
ags | +0.006 |
< | +0.006 |
Neg logit contributions | |
ho | -0.027 |
ited | -0.025 |
mer | -0.023 |
wished | -0.022 |
solar | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
ho | +0.012 |
ited | +0.011 |
solar | +0.010 |
mer | +0.010 |
lifetime | +0.010 |
Neg logit contributions | |
off | -0.002 |
two | -0.002 |
some | -0.002 |
our | -0.002 |
what | -0.002 |
Token | Lily |
Token ID | 20037 |
Feature activation | -6.58e-03 |
Pos logit contributions | |
off | +0.007 |
two | +0.006 |
some | +0.006 |
ags | +0.006 |
about | +0.006 |
Neg logit contributions | |
ho | -0.022 |
ited | -0.019 |
solar | -0.018 |
mer | -0.017 |
years | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
off | +0.012 |
our | +0.011 |
two | +0.011 |
adoes | +0.010 |
some | +0.010 |
Neg logit contributions | |
ho | -0.052 |
ited | -0.048 |
solar | -0.044 |
mer | -0.044 |
lifetime | -0.043 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
ho | +0.003 |
ited | +0.003 |
solar | +0.003 |
mer | +0.003 |
lifetime | +0.003 |
Neg logit contributions | |
off | -0.003 |
two | -0.003 |
some | -0.003 |
what | -0.003 |
our | -0.003 |
Token | two |
Token ID | 734 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
off | +0.007 |
our | +0.006 |
two | +0.006 |
some | +0.005 |
adoes | +0.005 |
Neg logit contributions | |
ho | -0.046 |
ited | -0.043 |
solar | -0.040 |
mer | -0.039 |
lifetime | -0.039 |
Token | birds |
Token ID | 10087 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
off | +0.006 |
our | +0.006 |
some | +0.006 |
two | +0.006 |
adoes | +0.005 |
Neg logit contributions | |
ho | -0.016 |
ited | -0.015 |
solar | -0.014 |
mer | -0.013 |
lifetime | -0.013 |
Token | qu |
Token ID | 627 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
off | +0.010 |
two | +0.010 |
our | +0.010 |
some | +0.010 |
adoes | +0.009 |
Neg logit contributions | |
ho | -0.021 |
ited | -0.019 |
solar | -0.017 |
mer | -0.017 |
lifetime | -0.017 |
Token | arre |
Token ID | 9624 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
mom | +0.068 |
Spot | +0.066 |
some | +0.066 |
what | +0.066 |
off | +0.066 |
Neg logit contributions | |
ho | -0.052 |
ited | -0.051 |
mer | -0.042 |
solar | -0.038 |
years | -0.038 |
Token | ling |
Token ID | 1359 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
off | +0.138 |
Spot | +0.137 |
two | +0.136 |
mom | +0.136 |
some | +0.135 |
Neg logit contributions | |
ho | -0.129 |
ited | -0.121 |
mer | -0.104 |
solar | -0.098 |
ad | -0.092 |
Token | ! |
Token ID | 0 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
off | +0.029 |
two | +0.027 |
some | +0.026 |
our | +0.026 |
what | +0.024 |
Neg logit contributions | |
ho | -0.080 |
ited | -0.074 |
solar | -0.069 |
mer | -0.067 |
lifetime | -0.066 |
Token | They |
Token ID | 1119 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
off | +0.005 |
adoes | +0.005 |
our | +0.005 |
ags | +0.005 |
what | +0.004 |
Neg logit contributions | |
ho | -0.010 |
ited | -0.009 |
mer | -0.009 |
solar | -0.009 |
years | -0.008 |
Token | were |
Token ID | 547 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
ho | +0.001 |
ited | +0.001 |
solar | +0.001 |
mer | +0.001 |
lifetime | +0.001 |
Neg logit contributions | |
off | -0.001 |
two | -0.001 |
some | -0.001 |
what | -0.001 |
them | -0.001 |
Token | squ |
Token ID | 2809 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
adoes | +0.009 |
off | +0.009 |
some | +0.009 |
our | +0.009 |
cookies | +0.009 |
Neg logit contributions | |
ho | -0.015 |
ited | -0.013 |
solar | -0.012 |
ad | -0.012 |
years | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
ho | +0.005 |
ited | +0.004 |
solar | +0.004 |
mer | +0.004 |
lifetime | +0.004 |
Neg logit contributions | |
off | -0.002 |
two | -0.001 |
some | -0.001 |
our | -0.001 |
adoes | -0.001 |
Token | They |
Token ID | 1119 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
ho | +0.001 |
ited | +0.001 |
solar | +0.001 |
mer | +0.001 |
lifetime | +0.001 |
Neg logit contributions | |
off | -0.000 |
two | -0.000 |
some | -0.000 |
adoes | -0.000 |
our | -0.000 |
Token | had |
Token ID | 550 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
ho | +0.001 |
ited | +0.001 |
umm | +0.001 |
mer | +0.001 |
lifetime | +0.001 |
Neg logit contributions | |
two | -0.001 |
the | -0.001 |
some | -0.001 |
off | -0.001 |
Spot | -0.001 |
Token | stopped |
Token ID | 5025 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
off | +0.004 |
two | +0.004 |
some | +0.004 |
our | +0.004 |
what | +0.004 |
Neg logit contributions | |
ho | -0.010 |
ited | -0.009 |
solar | -0.009 |
mer | -0.009 |
lifetime | -0.008 |
Token | qu |
Token ID | 627 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
off | +0.006 |
Zip | +0.005 |
adoes | +0.005 |
uate | +0.005 |
icles | +0.005 |
Neg logit contributions | |
ho | -0.010 |
solar | -0.009 |
ited | -0.008 |
mer | -0.008 |
years | -0.008 |
Token | arre |
Token ID | 9624 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
off | +0.043 |
what | +0.043 |
mom | +0.043 |
our | +0.043 |
Spot | +0.042 |
Neg logit contributions | |
ited | -0.056 |
ho | -0.054 |
mer | -0.048 |
solar | -0.044 |
years | -0.043 |
Token | ling |
Token ID | 1359 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
off | +0.131 |
two | +0.126 |
some | +0.125 |
our | +0.124 |
Spot | +0.123 |
Neg logit contributions | |
ho | -0.137 |
ited | -0.127 |
mer | -0.110 |
solar | -0.109 |
lifetime | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | +2.03e-03 |
Pos logit contributions | |
off | +0.022 |
two | +0.020 |
some | +0.019 |
our | +0.018 |
what | +0.017 |
Neg logit contributions | |
ho | -0.090 |
ited | -0.085 |
solar | -0.079 |
mer | -0.077 |
lifetime | -0.076 |
Token | To |
Token ID | 1675 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
off | +0.000 |
adoes | +0.000 |
two | +0.000 |
some | +0.000 |
our | +0.000 |
Neg logit contributions | |
ho | -0.000 |
ited | -0.000 |
solar | -0.000 |
mer | -0.000 |
lifetime | -0.000 |
Token | celebrate |
Token ID | 10648 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
ho | +0.004 |
ited | +0.003 |
solar | +0.003 |
mer | +0.003 |
lifetime | +0.003 |
Neg logit contributions | |
off | -0.001 |
two | -0.001 |
some | -0.001 |
our | -0.001 |
what | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
off | +0.003 |
two | +0.003 |
some | +0.003 |
our | +0.003 |
adoes | +0.003 |
Neg logit contributions | |
ho | -0.009 |
ited | -0.009 |
solar | -0.008 |
mer | -0.008 |
lifetime | -0.008 |
Token | weather |
Token ID | 6193 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
off | +0.008 |
two | +0.008 |
some | +0.008 |
our | +0.008 |
what | +0.007 |
Neg logit contributions | |
ho | -0.020 |
ited | -0.019 |
solar | -0.017 |
mer | -0.017 |
lifetime | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
ho | +0.008 |
ited | +0.008 |
solar | +0.008 |
years | +0.007 |
lifetime | +0.007 |
Neg logit contributions | |
off | -0.002 |
some | -0.002 |
two | -0.002 |
about | -0.002 |
them | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
off | +0.015 |
adoes | +0.013 |
our | +0.013 |
cookies | +0.013 |
friends | +0.012 |
Neg logit contributions | |
ho | -0.027 |
solar | -0.024 |
ited | -0.023 |
mer | -0.023 |
generation | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
off | +0.013 |
adoes | +0.012 |
our | +0.011 |
some | +0.011 |
two | +0.011 |
Neg logit contributions | |
ho | -0.033 |
ited | -0.030 |
solar | -0.028 |
mer | -0.028 |
lifetime | -0.027 |
Token | M |
Token ID | 44 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
off | +0.013 |
adoes | +0.011 |
our | +0.011 |
some | +0.011 |
what | +0.011 |
Neg logit contributions | |
ho | -0.020 |
ited | -0.019 |
mer | -0.017 |
solar | -0.017 |
lifetime | -0.017 |
Token | add |
Token ID | 2860 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
off | +0.043 |
two | +0.040 |
some | +0.040 |
our | +0.039 |
what | +0.038 |
Neg logit contributions | |
ho | -0.061 |
ited | -0.056 |
solar | -0.050 |
mer | -0.049 |
lifetime | -0.048 |
Token | ie |
Token ID | 494 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
off | +0.131 |
two | +0.125 |
some | +0.123 |
our | +0.121 |
them | +0.119 |
Neg logit contributions | |
ho | -0.139 |
ited | -0.125 |
solar | -0.113 |
mer | -0.107 |
lifetime | -0.106 |
Token | was |
Token ID | 373 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
off | +0.024 |
two | +0.023 |
some | +0.023 |
friends | +0.021 |
our | +0.021 |
Neg logit contributions | |
ho | -0.039 |
ited | -0.036 |
solar | -0.033 |
mer | -0.032 |
lifetime | -0.032 |
Token | playing |
Token ID | 2712 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
ho | +0.007 |
ited | +0.007 |
years | +0.006 |
solar | +0.006 |
mer | +0.006 |
Neg logit contributions | |
off | -0.006 |
adoes | -0.006 |
our | -0.006 |
icles | -0.005 |
cookies | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
off | +0.007 |
our | +0.007 |
two | +0.006 |
adoes | +0.006 |
my | +0.006 |
Neg logit contributions | |
ho | -0.025 |
ited | -0.023 |
mer | -0.022 |
solar | -0.022 |
thank | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
ho | +0.020 |
ited | +0.019 |
solar | +0.018 |
mer | +0.017 |
lifetime | +0.017 |
Neg logit contributions | |
off | -0.002 |
two | -0.002 |
our | -0.001 |
some | -0.001 |
adoes | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
off | +0.005 |
two | +0.004 |
adoes | +0.004 |
our | +0.004 |
Buddy | +0.004 |
Neg logit contributions | |
ho | -0.021 |
ited | -0.020 |
solar | -0.019 |
mer | -0.018 |
lifetime | -0.017 |
Token | cheese |
Token ID | 9891 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
off | +0.020 |
two | +0.019 |
some | +0.018 |
our | +0.018 |
what | +0.018 |
Neg logit contributions | |
ho | -0.041 |
ited | -0.038 |
solar | -0.035 |
mer | -0.034 |
lifetime | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
off | +0.014 |
two | +0.012 |
some | +0.012 |
our | +0.012 |
what | +0.011 |
Neg logit contributions | |
ho | -0.051 |
ited | -0.049 |
solar | -0.045 |
mer | -0.044 |
lifetime | -0.044 |
Token | sauce |
Token ID | 10746 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
off | +0.016 |
two | +0.013 |
adoes | +0.013 |
about | +0.013 |
ags | +0.013 |
Neg logit contributions | |
ho | -0.039 |
ited | -0.035 |
solar | -0.033 |
mer | -0.032 |
lifetime | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
off | +0.012 |
some | +0.011 |
two | +0.010 |
on | +0.010 |
our | +0.010 |
Neg logit contributions | |
ho | -0.036 |
ited | -0.036 |
solar | -0.032 |
lifetime | -0.032 |
years | -0.032 |
Token | topp |
Token ID | 23126 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
off | +0.014 |
two | +0.012 |
adoes | +0.012 |
about | +0.012 |
our | +0.012 |
Neg logit contributions | |
ho | -0.032 |
ited | -0.029 |
solar | -0.027 |
mer | -0.026 |
lifetime | -0.025 |
Token | ings |
Token ID | 654 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
Buddy | +0.131 |
Kitty | +0.126 |
Zip | +0.125 |
Spot | +0.123 |
off | +0.123 |
Neg logit contributions | |
ho | -0.134 |
ited | -0.103 |
mer | -0.098 |
solar | -0.091 |
yt | -0.086 |
Token | . |
Token ID | 13 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
ho | +0.002 |
ited | +0.002 |
solar | +0.001 |
mer | +0.001 |
thank | +0.001 |
Neg logit contributions | |
off | -0.001 |
two | -0.001 |
friends | -0.001 |
adoes | -0.001 |
our | -0.001 |
Token | The |
Token ID | 383 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
off | +0.001 |
friends | +0.001 |
adoes | +0.001 |
two | +0.001 |
what | +0.001 |
Neg logit contributions | |
ho | -0.001 |
solar | -0.001 |
ited | -0.001 |
mer | -0.001 |
generation | -0.001 |
Token | people |
Token ID | 661 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
two | +0.009 |
some | +0.009 |
off | +0.008 |
our | +0.008 |
friends | +0.008 |
Neg logit contributions | |
ho | -0.019 |
ited | -0.018 |
solar | -0.016 |
years | -0.016 |
mer | -0.016 |
Token | who |
Token ID | 508 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
ho | +0.010 |
ited | +0.010 |
solar | +0.009 |
mer | +0.009 |
lifetime | +0.008 |
Neg logit contributions | |
off | -0.005 |
two | -0.005 |
some | -0.005 |
our | -0.004 |
adoes | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
some | +0.014 |
off | +0.013 |
two | +0.013 |
what | +0.013 |
them | +0.012 |
Neg logit contributions | |
ho | -0.030 |
ited | -0.029 |
solar | -0.025 |
mer | -0.025 |
thank | -0.025 |
Token | hills |
Token ID | 18639 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
ho | +0.008 |
ited | +0.008 |
solar | +0.007 |
mer | +0.007 |
years | +0.007 |
Neg logit contributions | |
off | -0.003 |
two | -0.003 |
some | -0.003 |
friends | -0.002 |
our | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
off | +0.009 |
some | +0.007 |
the | +0.007 |
two | +0.007 |
on | +0.007 |
Neg logit contributions | |
ited | -0.030 |
ho | -0.029 |
solar | -0.028 |
years | -0.027 |
lifetime | -0.027 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
off | +0.003 |
two | +0.003 |
some | +0.002 |
what | +0.002 |
our | +0.002 |
Neg logit contributions | |
ho | -0.006 |
ited | -0.006 |
solar | -0.005 |
mer | -0.005 |
lifetime | -0.005 |
Token | P |
Token ID | 350 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ho | +0.046 |
ited | +0.044 |
solar | +0.040 |
epad | +0.040 |
thank | +0.040 |
Neg logit contributions | |
the | -0.012 |
two | -0.011 |
some | -0.011 |
on | -0.011 |
off | -0.010 |
Token | add |
Token ID | 2860 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
off | +0.029 |
two | +0.027 |
some | +0.027 |
our | +0.027 |
what | +0.026 |
Neg logit contributions | |
ho | -0.059 |
ited | -0.054 |
solar | -0.050 |
mer | -0.049 |
lifetime | -0.047 |
Token | ington |
Token ID | 9557 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
off | +0.130 |
two | +0.124 |
some | +0.123 |
our | +0.122 |
what | +0.120 |
Neg logit contributions | |
ho | -0.135 |
ited | -0.122 |
solar | -0.107 |
mer | -0.105 |
lifetime | -0.100 |
Token | went |
Token ID | 1816 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
friends | +0.007 |
two | +0.007 |
off | +0.007 |
some | +0.007 |
the | +0.007 |
Neg logit contributions | |
ho | -0.011 |
ited | -0.010 |
solar | -0.009 |
thank | -0.009 |
umm | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
ho | +0.012 |
ited | +0.010 |
mer | +0.010 |
solar | +0.010 |
lifetime | +0.009 |
Neg logit contributions | |
off | -0.006 |
adoes | -0.006 |
our | -0.006 |
cookies | -0.006 |
two | -0.006 |
Token | he |
Token ID | 339 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
ho | +0.006 |
ited | +0.006 |
solar | +0.005 |
mer | +0.005 |
lifetime | +0.005 |
Neg logit contributions | |
off | -0.002 |
some | -0.002 |
two | -0.002 |
what | -0.002 |
the | -0.002 |
Token | found |
Token ID | 1043 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
ho | +0.028 |
umm | +0.026 |
ited | +0.026 |
solar | +0.025 |
epad | +0.024 |
Neg logit contributions | |
the | -0.015 |
some | -0.015 |
two | -0.015 |
too | -0.014 |
on | -0.014 |
Token | caul |
Token ID | 46087 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
ho | +0.014 |
ited | +0.013 |
solar | +0.011 |
mer | +0.011 |
lifetime | +0.010 |
Neg logit contributions | |
off | -0.012 |
two | -0.012 |
some | -0.012 |
our | -0.011 |
friends | -0.011 |
Token | iflower |
Token ID | 42642 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
off | +0.028 |
two | +0.027 |
some | +0.026 |
our | +0.026 |
what | +0.025 |
Neg logit contributions | |
ho | -0.027 |
ited | -0.024 |
solar | -0.021 |
mer | -0.020 |
lifetime | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
off | +0.008 |
some | +0.007 |
two | +0.006 |
our | +0.006 |
friends | +0.006 |
Neg logit contributions | |
ho | -0.030 |
ited | -0.029 |
solar | -0.027 |
years | -0.026 |
mer | -0.026 |
Token | stopped |
Token ID | 5025 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
some | +0.001 |
off | +0.001 |
the | +0.001 |
two | +0.001 |
Spot | +0.001 |
Neg logit contributions | |
ho | -0.001 |
ited | -0.001 |
mer | -0.001 |
solar | -0.001 |
years | -0.001 |
Token | qu |
Token ID | 627 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
off | +0.004 |
adoes | +0.004 |
two | +0.004 |
Zip | +0.004 |
Buddy | +0.003 |
Neg logit contributions | |
ho | -0.007 |
ited | -0.006 |
solar | -0.005 |
years | -0.005 |
thank | -0.005 |
Token | arre |
Token ID | 9624 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
off | +0.057 |
our | +0.055 |
two | +0.055 |
some | +0.054 |
what | +0.054 |
Neg logit contributions | |
ho | -0.062 |
ited | -0.059 |
mer | -0.050 |
solar | -0.050 |
thank | -0.046 |
Token | ling |
Token ID | 1359 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
off | +0.118 |
two | +0.111 |
some | +0.110 |
our | +0.108 |
them | +0.105 |
Neg logit contributions | |
ho | -0.150 |
ited | -0.134 |
solar | -0.122 |
mer | -0.116 |
lifetime | -0.115 |
Token | . |
Token ID | 13 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
off | +0.034 |
some | +0.032 |
two | +0.030 |
them | +0.029 |
about | +0.028 |
Neg logit contributions | |
ho | -0.085 |
ited | -0.082 |
solar | -0.074 |
lifetime | -0.072 |
mer | -0.072 |
Token | They |
Token ID | 1119 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ho | +0.009 |
ited | +0.009 |
solar | +0.008 |
mer | +0.008 |
lifetime | +0.008 |
Neg logit contributions | |
off | -0.003 |
two | -0.003 |
some | -0.003 |
our | -0.003 |
what | -0.003 |
Token | said |
Token ID | 531 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
two | +0.005 |
the | +0.004 |
some | +0.004 |
all | +0.004 |
mom | +0.004 |
Neg logit contributions | |
ho | -0.007 |
mer | -0.007 |
ited | -0.007 |
umm | -0.007 |
lifetime | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -7.87e-02 |
Pos logit contributions | |
off | +0.004 |
two | +0.004 |
adoes | +0.004 |
some | +0.004 |
our | +0.004 |
Neg logit contributions | |
ho | -0.010 |
ited | -0.008 |
solar | -0.008 |
mer | -0.007 |
lifetime | -0.007 |
Token | but |
Token ID | 475 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
ho | +0.022 |
ited | +0.021 |
solar | +0.019 |
mer | +0.019 |
lifetime | +0.018 |
Neg logit contributions | |
off | -0.007 |
two | -0.007 |
some | -0.007 |
our | -0.006 |
what | -0.006 |
Token | today |
Token ID | 1909 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
ho | +0.026 |
ited | +0.025 |
solar | +0.023 |
mer | +0.022 |
lifetime | +0.022 |
Neg logit contributions | |
off | -0.011 |
two | -0.010 |
some | -0.010 |
our | -0.010 |
what | -0.010 |
Token | they |
Token ID | 484 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
ho | +0.035 |
ited | +0.032 |
solar | +0.030 |
mer | +0.029 |
lifetime | +0.029 |
Neg logit contributions | |
off | -0.011 |
two | -0.011 |
some | -0.010 |
our | -0.010 |
what | -0.010 |
Token | were |
Token ID | 547 |
Feature activation | +9.31e-04 |
Pos logit contributions | |
ho | +0.008 |
ited | +0.008 |
solar | +0.007 |
lifetime | +0.007 |
mer | +0.007 |
Neg logit contributions | |
off | -0.007 |
two | -0.007 |
some | -0.007 |
them | -0.007 |
what | -0.007 |
Token | qu |
Token ID | 627 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
off | +0.000 |
adoes | +0.000 |
our | +0.000 |
some | +0.000 |
two | +0.000 |
Neg logit contributions | |
ho | -0.000 |
ited | -0.000 |
solar | -0.000 |
mer | -0.000 |
years | -0.000 |
Token | arre |
Token ID | 9624 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
off | +0.045 |
our | +0.044 |
what | +0.043 |
some | +0.043 |
Spot | +0.043 |
Neg logit contributions | |
ited | -0.067 |
ho | -0.066 |
mer | -0.058 |
solar | -0.056 |
years | -0.055 |
Token | ling |
Token ID | 1359 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
off | +0.128 |
two | +0.122 |
some | +0.121 |
our | +0.119 |
what | +0.117 |
Neg logit contributions | |
ho | -0.136 |
ited | -0.122 |
solar | -0.109 |
mer | -0.105 |
lifetime | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | +6.23e-02 |
Pos logit contributions | |
off | +0.026 |
two | +0.024 |
some | +0.024 |
our | +0.023 |
what | +0.022 |
Neg logit contributions | |
ho | -0.078 |
ited | -0.073 |
solar | -0.067 |
mer | -0.065 |
lifetime | -0.065 |
Token | Jenna |
Token ID | 45377 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
off | +0.001 |
two | +0.001 |
some | +0.001 |
our | +0.001 |
what | +0.001 |
Neg logit contributions | |
ho | -0.003 |
ited | -0.003 |
solar | -0.003 |
mer | -0.003 |
lifetime | -0.003 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ho | +0.016 |
ited | +0.015 |
solar | +0.014 |
years | +0.014 |
lifetime | +0.013 |
Neg logit contributions | |
off | -0.010 |
two | -0.010 |
some | -0.010 |
the | -0.009 |
them | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
ho | +0.008 |
ited | +0.007 |
solar | +0.007 |
years | +0.007 |
mer | +0.007 |
Neg logit contributions | |
adoes | -0.003 |
ags | -0.003 |
off | -0.003 |
snowball | -0.002 |
uate | -0.002 |
Token | They |
Token ID | 2990 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
ho | +0.000 |
ited | +0.000 |
solar | +0.000 |
mer | +0.000 |
years | +0.000 |
Neg logit contributions | |
off | -0.000 |
adoes | -0.000 |
about | -0.000 |
icles | -0.000 |
some | -0.000 |
Token | are |
Token ID | 389 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
off | +0.007 |
two | +0.006 |
some | +0.006 |
what | +0.006 |
our | +0.006 |
Neg logit contributions | |
ho | -0.014 |
ited | -0.013 |
mer | -0.012 |
solar | -0.012 |
lifetime | -0.012 |
Token | tired |
Token ID | 10032 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
icles | +0.005 |
icle | +0.004 |
adoes | +0.004 |
Zip | +0.004 |
off | +0.004 |
Neg logit contributions | |
ho | -0.006 |
wished | -0.006 |
wil | -0.005 |
solar | -0.005 |
ited | -0.005 |
Token | from |
Token ID | 422 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
off | +0.004 |
two | +0.003 |
some | +0.003 |
our | +0.003 |
what | +0.003 |
Neg logit contributions | |
ho | -0.018 |
ited | -0.017 |
solar | -0.016 |
mer | -0.015 |
lifetime | -0.015 |
Token | qu |
Token ID | 627 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
off | +0.002 |
adoes | +0.002 |
two | +0.002 |
uate | +0.002 |
icles | +0.002 |
Neg logit contributions | |
ho | -0.006 |
solar | -0.005 |
ited | -0.005 |
wished | -0.005 |
years | -0.005 |
Token | arre |
Token ID | 9624 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
Kitty | +0.060 |
Spot | +0.059 |
Zip | +0.059 |
Mark | +0.058 |
what | +0.057 |
Neg logit contributions | |
ited | -0.051 |
ho | -0.049 |
mer | -0.042 |
solar | -0.039 |
aciously | -0.035 |
Token | ling |
Token ID | 1359 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
off | +0.122 |
Spot | +0.120 |
two | +0.118 |
Zip | +0.117 |
some | +0.117 |
Neg logit contributions | |
ho | -0.133 |
ited | -0.125 |
mer | -0.110 |
solar | -0.105 |
thank | -0.099 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
off | +0.030 |
two | +0.028 |
some | +0.028 |
our | +0.028 |
what | +0.027 |
Neg logit contributions | |
ho | -0.060 |
ited | -0.055 |
solar | -0.051 |
mer | -0.050 |
lifetime | -0.048 |
Token | They |
Token ID | 1119 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
off | +0.003 |
what | +0.003 |
friends | +0.003 |
two | +0.003 |
cookies | +0.003 |
Neg logit contributions | |
ho | -0.005 |
solar | -0.005 |
ited | -0.005 |
mer | -0.004 |
wished | -0.004 |
Token | sit |
Token ID | 1650 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
off | +0.006 |
two | +0.006 |
some | +0.005 |
what | +0.005 |
our | +0.005 |
Neg logit contributions | |
ho | -0.012 |
ited | -0.011 |
mer | -0.010 |
solar | -0.010 |
lifetime | -0.010 |
Token | in |
Token ID | 287 |
Feature activation | -9.55e-02 |
Pos logit contributions | |
ho | +0.014 |
ited | +0.012 |
mer | +0.012 |
solar | +0.012 |
years | +0.011 |
Neg logit contributions | |
Zip | -0.003 |
Buddy | -0.003 |
Mark | -0.003 |
Kitty | -0.003 |
off | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
off | +0.007 |
two | +0.007 |
our | +0.007 |
some | +0.007 |
adoes | +0.006 |
Neg logit contributions | |
ho | -0.016 |
ited | -0.015 |
solar | -0.013 |
mer | -0.013 |
lifetime | -0.013 |
Token | their |
Token ID | 511 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
off | +0.021 |
two | +0.019 |
some | +0.018 |
our | +0.018 |
what | +0.017 |
Neg logit contributions | |
ho | -0.062 |
ited | -0.058 |
solar | -0.054 |
mer | -0.053 |
lifetime | -0.052 |
Token | children |
Token ID | 1751 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
two | +0.008 |
off | +0.008 |
friends | +0.008 |
some | +0.008 |
mom | +0.007 |
Neg logit contributions | |
ho | -0.026 |
ited | -0.026 |
solar | -0.023 |
mer | -0.023 |
lifetime | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +8.84e-02 |
Pos logit contributions | |
off | +0.010 |
two | +0.009 |
some | +0.009 |
our | +0.009 |
what | +0.009 |
Neg logit contributions | |
ho | -0.021 |
ited | -0.019 |
solar | -0.018 |
mer | -0.017 |
lifetime | -0.017 |
Token | qu |
Token ID | 627 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
off | +0.002 |
our | +0.002 |
two | +0.002 |
some | +0.002 |
adoes | +0.002 |
Neg logit contributions | |
ho | -0.005 |
ited | -0.004 |
solar | -0.004 |
mer | -0.004 |
lifetime | -0.004 |
Token | arre |
Token ID | 9624 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
Spot | +0.055 |
some | +0.054 |
what | +0.054 |
mom | +0.053 |
off | +0.053 |
Neg logit contributions | |
ited | -0.046 |
ho | -0.044 |
mer | -0.037 |
solar | -0.035 |
years | -0.035 |
Token | ling |
Token ID | 1359 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Spot | +0.133 |
Zip | +0.130 |
Rex | +0.129 |
off | +0.129 |
two | +0.128 |
Neg logit contributions | |
ho | -0.121 |
ited | -0.117 |
mer | -0.101 |
solar | -0.093 |
ad | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
off | +0.028 |
two | +0.026 |
our | +0.026 |
some | +0.025 |
what | +0.025 |
Neg logit contributions | |
ho | -0.064 |
ited | -0.058 |
solar | -0.054 |
mer | -0.054 |
lifetime | -0.051 |
Token | |
Token ID | 220 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
off | +0.020 |
ags | +0.018 |
adoes | +0.018 |
our | +0.017 |
uate | +0.017 |
Neg logit contributions | |
ho | -0.030 |
solar | -0.026 |
ited | -0.026 |
mer | -0.024 |
lifetime | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
off | +0.006 |
adoes | +0.006 |
cookies | +0.005 |
my | +0.005 |
our | +0.005 |
Neg logit contributions | |
ho | -0.009 |
solar | -0.007 |
mer | -0.007 |
ited | -0.007 |
commented | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
off | +0.024 |
adoes | +0.024 |
ags | +0.022 |
dogs | +0.021 |
cookies | +0.021 |
Neg logit contributions | |
ho | -0.051 |
ited | -0.046 |
solar | -0.044 |
mer | -0.043 |
lifetime | -0.043 |
Token | together |
Token ID | 1978 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
off | +0.003 |
some | +0.003 |
two | +0.003 |
our | +0.003 |
what | +0.003 |
Neg logit contributions | |
ho | -0.010 |
ited | -0.009 |
solar | -0.009 |
mer | -0.008 |
lifetime | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
ho | +0.007 |
ited | +0.007 |
solar | +0.006 |
years | +0.006 |
lifetime | +0.006 |
Neg logit contributions | |
off | -0.002 |
on | -0.002 |
some | -0.002 |
about | -0.002 |
them | -0.002 |
Token | They |
Token ID | 1119 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
off | +0.003 |
our | +0.003 |
adoes | +0.003 |
cookies | +0.003 |
two | +0.002 |
Neg logit contributions | |
ho | -0.006 |
ited | -0.005 |
solar | -0.005 |
mer | -0.005 |
lifetime | -0.005 |
Token | never |
Token ID | 1239 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
ho | +0.007 |
ited | +0.006 |
mer | +0.006 |
solar | +0.006 |
lifetime | +0.006 |
Neg logit contributions | |
off | -0.005 |
two | -0.005 |
some | -0.004 |
over | -0.004 |
the | -0.004 |
Token | qu |
Token ID | 627 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
off | +0.016 |
two | +0.015 |
over | +0.015 |
some | +0.015 |
what | +0.015 |
Neg logit contributions | |
ho | -0.019 |
solar | -0.017 |
ited | -0.016 |
mer | -0.016 |
lifetime | -0.016 |
Token | arre |
Token ID | 9624 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
mom | +0.050 |
our | +0.047 |
off | +0.047 |
what | +0.047 |
Spot | +0.046 |
Neg logit contributions | |
ited | -0.054 |
ho | -0.050 |
mer | -0.046 |
years | -0.043 |
solar | -0.043 |
Token | led |
Token ID | 992 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
off | +0.146 |
two | +0.143 |
some | +0.142 |
Spot | +0.142 |
our | +0.141 |
Neg logit contributions | |
ho | -0.108 |
ited | -0.102 |
mer | -0.086 |
solar | -0.082 |
years | -0.077 |
Token | again |
Token ID | 757 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
off | +0.011 |
some | +0.010 |
two | +0.009 |
our | +0.009 |
what | +0.009 |
Neg logit contributions | |
ho | -0.043 |
ited | -0.040 |
solar | -0.038 |
mer | -0.036 |
lifetime | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
off | +0.005 |
two | +0.004 |
some | +0.004 |
what | +0.004 |
friends | +0.004 |
Neg logit contributions | |
ho | -0.022 |
ited | -0.021 |
solar | -0.020 |
years | -0.019 |
mer | -0.019 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
off | +0.005 |
adoes | +0.004 |
two | +0.004 |
our | +0.004 |
some | +0.004 |
Neg logit contributions | |
ho | -0.011 |
ited | -0.010 |
solar | -0.009 |
mer | -0.009 |
lifetime | -0.009 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
off | +0.007 |
our | +0.006 |
two | +0.006 |
some | +0.006 |
adoes | +0.006 |
Neg logit contributions | |
ho | -0.017 |
ited | -0.016 |
solar | -0.015 |
mer | -0.015 |
lifetime | -0.014 |
Token | said |
Token ID | 531 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
off | +0.004 |
two | +0.004 |
some | +0.004 |
what | +0.004 |
on | +0.004 |
Neg logit contributions | |
ho | -0.009 |
ited | -0.008 |
solar | -0.008 |
mer | -0.007 |
years | -0.007 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
off | +0.008 |
some | +0.008 |
two | +0.007 |
what | +0.007 |
about | +0.007 |
Neg logit contributions | |
ho | -0.025 |
ited | -0.024 |
solar | -0.022 |
mer | -0.022 |
lifetime | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
ho | +0.010 |
ited | +0.010 |
solar | +0.009 |
mer | +0.009 |
years | +0.009 |
Neg logit contributions | |
off | -0.003 |
some | -0.002 |
two | -0.002 |
our | -0.002 |
about | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
off | +0.002 |
two | +0.002 |
some | +0.002 |
our | +0.002 |
adoes | +0.002 |
Neg logit contributions | |
ho | -0.007 |
ited | -0.007 |
solar | -0.006 |
mer | -0.006 |
lifetime | -0.006 |
Token | g |
Token ID | 308 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
two | +0.008 |
off | +0.008 |
some | +0.008 |
our | +0.008 |
friends | +0.008 |
Neg logit contributions | |
ho | -0.016 |
ited | -0.015 |
solar | -0.014 |
mer | -0.013 |
years | -0.013 |
Token | az |
Token ID | 1031 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
off | +0.048 |
two | +0.046 |
some | +0.045 |
our | +0.045 |
what | +0.044 |
Neg logit contributions | |
ho | -0.065 |
ited | -0.059 |
solar | -0.053 |
mer | -0.052 |
lifetime | -0.050 |
Token | eb |
Token ID | 1765 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
off | +0.100 |
two | +0.094 |
some | +0.093 |
our | +0.091 |
them | +0.090 |
Neg logit contributions | |
ho | -0.160 |
ited | -0.148 |
solar | -0.137 |
mer | -0.130 |
lifetime | -0.129 |
Token | o |
Token ID | 78 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
off | +0.080 |
two | +0.076 |
some | +0.075 |
our | +0.074 |
what | +0.073 |
Neg logit contributions | |
ho | -0.101 |
ited | -0.093 |
solar | -0.084 |
mer | -0.081 |
lifetime | -0.078 |
Token | and |
Token ID | 290 |
Feature activation | -8.58e-02 |
Pos logit contributions | |
off | +0.038 |
two | +0.035 |
some | +0.034 |
our | +0.033 |
what | +0.032 |
Neg logit contributions | |
ho | -0.095 |
ited | -0.088 |
solar | -0.082 |
mer | -0.079 |
lifetime | -0.077 |
Token | went |
Token ID | 1816 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ho | +0.004 |
ited | +0.004 |
solar | +0.003 |
mer | +0.003 |
years | +0.003 |
Neg logit contributions | |
off | -0.003 |
two | -0.003 |
some | -0.003 |
our | -0.003 |
Spot | -0.002 |
Token | back |
Token ID | 736 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
adoes | +0.003 |
asuring | +0.003 |
two | +0.003 |
our | +0.003 |
Zip | +0.003 |
Neg logit contributions | |
ho | -0.009 |
ited | -0.008 |
solar | -0.008 |
lifetime | -0.008 |
mer | -0.008 |
Token | ? |
Token ID | 30 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
off | +0.019 |
adoes | +0.018 |
Zip | +0.018 |
snowball | +0.017 |
two | +0.017 |
Neg logit contributions | |
ho | -0.048 |
ited | -0.044 |
mer | -0.042 |
solar | -0.041 |
thank | -0.040 |
Token | Why |
Token ID | 4162 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
ho | +0.015 |
solar | +0.013 |
ited | +0.013 |
mer | +0.012 |
years | +0.012 |
Neg logit contributions | |
off | -0.011 |
ags | -0.010 |
friends | -0.010 |
adoes | -0.010 |
our | -0.010 |
Token | are |
Token ID | 389 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
off | +0.012 |
ags | +0.011 |
snowball | +0.010 |
Zip | +0.010 |
some | +0.010 |
Neg logit contributions | |
ho | -0.012 |
ited | -0.010 |
solar | -0.010 |
mer | -0.009 |
wished | -0.009 |
Token | you |
Token ID | 345 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
ags | +0.016 |
snowball | +0.016 |
< | +0.014 |
adoes | +0.014 |
off | +0.014 |
Neg logit contributions | |
ho | -0.019 |
years | -0.016 |
solar | -0.014 |
wished | -0.014 |
ited | -0.014 |
Token | qu |
Token ID | 627 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ags | +0.008 |
Zip | +0.008 |
cookies | +0.008 |
off | +0.008 |
adoes | +0.008 |
Neg logit contributions | |
ho | -0.014 |
ited | -0.012 |
solar | -0.011 |
mer | -0.011 |
years | -0.011 |
Token | arre |
Token ID | 9624 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
Spot | +0.046 |
off | +0.045 |
mom | +0.045 |
our | +0.045 |
Zip | +0.045 |
Neg logit contributions | |
ited | -0.053 |
ho | -0.050 |
mer | -0.044 |
solar | -0.042 |
years | -0.041 |
Token | ling |
Token ID | 1359 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Spot | +0.138 |
Rex | +0.135 |
Zip | +0.135 |
mom | +0.133 |
off | +0.131 |
Neg logit contributions | |
ited | -0.111 |
ho | -0.110 |
mer | -0.096 |
solar | -0.086 |
thank | -0.084 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Zip | +0.021 |
off | +0.020 |
snowball | +0.019 |
Spot | +0.019 |
two | +0.019 |
Neg logit contributions | |
ho | -0.055 |
ited | -0.049 |
mer | -0.049 |
solar | -0.048 |
thank | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
ho | +0.007 |
ited | +0.006 |
solar | +0.006 |
years | +0.006 |
mer | +0.005 |
Neg logit contributions | |
off | -0.003 |
adoes | -0.003 |
our | -0.003 |
two | -0.003 |
dogs | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
adoes | +0.007 |
off | +0.007 |
dogs | +0.006 |
cookies | +0.006 |
about | +0.006 |
Neg logit contributions | |
ho | -0.014 |
ited | -0.012 |
solar | -0.012 |
mer | -0.011 |
lifetime | -0.011 |
Token | The |
Token ID | 464 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
off | +0.003 |
about | +0.003 |
some | +0.003 |
what | +0.003 |
adoes | +0.003 |
Neg logit contributions | |
ho | -0.007 |
ited | -0.007 |
solar | -0.006 |
mer | -0.006 |
years | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
ags | +0.003 |
off | +0.003 |
uate | +0.002 |
< | +0.002 |
cookies | +0.002 |
Neg logit contributions | |
ho | -0.005 |
mer | -0.004 |
solar | -0.004 |
ited | -0.004 |
yt | -0.004 |
Token | why |
Token ID | 1521 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
ags | +0.002 |
off | +0.002 |
< | +0.002 |
uate | +0.002 |
adoes | +0.002 |
Neg logit contributions | |
ho | -0.004 |
solar | -0.003 |
mer | -0.003 |
ad | -0.003 |
wished | -0.003 |
Token | are |
Token ID | 389 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
ho | +0.021 |
solar | +0.017 |
ited | +0.017 |
mer | +0.016 |
ad | +0.016 |
Neg logit contributions | |
ags | -0.014 |
off | -0.013 |
< | -0.012 |
some | -0.012 |
snowball | -0.012 |
Token | you |
Token ID | 345 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
ags | +0.007 |
snowball | +0.007 |
< | +0.006 |
adoes | +0.006 |
off | +0.006 |
Neg logit contributions | |
ho | -0.009 |
years | -0.007 |
solar | -0.007 |
wished | -0.007 |
seaw | -0.007 |
Token | qu |
Token ID | 627 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Zip | +0.015 |
off | +0.014 |
adoes | +0.014 |
cookies | +0.014 |
some | +0.014 |
Neg logit contributions | |
ho | -0.026 |
ited | -0.022 |
solar | -0.021 |
mer | -0.021 |
years | -0.020 |
Token | arre |
Token ID | 9624 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
Spot | +0.044 |
off | +0.044 |
mom | +0.043 |
what | +0.043 |
some | +0.043 |
Neg logit contributions | |
ited | -0.057 |
ho | -0.055 |
mer | -0.049 |
solar | -0.045 |
years | -0.044 |
Token | ling |
Token ID | 1359 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Spot | +0.130 |
off | +0.128 |
Zip | +0.127 |
Rex | +0.127 |
mom | +0.126 |
Neg logit contributions | |
ho | -0.119 |
ited | -0.116 |
mer | -0.101 |
solar | -0.092 |
thank | -0.089 |
Token | ?" |
Token ID | 1701 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
Zip | +0.021 |
off | +0.021 |
two | +0.020 |
cookies | +0.020 |
Spot | +0.020 |
Neg logit contributions | |
ho | -0.056 |
ited | -0.050 |
mer | -0.049 |
solar | -0.049 |
thank | -0.045 |
Token | But |
Token ID | 887 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
ho | +0.026 |
ited | +0.023 |
solar | +0.021 |
mer | +0.021 |
lifetime | +0.020 |
Neg logit contributions | |
off | -0.014 |
adoes | -0.013 |
our | -0.013 |
two | -0.012 |
my | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
ho | +0.014 |
ited | +0.012 |
mer | +0.012 |
solar | +0.011 |
years | +0.011 |
Neg logit contributions | |
ags | -0.003 |
off | -0.003 |
cookies | -0.003 |
adoes | -0.003 |
our | -0.003 |
Token | birds |
Token ID | 10087 |
Feature activation | -6.98e-02 |
Pos logit contributions | |
ho | +0.001 |
ited | +0.001 |
solar | +0.001 |
mer | +0.001 |
lifetime | +0.001 |
Neg logit contributions | |
off | -0.000 |
our | -0.000 |
some | -0.000 |
two | -0.000 |
what | -0.000 |
Token | ? |
Token ID | 30 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
off | +0.019 |
two | +0.018 |
some | +0.017 |
our | +0.017 |
what | +0.016 |
Neg logit contributions | |
ho | -0.049 |
ited | -0.045 |
solar | -0.042 |
mer | -0.041 |
lifetime | -0.040 |
Token | Why |
Token ID | 4162 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
ho | +0.011 |
ited | +0.009 |
solar | +0.009 |
mer | +0.009 |
years | +0.008 |
Neg logit contributions | |
off | -0.007 |
two | -0.006 |
friends | -0.006 |
some | -0.006 |
them | -0.006 |
Token | are |
Token ID | 389 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
off | +0.015 |
ags | +0.014 |
adoes | +0.013 |
snowball | +0.013 |
Zip | +0.013 |
Neg logit contributions | |
ho | -0.012 |
ited | -0.010 |
solar | -0.010 |
wished | -0.009 |
mer | -0.009 |
Token | you |
Token ID | 345 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
snowball | +0.023 |
ags | +0.023 |
adoes | +0.022 |
over | +0.021 |
off | +0.021 |
Neg logit contributions | |
ho | -0.023 |
years | -0.018 |
wished | -0.017 |
solar | -0.017 |
cuc | -0.016 |
Token | qu |
Token ID | 627 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
adoes | +0.011 |
off | +0.011 |
Zip | +0.011 |
ags | +0.010 |
Buddy | +0.010 |
Neg logit contributions | |
ho | -0.016 |
years | -0.013 |
ited | -0.013 |
wishing | -0.012 |
commented | -0.012 |
Token | arre |
Token ID | 9624 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
off | +0.038 |
Zip | +0.037 |
our | +0.037 |
Spot | +0.037 |
some | +0.037 |
Neg logit contributions | |
ited | -0.052 |
ho | -0.050 |
mer | -0.043 |
solar | -0.042 |
years | -0.041 |
Token | ling |
Token ID | 1359 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Spot | +0.130 |
Zip | +0.129 |
off | +0.126 |
Rex | +0.126 |
Buddy | +0.126 |
Neg logit contributions | |
ho | -0.115 |
ited | -0.114 |
mer | -0.100 |
solar | -0.092 |
thank | -0.088 |
Token | with |
Token ID | 351 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
off | +0.024 |
two | +0.023 |
Zip | +0.022 |
some | +0.021 |
adoes | +0.021 |
Neg logit contributions | |
ho | -0.056 |
ited | -0.051 |
solar | -0.049 |
mer | -0.048 |
thank | -0.045 |
Token | your |
Token ID | 534 |
Feature activation | +9.79e-02 |
Pos logit contributions | |
ho | +0.017 |
ited | +0.016 |
solar | +0.015 |
years | +0.015 |
wil | +0.014 |
Neg logit contributions | |
off | -0.005 |
Zip | -0.004 |
adoes | -0.004 |
< | -0.004 |
about | -0.004 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
off | +0.003 |
two | +0.002 |
some | +0.002 |
our | +0.002 |
what | +0.002 |
Neg logit contributions | |
ho | -0.005 |
ited | -0.005 |
solar | -0.004 |
mer | -0.004 |
lifetime | -0.004 |
Token | ? |
Token ID | 30 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
ho | +0.017 |
ited | +0.016 |
solar | +0.014 |
mer | +0.014 |
thank | +0.014 |
Neg logit contributions | |
off | -0.006 |
Zip | -0.005 |
two | -0.005 |
adoes | -0.005 |
some | -0.005 |
Token | on |
Token ID | 319 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
adoes | +0.000 |
off | +0.000 |
some | +0.000 |
our | +0.000 |
what | +0.000 |
Neg logit contributions | |
ho | -0.003 |
ited | -0.003 |
solar | -0.003 |
mer | -0.003 |
years | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
off | +0.003 |
two | +0.002 |
some | +0.002 |
adoes | +0.002 |
what | +0.002 |
Neg logit contributions | |
ho | -0.005 |
ited | -0.005 |
solar | -0.005 |
mer | -0.004 |
lifetime | -0.004 |
Token | they |
Token ID | 484 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
off | +0.008 |
two | +0.007 |
some | +0.007 |
our | +0.006 |
what | +0.006 |
Neg logit contributions | |
ho | -0.027 |
ited | -0.025 |
solar | -0.023 |
mer | -0.023 |
lifetime | -0.022 |
Token | never |
Token ID | 1239 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
ho | +0.002 |
ited | +0.002 |
mer | +0.001 |
lifetime | +0.001 |
umm | +0.001 |
Neg logit contributions | |
the | -0.001 |
off | -0.001 |
two | -0.001 |
them | -0.001 |
on | -0.001 |
Token | qu |
Token ID | 627 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
off | +0.016 |
two | +0.015 |
the | +0.015 |
some | +0.015 |
over | +0.015 |
Neg logit contributions | |
ho | -0.021 |
solar | -0.019 |
ited | -0.019 |
mer | -0.018 |
lifetime | -0.018 |
Token | arre |
Token ID | 9624 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
mom | +0.042 |
off | +0.042 |
our | +0.042 |
what | +0.042 |
Spot | +0.041 |
Neg logit contributions | |
ited | -0.056 |
ho | -0.053 |
mer | -0.047 |
years | -0.045 |
solar | -0.045 |
Token | led |
Token ID | 992 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
off | +0.141 |
two | +0.136 |
some | +0.135 |
our | +0.134 |
what | +0.132 |
Neg logit contributions | |
ho | -0.111 |
ited | -0.102 |
solar | -0.086 |
mer | -0.085 |
lifetime | -0.079 |
Token | again |
Token ID | 757 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
off | +0.009 |
some | +0.008 |
two | +0.008 |
our | +0.007 |
what | +0.007 |
Neg logit contributions | |
ho | -0.039 |
ited | -0.037 |
solar | -0.034 |
lifetime | -0.033 |
mer | -0.033 |
Token | over |
Token ID | 625 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
some | +0.006 |
off | +0.006 |
friends | +0.005 |
the | +0.005 |
two | +0.005 |
Neg logit contributions | |
ho | -0.024 |
ited | -0.023 |
solar | -0.021 |
years | -0.020 |
mer | -0.020 |
Token | clothes |
Token ID | 8242 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
some | +0.002 |
two | +0.001 |
the | +0.001 |
them | +0.001 |
off | +0.001 |
Neg logit contributions | |
ho | -0.012 |
ited | -0.012 |
solar | -0.011 |
mer | -0.010 |
lifetime | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ho | +0.025 |
ited | +0.025 |
solar | +0.024 |
years | +0.023 |
lifetime | +0.022 |
Neg logit contributions | |
off | -0.004 |
on | -0.003 |
too | -0.003 |
some | -0.003 |
about | -0.003 |
Token | sund |
Token ID | 37437 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
ho | +0.002 |
ited | +0.002 |
solar | +0.002 |
mer | +0.002 |
years | +0.002 |
Neg logit contributions | |
off | -0.001 |
two | -0.001 |
some | -0.001 |
our | -0.001 |
what | -0.001 |
Token | ae |
Token ID | 3609 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
off | +0.008 |
two | +0.008 |
some | +0.008 |
our | +0.008 |
friends | +0.008 |
Neg logit contributions | |
ho | -0.010 |
ited | -0.009 |
solar | -0.008 |
mer | -0.008 |
years | -0.007 |
Token | with |
Token ID | 351 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
off | +0.003 |
our | +0.003 |
adoes | +0.003 |
two | +0.003 |
Buddy | +0.003 |
Neg logit contributions | |
ho | -0.008 |
ited | -0.008 |
solar | -0.007 |
mer | -0.007 |
lifetime | -0.007 |
Token | lots |
Token ID | 6041 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
ho | +0.051 |
ited | +0.049 |
mer | +0.048 |
solar | +0.045 |
lifetime | +0.044 |
Neg logit contributions | |
two | -0.008 |
some | -0.008 |
off | -0.006 |
the | -0.006 |
them | -0.005 |
Token | of |
Token ID | 286 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
ho | +0.007 |
ited | +0.006 |
solar | +0.006 |
mer | +0.006 |
lifetime | +0.006 |
Neg logit contributions | |
off | -0.001 |
two | -0.001 |
some | -0.001 |
about | -0.001 |
what | -0.000 |
Token | topp |
Token ID | 23126 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
off | +0.014 |
adoes | +0.014 |
our | +0.013 |
Buddy | +0.013 |
Zip | +0.012 |
Neg logit contributions | |
ho | -0.030 |
ited | -0.029 |
solar | -0.025 |
mer | -0.025 |
thank | -0.024 |
Token | ings |
Token ID | 654 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
off | +0.110 |
two | +0.105 |
some | +0.104 |
our | +0.103 |
what | +0.102 |
Neg logit contributions | |
ho | -0.145 |
ited | -0.128 |
solar | -0.113 |
mer | -0.113 |
lifetime | -0.106 |
Token | . |
Token ID | 13 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
ho | +0.009 |
ited | +0.009 |
solar | +0.008 |
mer | +0.008 |
lifetime | +0.007 |
Neg logit contributions | |
off | -0.004 |
two | -0.004 |
some | -0.004 |
our | -0.004 |
what | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
ho | +0.002 |
ited | +0.002 |
solar | +0.002 |
mer | +0.002 |
lifetime | +0.002 |
Neg logit contributions | |
off | -0.001 |
our | -0.001 |
two | -0.001 |
some | -0.001 |
what | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
off | +0.005 |
adoes | +0.005 |
our | +0.004 |
two | +0.004 |
some | +0.004 |
Neg logit contributions | |
ho | -0.012 |
ited | -0.010 |
solar | -0.010 |
mer | -0.010 |
lifetime | -0.009 |
Token | They |
Token ID | 2990 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
off | +0.002 |
two | +0.002 |
some | +0.002 |
our | +0.002 |
adoes | +0.002 |
Neg logit contributions | |
ho | -0.003 |
ited | -0.003 |
solar | -0.003 |
mer | -0.003 |
lifetime | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -7.89e-03 |
Pos logit contributions | |
off | +0.000 |
two | +0.000 |
some | +0.000 |
on | +0.000 |
them | +0.000 |
Neg logit contributions | |
ho | -0.001 |
ited | -0.001 |
solar | -0.001 |
lifetime | -0.001 |
years | -0.001 |
Token | The |
Token ID | 383 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
ho | +0.000 |
ited | +0.000 |
solar | +0.000 |
mer | +0.000 |
lifetime | +0.000 |
Neg logit contributions | |
off | -0.000 |
our | -0.000 |
adoes | -0.000 |
two | -0.000 |
some | -0.000 |
Token | bears |
Token ID | 13062 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
ho | +0.001 |
ited | +0.001 |
solar | +0.001 |
mer | +0.001 |
thank | +0.001 |
Neg logit contributions | |
two | -0.001 |
friends | -0.001 |
mom | -0.001 |
kids | -0.001 |
some | -0.001 |
Token | stopped |
Token ID | 5025 |
Feature activation | +7.00e-02 |
Pos logit contributions | |
off | +0.031 |
two | +0.030 |
some | +0.029 |
what | +0.028 |
them | +0.028 |
Neg logit contributions | |
ho | -0.036 |
ited | -0.033 |
solar | -0.030 |
mer | -0.029 |
lifetime | -0.029 |
Token | qu |
Token ID | 627 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
off | +0.002 |
adoes | +0.002 |
cookies | +0.002 |
two | +0.002 |
ags | +0.002 |
Neg logit contributions | |
ho | -0.004 |
ited | -0.003 |
solar | -0.003 |
mer | -0.003 |
years | -0.003 |
Token | arre |
Token ID | 9624 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
mom | +0.052 |
what | +0.052 |
our | +0.052 |
Spot | +0.052 |
off | +0.051 |
Neg logit contributions | |
ited | -0.049 |
ho | -0.048 |
mer | -0.040 |
years | -0.036 |
solar | -0.036 |
Token | ling |
Token ID | 1359 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
off | +0.121 |
two | +0.119 |
Spot | +0.118 |
some | +0.118 |
our | +0.117 |
Neg logit contributions | |
ho | -0.127 |
ited | -0.119 |
mer | -0.103 |
solar | -0.099 |
thank | -0.093 |
Token | and |
Token ID | 290 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
off | +0.019 |
two | +0.017 |
some | +0.016 |
our | +0.016 |
what | +0.014 |
Neg logit contributions | |
ho | -0.094 |
ited | -0.088 |
solar | -0.082 |
mer | -0.081 |
lifetime | -0.079 |
Token | asked |
Token ID | 1965 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
off | +0.007 |
two | +0.007 |
some | +0.006 |
our | +0.006 |
what | +0.006 |
Neg logit contributions | |
ho | -0.009 |
ited | -0.008 |
solar | -0.008 |
mer | -0.007 |
lifetime | -0.007 |
Token | him |
Token ID | 683 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
off | +0.004 |
two | +0.004 |
some | +0.004 |
our | +0.004 |
what | +0.003 |
Neg logit contributions | |
ho | -0.015 |
ited | -0.014 |
solar | -0.013 |
mer | -0.012 |
lifetime | -0.012 |
Token | for |
Token ID | 329 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
ags | +0.004 |
adoes | +0.003 |
off | +0.003 |
uate | +0.003 |
our | +0.003 |
Neg logit contributions | |
ho | -0.009 |
ited | -0.008 |
solar | -0.007 |
mer | -0.007 |
years | -0.007 |
Token | walking |
Token ID | 6155 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
off | +0.019 |
adoes | +0.017 |
our | +0.017 |
some | +0.017 |
two | +0.017 |
Neg logit contributions | |
ho | -0.030 |
ited | -0.028 |
solar | -0.025 |
mer | -0.024 |
years | -0.024 |
Token | by |
Token ID | 416 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
off | +0.006 |
some | +0.006 |
two | +0.005 |
them | +0.005 |
on | +0.005 |
Neg logit contributions | |
ho | -0.025 |
ited | -0.024 |
solar | -0.022 |
lifetime | -0.022 |
mer | -0.021 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
off | +0.009 |
two | +0.008 |
our | +0.008 |
some | +0.008 |
adoes | +0.007 |
Neg logit contributions | |
ho | -0.036 |
ited | -0.033 |
mer | -0.030 |
solar | -0.030 |
years | -0.029 |
Token | them |
Token ID | 606 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
off | +0.009 |
two | +0.006 |
our | +0.005 |
some | +0.005 |
adoes | +0.005 |
Neg logit contributions | |
ho | -0.097 |
ited | -0.090 |
solar | -0.085 |
mer | -0.083 |
years | -0.082 |
Token | qu |
Token ID | 627 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
off | +0.013 |
two | +0.012 |
our | +0.012 |
some | +0.011 |
adoes | +0.011 |
Neg logit contributions | |
ho | -0.040 |
ited | -0.037 |
solar | -0.034 |
mer | -0.033 |
lifetime | -0.033 |
Token | arre |
Token ID | 9624 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
what | +0.038 |
mom | +0.038 |
Spot | +0.037 |
off | +0.037 |
our | +0.037 |
Neg logit contributions | |
ited | -0.042 |
ho | -0.039 |
mer | -0.035 |
solar | -0.033 |
years | -0.033 |
Token | ling |
Token ID | 1359 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Spot | +0.129 |
mom | +0.126 |
Zip | +0.126 |
Rex | +0.126 |
Kitty | +0.124 |
Neg logit contributions | |
ho | -0.113 |
ited | -0.112 |
mer | -0.097 |
solar | -0.087 |
ad | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
off | +0.025 |
two | +0.023 |
some | +0.022 |
our | +0.022 |
what | +0.021 |
Neg logit contributions | |
ho | -0.080 |
ited | -0.075 |
solar | -0.070 |
mer | -0.068 |
lifetime | -0.067 |
Token | She |
Token ID | 1375 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
off | +0.026 |
two | +0.025 |
some | +0.025 |
what | +0.024 |
Spot | +0.024 |
Neg logit contributions | |
ho | -0.046 |
ited | -0.044 |
solar | -0.039 |
mer | -0.039 |
lifetime | -0.038 |
Token | was |
Token ID | 373 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
off | +0.040 |
two | +0.038 |
some | +0.037 |
our | +0.037 |
what | +0.036 |
Neg logit contributions | |
ho | -0.052 |
ited | -0.048 |
solar | -0.043 |
mer | -0.042 |
lifetime | -0.041 |
Token | very |
Token ID | 845 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
adoes | +0.023 |
off | +0.023 |
our | +0.021 |
icles | +0.021 |
some | +0.021 |
Neg logit contributions | |
ho | -0.038 |
ited | -0.034 |
years | -0.033 |
ad | -0.031 |
solar | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
ited | +0.024 |
ho | +0.024 |
solar | +0.022 |
lifetime | +0.021 |
mer | +0.021 |
Neg logit contributions | |
off | -0.007 |
some | -0.007 |
on | -0.007 |
the | -0.007 |
about | -0.006 |
Token | Soon |
Token ID | 15894 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
ho | +0.028 |
ited | +0.026 |
solar | +0.024 |
mer | +0.024 |
lifetime | +0.023 |
Neg logit contributions | |
off | -0.010 |
two | -0.010 |
some | -0.009 |
our | -0.009 |
what | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +4.63e-03 |
Pos logit contributions | |
ho | +0.022 |
ited | +0.020 |
solar | +0.018 |
lifetime | +0.018 |
wished | +0.018 |
Neg logit contributions | |
ags | -0.012 |
adoes | -0.012 |
< | -0.011 |
off | -0.011 |
asuring | -0.010 |
Token | little |
Token ID | 1310 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ags | +0.000 |
< | +0.000 |
adoes | +0.000 |
off | +0.000 |
Zip | +0.000 |
Neg logit contributions | |
ho | -0.000 |
ited | -0.000 |
solar | -0.000 |
lifetime | -0.000 |
thank | -0.000 |
Token | green |
Token ID | 4077 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
ho | +0.069 |
ited | +0.064 |
solar | +0.059 |
mer | +0.058 |
lifetime | +0.056 |
Neg logit contributions | |
off | -0.029 |
two | -0.026 |
some | -0.026 |
our | -0.026 |
what | -0.025 |
Token | spr |
Token ID | 7500 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
ho | +0.039 |
ited | +0.036 |
solar | +0.034 |
mer | +0.033 |
lifetime | +0.032 |
Neg logit contributions | |
off | -0.016 |
two | -0.015 |
some | -0.015 |
our | -0.014 |
what | -0.014 |
Token | outs |
Token ID | 5269 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
ho | +0.105 |
ited | +0.096 |
solar | +0.087 |
mer | +0.085 |
lifetime | +0.082 |
Neg logit contributions | |
off | -0.072 |
two | -0.069 |
some | -0.068 |
our | -0.067 |
what | -0.065 |
Token | started |
Token ID | 2067 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
ho | +0.013 |
ited | +0.012 |
solar | +0.011 |
lifetime | +0.011 |
years | +0.011 |
Neg logit contributions | |
off | -0.008 |
two | -0.008 |
some | -0.008 |
about | -0.008 |
over | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
ho | +0.028 |
ited | +0.027 |
solar | +0.025 |
mer | +0.025 |
lifetime | +0.025 |
Neg logit contributions | |
off | -0.005 |
some | -0.004 |
two | -0.004 |
our | -0.003 |
them | -0.003 |
Token | appear |
Token ID | 1656 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
ho | +0.040 |
ited | +0.037 |
years | +0.036 |
solar | +0.035 |
mer | +0.035 |
Neg logit contributions | |
some | -0.021 |
off | -0.020 |
the | -0.020 |
two | -0.020 |
them | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
ho | +0.007 |
ited | +0.007 |
solar | +0.006 |
years | +0.006 |
lifetime | +0.006 |
Neg logit contributions | |
off | -0.002 |
some | -0.002 |
two | -0.002 |
on | -0.002 |
over | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +7.17e-02 |
Pos logit contributions | |
off | +0.004 |
two | +0.004 |
our | +0.003 |
adoes | +0.003 |
some | +0.003 |
Neg logit contributions | |
ho | -0.013 |
ited | -0.012 |
solar | -0.011 |
mer | -0.011 |
lifetime | -0.011 |
Token | As |
Token ID | 1722 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
off | +0.002 |
two | +0.002 |
some | +0.002 |
them | +0.001 |
our | +0.001 |
Neg logit contributions | |
ho | -0.004 |
ited | -0.004 |
solar | -0.003 |
mer | -0.003 |
lifetime | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
ho | +0.077 |
ited | +0.072 |
solar | +0.067 |
mer | +0.066 |
lifetime | +0.064 |
Neg logit contributions | |
off | -0.023 |
two | -0.021 |
some | -0.021 |
our | -0.020 |
what | -0.019 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
ho | +0.046 |
ited | +0.042 |
solar | +0.038 |
mer | +0.037 |
lifetime | +0.036 |
Neg logit contributions | |
off | -0.026 |
some | -0.023 |
two | -0.023 |
our | -0.023 |
what | -0.023 |
Token | began |
Token ID | 2540 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
ho | +0.061 |
ited | +0.050 |
mer | +0.044 |
thank | +0.042 |
solar | +0.036 |
Neg logit contributions | |
our | -0.073 |
my | -0.071 |
what | -0.071 |
ags | -0.071 |
about | -0.070 |
Token | to |
Token ID | 284 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
ho | +0.139 |
ited | +0.129 |
solar | +0.120 |
mer | +0.118 |
lifetime | +0.116 |
Neg logit contributions | |
off | -0.026 |
two | -0.024 |
our | -0.022 |
some | -0.022 |
what | -0.021 |
Token | set |
Token ID | 900 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ho | +0.107 |
ited | +0.099 |
solar | +0.092 |
mer | +0.091 |
years | +0.091 |
Neg logit contributions | |
off | -0.063 |
two | -0.060 |
some | -0.059 |
them | -0.057 |
our | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
ho | +0.068 |
ited | +0.061 |
mer | +0.056 |
solar | +0.056 |
lifetime | +0.054 |
Neg logit contributions | |
off | -0.027 |
two | -0.026 |
our | -0.025 |
some | -0.025 |
what | -0.024 |
Token | Bub |
Token ID | 19645 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
ho | +0.026 |
ited | +0.024 |
solar | +0.022 |
mer | +0.021 |
lifetime | +0.021 |
Neg logit contributions | |
off | -0.015 |
two | -0.014 |
our | -0.013 |
some | -0.013 |
what | -0.013 |
Token | bles |
Token ID | 7689 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
off | +0.008 |
two | +0.008 |
our | +0.007 |
friends | +0.007 |
some | +0.007 |
Neg logit contributions | |
ho | -0.024 |
ited | -0.023 |
solar | -0.021 |
lifetime | -0.020 |
mer | -0.020 |
Token | started |
Token ID | 2067 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ho | +0.005 |
ited | +0.005 |
solar | +0.004 |
years | +0.004 |
mer | +0.004 |
Neg logit contributions | |
two | -0.004 |
off | -0.004 |
some | -0.004 |
the | -0.004 |
friends | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
off | +0.004 |
two | +0.004 |
some | +0.003 |
our | +0.003 |
what | +0.003 |
Neg logit contributions | |
ho | -0.016 |
ited | -0.015 |
solar | -0.014 |
mer | -0.013 |
lifetime | -0.013 |
Token | As |
Token ID | 1722 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
off | +0.004 |
two | +0.004 |
some | +0.004 |
our | +0.003 |
what | +0.003 |
Neg logit contributions | |
ho | -0.010 |
ited | -0.009 |
solar | -0.008 |
mer | -0.008 |
lifetime | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
ho | +0.067 |
ited | +0.064 |
solar | +0.058 |
mer | +0.058 |
years | +0.054 |
Neg logit contributions | |
off | -0.030 |
two | -0.029 |
some | -0.029 |
the | -0.028 |
Spot | -0.027 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ho | +0.040 |
ited | +0.036 |
solar | +0.033 |
mer | +0.033 |
lifetime | +0.032 |
Neg logit contributions | |
off | -0.026 |
our | -0.025 |
adoes | -0.024 |
about | -0.024 |
what | -0.024 |
Token | started |
Token ID | 2067 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
ho | +0.056 |
ited | +0.044 |
mer | +0.040 |
thank | +0.037 |
lifetime | +0.034 |
Neg logit contributions | |
our | -0.074 |
my | -0.072 |
ags | -0.071 |
what | -0.069 |
Zip | -0.067 |
Token | to |
Token ID | 284 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
ho | +0.121 |
ited | +0.109 |
solar | +0.103 |
mer | +0.101 |
lifetime | +0.099 |
Neg logit contributions | |
off | -0.024 |
two | -0.022 |
our | -0.022 |
some | -0.021 |
what | -0.020 |
Token | set |
Token ID | 900 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ho | +0.110 |
ited | +0.103 |
years | +0.096 |
solar | +0.095 |
mer | +0.093 |
Neg logit contributions | |
off | -0.059 |
two | -0.058 |
some | -0.057 |
them | -0.055 |
the | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
ho | +0.071 |
ited | +0.066 |
solar | +0.061 |
mer | +0.060 |
lifetime | +0.058 |
Neg logit contributions | |
off | -0.025 |
two | -0.023 |
some | -0.023 |
our | -0.022 |
what | -0.021 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
ho | +0.028 |
ited | +0.025 |
solar | +0.024 |
mer | +0.023 |
lifetime | +0.023 |
Neg logit contributions | |
off | -0.011 |
ags | -0.011 |
our | -0.010 |
adoes | -0.010 |
asuring | -0.010 |
Token | realized |
Token ID | 6939 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
ho | +0.009 |
ited | +0.008 |
solar | +0.007 |
mer | +0.007 |
lifetime | +0.007 |
Neg logit contributions | |
off | -0.006 |
two | -0.006 |
some | -0.006 |
friends | -0.006 |
what | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
ho | +0.023 |
ited | +0.020 |
solar | +0.019 |
wished | +0.019 |
ad | +0.019 |
Neg logit contributions | |
ags | -0.011 |
our | -0.011 |
off | -0.011 |
adoes | -0.010 |
snowball | -0.010 |
Token | 's |
Token ID | 338 |
Feature activation | +8.45e-02 |
Pos logit contributions | |
two | +0.003 |
some | +0.003 |
the | +0.003 |
our | +0.003 |
on | +0.003 |
Neg logit contributions | |
ho | -0.004 |
ited | -0.004 |
lifetime | -0.003 |
years | -0.003 |
solar | -0.003 |
Token | flag |
Token ID | 6056 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
off | +0.002 |
two | +0.002 |
some | +0.002 |
our | +0.002 |
friends | +0.002 |
Neg logit contributions | |
ho | -0.005 |
ited | -0.004 |
solar | -0.004 |
mer | -0.004 |
lifetime | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
ited | +0.047 |
ho | +0.046 |
years | +0.042 |
solar | +0.041 |
mer | +0.040 |
Neg logit contributions | |
on | -0.017 |
two | -0.016 |
friends | -0.016 |
off | -0.016 |
about | -0.015 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
ho | +0.043 |
ited | +0.041 |
mer | +0.036 |
solar | +0.036 |
lifetime | +0.035 |
Neg logit contributions | |
off | -0.021 |
two | -0.020 |
some | -0.019 |
our | -0.019 |
on | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
ho | +0.063 |
ited | +0.061 |
solar | +0.055 |
years | +0.054 |
lifetime | +0.054 |
Neg logit contributions | |
off | -0.014 |
two | -0.013 |
some | -0.013 |
on | -0.012 |
too | -0.012 |
Token | full |
Token ID | 1336 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
ho | +0.039 |
ited | +0.038 |
mer | +0.033 |
solar | +0.032 |
lifetime | +0.031 |
Neg logit contributions | |
off | -0.018 |
two | -0.018 |
some | -0.017 |
our | -0.017 |
the | -0.017 |
Token | of |
Token ID | 286 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
ho | +0.160 |
ited | +0.159 |
mer | +0.145 |
solar | +0.144 |
years | +0.141 |
Neg logit contributions | |
off | -0.011 |
some | -0.010 |
two | -0.009 |
about | -0.008 |
the | -0.006 |
Token | many |
Token ID | 867 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ho | +0.017 |
ited | +0.016 |
mer | +0.015 |
solar | +0.014 |
years | +0.014 |
Neg logit contributions | |
two | -0.008 |
off | -0.008 |
some | -0.007 |
our | -0.007 |
them | -0.007 |
Token | colors |
Token ID | 7577 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
ho | +0.060 |
ited | +0.054 |
mer | +0.049 |
solar | +0.049 |
years | +0.047 |
Neg logit contributions | |
off | -0.020 |
two | -0.020 |
friends | -0.019 |
some | -0.019 |
our | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
ho | +0.032 |
ited | +0.030 |
solar | +0.027 |
mer | +0.026 |
lifetime | +0.026 |
Neg logit contributions | |
off | -0.016 |
two | -0.015 |
some | -0.015 |
our | -0.014 |
what | -0.014 |
Token | He |
Token ID | 679 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ho | +0.003 |
ited | +0.003 |
solar | +0.003 |
mer | +0.003 |
lifetime | +0.003 |
Neg logit contributions | |
off | -0.002 |
our | -0.002 |
adoes | -0.002 |
cookies | -0.002 |
two | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
ho | +0.014 |
ited | +0.013 |
solar | +0.012 |
mer | +0.012 |
lifetime | +0.012 |
Neg logit contributions | |
off | -0.005 |
two | -0.004 |
our | -0.004 |
some | -0.004 |
adoes | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +7.17e-02 |
Pos logit contributions | |
off | +0.004 |
two | +0.004 |
our | +0.003 |
adoes | +0.003 |
some | +0.003 |
Neg logit contributions | |
ho | -0.013 |
ited | -0.012 |
solar | -0.011 |
mer | -0.011 |
lifetime | -0.011 |
Token | As |
Token ID | 1722 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
off | +0.002 |
two | +0.002 |
some | +0.002 |
them | +0.001 |
our | +0.001 |
Neg logit contributions | |
ho | -0.004 |
ited | -0.004 |
solar | -0.003 |
mer | -0.003 |
lifetime | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
ho | +0.077 |
ited | +0.072 |
solar | +0.067 |
mer | +0.066 |
lifetime | +0.064 |
Neg logit contributions | |
off | -0.023 |
two | -0.021 |
some | -0.021 |
our | -0.020 |
what | -0.019 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
ho | +0.046 |
ited | +0.042 |
solar | +0.038 |
mer | +0.037 |
lifetime | +0.036 |
Neg logit contributions | |
off | -0.026 |
some | -0.023 |
two | -0.023 |
our | -0.023 |
what | -0.023 |
Token | began |
Token ID | 2540 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
ho | +0.061 |
ited | +0.050 |
mer | +0.044 |
thank | +0.042 |
solar | +0.036 |
Neg logit contributions | |
our | -0.073 |
my | -0.071 |
what | -0.071 |
ags | -0.071 |
about | -0.070 |
Token | to |
Token ID | 284 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
ho | +0.139 |
ited | +0.129 |
solar | +0.120 |
mer | +0.118 |
lifetime | +0.116 |
Neg logit contributions | |
off | -0.026 |
two | -0.024 |
our | -0.022 |
some | -0.022 |
what | -0.021 |
Token | set |
Token ID | 900 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ho | +0.107 |
ited | +0.099 |
solar | +0.092 |
mer | +0.091 |
years | +0.091 |
Neg logit contributions | |
off | -0.063 |
two | -0.060 |
some | -0.059 |
them | -0.057 |
our | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
ho | +0.068 |
ited | +0.061 |
mer | +0.056 |
solar | +0.056 |
lifetime | +0.054 |
Neg logit contributions | |
off | -0.027 |
two | -0.026 |
our | -0.025 |
some | -0.025 |
what | -0.024 |
Token | Bub |
Token ID | 19645 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
ho | +0.026 |
ited | +0.024 |
solar | +0.022 |
mer | +0.021 |
lifetime | +0.021 |
Neg logit contributions | |
off | -0.015 |
two | -0.014 |
our | -0.013 |
some | -0.013 |
what | -0.013 |
Token | bles |
Token ID | 7689 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
off | +0.008 |
two | +0.008 |
our | +0.007 |
friends | +0.007 |
some | +0.007 |
Neg logit contributions | |
ho | -0.024 |
ited | -0.023 |
solar | -0.021 |
lifetime | -0.020 |
mer | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
off | +0.008 |
adoes | +0.008 |
two | +0.007 |
our | +0.007 |
some | +0.007 |
Neg logit contributions | |
ho | -0.023 |
ited | -0.021 |
solar | -0.020 |
mer | -0.019 |
lifetime | -0.019 |
Token | As |
Token ID | 1722 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
off | +0.007 |
two | +0.007 |
some | +0.006 |
our | +0.006 |
what | +0.006 |
Neg logit contributions | |
ho | -0.018 |
ited | -0.016 |
solar | -0.015 |
mer | -0.015 |
lifetime | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
ho | +0.075 |
ited | +0.070 |
solar | +0.065 |
mer | +0.064 |
lifetime | +0.063 |
Neg logit contributions | |
off | -0.016 |
two | -0.014 |
some | -0.014 |
our | -0.013 |
what | -0.012 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
ho | +0.043 |
ited | +0.040 |
solar | +0.036 |
mer | +0.035 |
lifetime | +0.035 |
Neg logit contributions | |
off | -0.021 |
our | -0.019 |
what | -0.019 |
some | -0.019 |
them | -0.019 |
Token | started |
Token ID | 2067 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
ho | +0.055 |
ited | +0.048 |
mer | +0.041 |
solar | +0.040 |
thank | +0.040 |
Neg logit contributions | |
our | -0.059 |
what | -0.058 |
off | -0.058 |
my | -0.057 |
two | -0.056 |
Token | to |
Token ID | 284 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
ho | +0.116 |
ited | +0.106 |
solar | +0.100 |
mer | +0.098 |
lifetime | +0.096 |
Neg logit contributions | |
off | -0.023 |
two | -0.021 |
our | -0.021 |
some | -0.020 |
what | -0.020 |
Token | set |
Token ID | 900 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ho | +0.110 |
ited | +0.101 |
years | +0.094 |
mer | +0.094 |
solar | +0.094 |
Neg logit contributions | |
off | -0.059 |
two | -0.055 |
some | -0.055 |
them | -0.053 |
our | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
ho | +0.061 |
ited | +0.057 |
solar | +0.053 |
mer | +0.052 |
lifetime | +0.051 |
Neg logit contributions | |
off | -0.022 |
two | -0.020 |
some | -0.019 |
our | -0.019 |
what | -0.018 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
ho | +0.017 |
ited | +0.015 |
solar | +0.015 |
mer | +0.014 |
wished | +0.014 |
Neg logit contributions | |
ags | -0.008 |
asuring | -0.008 |
off | -0.008 |
adoes | -0.008 |
uate | -0.008 |
Token | knew |
Token ID | 2993 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
ho | +0.013 |
ited | +0.012 |
solar | +0.011 |
mer | +0.011 |
lifetime | +0.011 |
Neg logit contributions | |
off | -0.005 |
two | -0.005 |
some | -0.005 |
friends | -0.005 |
our | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
ho | +0.025 |
ited | +0.020 |
solar | +0.019 |
wished | +0.019 |
lifetime | +0.019 |
Neg logit contributions | |
ags | -0.018 |
off | -0.018 |
adoes | -0.017 |
our | -0.017 |
two | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
off | +0.010 |
two | +0.009 |
our | +0.009 |
some | +0.008 |
adoes | +0.008 |
Neg logit contributions | |
ho | -0.035 |
ited | -0.033 |
solar | -0.031 |
mer | -0.030 |
lifetime | -0.029 |
Token | As |
Token ID | 1722 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
off | +0.017 |
two | +0.016 |
some | +0.016 |
our | +0.016 |
what | +0.015 |
Neg logit contributions | |
ho | -0.016 |
ited | -0.014 |
solar | -0.012 |
mer | -0.012 |
lifetime | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
ho | +0.051 |
ited | +0.047 |
solar | +0.043 |
mer | +0.042 |
lifetime | +0.041 |
Neg logit contributions | |
off | -0.030 |
two | -0.028 |
some | -0.028 |
our | -0.027 |
what | -0.027 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ho | +0.042 |
ited | +0.038 |
solar | +0.035 |
mer | +0.034 |
lifetime | +0.033 |
Neg logit contributions | |
off | -0.020 |
adoes | -0.019 |
what | -0.019 |
our | -0.018 |
about | -0.018 |
Token | began |
Token ID | 2540 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ho | +0.051 |
ited | +0.042 |
mer | +0.037 |
thank | +0.034 |
solar | +0.032 |
Neg logit contributions | |
our | -0.063 |
my | -0.061 |
what | -0.061 |
ags | -0.060 |
about | -0.059 |
Token | to |
Token ID | 284 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
ho | +0.125 |
ited | +0.116 |
solar | +0.109 |
mer | +0.107 |
lifetime | +0.104 |
Neg logit contributions | |
off | -0.024 |
two | -0.021 |
our | -0.020 |
some | -0.020 |
what | -0.019 |
Token | set |
Token ID | 900 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ho | +0.107 |
ited | +0.099 |
solar | +0.091 |
mer | +0.090 |
years | +0.088 |
Neg logit contributions | |
off | -0.058 |
two | -0.054 |
some | -0.053 |
our | -0.052 |
them | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
ho | +0.059 |
ited | +0.053 |
mer | +0.049 |
solar | +0.049 |
lifetime | +0.046 |
Neg logit contributions | |
off | -0.025 |
two | -0.025 |
our | -0.024 |
some | -0.023 |
adoes | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
ho | +0.016 |
ited | +0.014 |
solar | +0.013 |
mer | +0.013 |
thank | +0.012 |
Neg logit contributions | |
off | -0.015 |
adoes | -0.014 |
our | -0.014 |
two | -0.014 |
Zip | -0.014 |
Token | ocean |
Token ID | 9151 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
ho | +0.021 |
ited | +0.019 |
solar | +0.018 |
mer | +0.017 |
lifetime | +0.017 |
Neg logit contributions | |
off | -0.009 |
our | -0.008 |
some | -0.008 |
adoes | -0.008 |
about | -0.008 |
Token | got |
Token ID | 1392 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ho | +0.022 |
ited | +0.020 |
solar | +0.018 |
mer | +0.017 |
lifetime | +0.017 |
Neg logit contributions | |
off | -0.017 |
two | -0.016 |
some | -0.016 |
our | -0.016 |
what | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
off | +0.006 |
two | +0.005 |
some | +0.005 |
our | +0.005 |
what | +0.005 |
Neg logit contributions | |
ho | -0.029 |
ited | -0.027 |
solar | -0.025 |
mer | -0.025 |
lifetime | -0.024 |
Token | As |
Token ID | 1722 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
two | +0.007 |
off | +0.007 |
some | +0.007 |
our | +0.007 |
them | +0.007 |
Neg logit contributions | |
ho | -0.019 |
ited | -0.017 |
solar | -0.016 |
mer | -0.016 |
years | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
ho | +0.088 |
ited | +0.083 |
solar | +0.078 |
mer | +0.077 |
lifetime | +0.075 |
Neg logit contributions | |
off | -0.009 |
two | -0.007 |
some | -0.007 |
our | -0.006 |
what | -0.005 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
ho | +0.021 |
ited | +0.020 |
solar | +0.018 |
thank | +0.017 |
lifetime | +0.017 |
Neg logit contributions | |
off | -0.012 |
them | -0.011 |
what | -0.011 |
our | -0.011 |
adoes | -0.011 |
Token | began |
Token ID | 2540 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
ho | +0.055 |
ited | +0.046 |
mer | +0.040 |
thank | +0.038 |
solar | +0.037 |
Neg logit contributions | |
our | -0.062 |
what | -0.060 |
my | -0.059 |
ags | -0.058 |
Buddy | -0.058 |
Token | to |
Token ID | 284 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
ho | +0.128 |
ited | +0.120 |
solar | +0.112 |
mer | +0.111 |
lifetime | +0.108 |
Neg logit contributions | |
off | -0.024 |
two | -0.021 |
some | -0.020 |
our | -0.020 |
what | -0.018 |
Token | set |
Token ID | 900 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ho | +0.107 |
ited | +0.099 |
solar | +0.091 |
mer | +0.090 |
years | +0.090 |
Neg logit contributions | |
off | -0.058 |
two | -0.056 |
some | -0.055 |
them | -0.052 |
our | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
ho | +0.059 |
ited | +0.053 |
solar | +0.049 |
mer | +0.048 |
lifetime | +0.047 |
Neg logit contributions | |
off | -0.025 |
two | -0.024 |
some | -0.023 |
our | -0.023 |
what | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
ho | +0.017 |
ited | +0.015 |
solar | +0.015 |
mer | +0.015 |
lifetime | +0.014 |
Neg logit contributions | |
off | -0.003 |
ags | -0.003 |
adoes | -0.003 |
our | -0.002 |
about | -0.002 |
Token | bird |
Token ID | 6512 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
off | +0.001 |
our | +0.001 |
some | +0.001 |
two | +0.001 |
them | +0.001 |
Neg logit contributions | |
ho | -0.002 |
ited | -0.002 |
solar | -0.002 |
mer | -0.002 |
lifetime | -0.002 |
Token | knew |
Token ID | 2993 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
off | +0.008 |
two | +0.008 |
some | +0.008 |
friends | +0.007 |
what | +0.007 |
Neg logit contributions | |
ho | -0.010 |
ited | -0.009 |
solar | -0.008 |
mer | -0.008 |
years | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
off | +0.002 |
two | +0.002 |
some | +0.002 |
our | +0.002 |
what | +0.002 |
Neg logit contributions | |
ho | -0.009 |
ited | -0.009 |
solar | -0.008 |
mer | -0.008 |
lifetime | -0.008 |
Token | As |
Token ID | 1722 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
ho | +0.002 |
ited | +0.002 |
solar | +0.002 |
mer | +0.002 |
years | +0.002 |
Neg logit contributions | |
off | -0.001 |
two | -0.001 |
some | -0.001 |
them | -0.001 |
our | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
ho | +0.068 |
ited | +0.063 |
solar | +0.057 |
mer | +0.056 |
lifetime | +0.055 |
Neg logit contributions | |
off | -0.035 |
two | -0.033 |
some | -0.032 |
our | -0.032 |
what | -0.031 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
ho | +0.045 |
ited | +0.041 |
solar | +0.037 |
mer | +0.037 |
lifetime | +0.035 |
Neg logit contributions | |
off | -0.025 |
adoes | -0.025 |
what | -0.023 |
about | -0.022 |
our | -0.022 |
Token | began |
Token ID | 2540 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
ho | +0.055 |
ited | +0.043 |
mer | +0.041 |
thank | +0.036 |
solar | +0.034 |
Neg logit contributions | |
our | -0.069 |
what | -0.068 |
ags | -0.066 |
my | -0.066 |
about | -0.065 |
Token | to |
Token ID | 284 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
ho | +0.128 |
ited | +0.119 |
solar | +0.112 |
mer | +0.110 |
lifetime | +0.107 |
Neg logit contributions | |
off | -0.023 |
two | -0.020 |
some | -0.019 |
our | -0.019 |
what | -0.018 |
Token | set |
Token ID | 900 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ho | +0.106 |
ited | +0.098 |
solar | +0.090 |
mer | +0.089 |
years | +0.088 |
Neg logit contributions | |
off | -0.059 |
two | -0.055 |
some | -0.055 |
them | -0.053 |
our | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
ho | +0.059 |
ited | +0.054 |
solar | +0.050 |
mer | +0.049 |
lifetime | +0.048 |
Neg logit contributions | |
off | -0.022 |
two | -0.020 |
some | -0.020 |
our | -0.020 |
what | -0.019 |
Token | Nem |
Token ID | 22547 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
ho | +0.018 |
ited | +0.016 |
solar | +0.014 |
mer | +0.014 |
thank | +0.013 |
Neg logit contributions | |
off | -0.016 |
adoes | -0.015 |
two | -0.015 |
our | -0.014 |
Zip | -0.014 |
Token | o |
Token ID | 78 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
off | +0.009 |
two | +0.009 |
some | +0.009 |
our | +0.008 |
what | +0.008 |
Neg logit contributions | |
ho | -0.023 |
ited | -0.022 |
solar | -0.020 |
mer | -0.019 |
lifetime | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
off | +0.001 |
two | +0.001 |
some | +0.001 |
friends | +0.001 |
over | +0.001 |
Neg logit contributions | |
ho | -0.002 |
ited | -0.002 |
solar | -0.001 |
years | -0.001 |
mer | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
adoes | +0.001 |
off | +0.001 |
two | +0.001 |
asuring | +0.001 |
our | +0.001 |
Neg logit contributions | |
ho | -0.004 |
solar | -0.003 |
ited | -0.003 |
lifetime | -0.003 |
ad | -0.003 |
Token | As |
Token ID | 1722 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
off | +0.001 |
two | +0.001 |
what | +0.001 |
adoes | +0.001 |
ags | +0.001 |
Neg logit contributions | |
ho | -0.002 |
ited | -0.002 |
solar | -0.002 |
mer | -0.002 |
lifetime | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
ho | +0.055 |
solar | +0.046 |
ited | +0.045 |
lifetime | +0.044 |
mer | +0.043 |
Neg logit contributions | |
ags | -0.032 |
adoes | -0.032 |
asuring | -0.032 |
wounds | -0.028 |
icles | -0.028 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
ho | +0.033 |
ited | +0.031 |
thank | +0.029 |
solar | +0.027 |
lifetime | +0.027 |
Neg logit contributions | |
what | -0.025 |
our | -0.024 |
off | -0.023 |
them | -0.023 |
wounds | -0.022 |
Token | began |
Token ID | 2540 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
ho | +0.048 |
ited | +0.039 |
mer | +0.034 |
thank | +0.034 |
solar | +0.029 |
Neg logit contributions | |
what | -0.065 |
our | -0.065 |
my | -0.063 |
ags | -0.061 |
adoes | -0.061 |
Token | to |
Token ID | 284 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
ho | +0.122 |
ited | +0.110 |
solar | +0.105 |
mer | +0.103 |
lifetime | +0.101 |
Neg logit contributions | |
off | -0.025 |
two | -0.023 |
our | -0.022 |
what | -0.022 |
some | -0.022 |
Token | set |
Token ID | 900 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ho | +0.104 |
ited | +0.095 |
solar | +0.087 |
mer | +0.086 |
years | +0.085 |
Neg logit contributions | |
off | -0.060 |
two | -0.057 |
some | -0.056 |
our | -0.055 |
them | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
ho | +0.052 |
ited | +0.046 |
mer | +0.043 |
solar | +0.043 |
lifetime | +0.041 |
Neg logit contributions | |
two | -0.023 |
off | -0.023 |
our | -0.023 |
some | -0.023 |
what | -0.022 |
Token | Buddy |
Token ID | 36896 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
ho | +0.007 |
wished | +0.006 |
mer | +0.006 |
spe | +0.005 |
solar | +0.005 |
Neg logit contributions | |
ags | -0.005 |
asuring | -0.004 |
uate | -0.004 |
icle | -0.004 |
icles | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
ho | +0.028 |
ited | +0.026 |
solar | +0.024 |
years | +0.024 |
lifetime | +0.024 |
Neg logit contributions | |
off | -0.010 |
two | -0.009 |
some | -0.009 |
Spot | -0.009 |
the | -0.008 |
Token | Lily |
Token ID | 20037 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
ho | +0.020 |
ited | +0.018 |
solar | +0.016 |
mer | +0.016 |
wished | +0.016 |
Neg logit contributions | |
ags | -0.008 |
asuring | -0.008 |
off | -0.008 |
two | -0.008 |
adoes | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ho | +0.003 |
ited | +0.003 |
solar | +0.002 |
lifetime | +0.002 |
years | +0.002 |
Neg logit contributions | |
off | -0.001 |
some | -0.001 |
two | -0.001 |
over | -0.001 |
too | -0.001 |
Token | Sara |
Token ID | 24799 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
off | +0.003 |
two | +0.003 |
our | +0.003 |
what | +0.003 |
friends | +0.003 |
Neg logit contributions | |
ho | -0.008 |
ited | -0.007 |
solar | -0.006 |
mer | -0.006 |
thank | -0.006 |
Token | runs |
Token ID | 4539 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
ho | +0.005 |
ited | +0.004 |
solar | +0.004 |
mer | +0.004 |
wished | +0.004 |
Neg logit contributions | |
adoes | -0.003 |
off | -0.003 |
our | -0.003 |
icles | -0.003 |
ags | -0.003 |
Token | away |
Token ID | 1497 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
ho | +0.023 |
ited | +0.022 |
solar | +0.020 |
mer | +0.020 |
lifetime | +0.019 |
Neg logit contributions | |
off | -0.008 |
two | -0.007 |
some | -0.007 |
our | -0.007 |
what | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
ho | +0.022 |
ited | +0.021 |
solar | +0.019 |
lifetime | +0.019 |
mer | +0.019 |
Neg logit contributions | |
off | -0.006 |
two | -0.005 |
some | -0.005 |
our | -0.005 |
what | -0.005 |
Token | spr |
Token ID | 7500 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
ho | +0.012 |
ited | +0.011 |
solar | +0.010 |
mer | +0.009 |
wished | +0.009 |
Neg logit contributions | |
off | -0.007 |
two | -0.007 |
adoes | -0.007 |
some | -0.007 |
our | -0.007 |
Token | ays |
Token ID | 592 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
ho | +0.092 |
ited | +0.082 |
years | +0.070 |
mer | +0.069 |
solar | +0.067 |
Neg logit contributions | |
two | -0.070 |
Buddy | -0.069 |
cookies | -0.068 |
some | -0.066 |
Zip | -0.065 |
Token | him |
Token ID | 683 |
Feature activation | +8.91e-02 |
Pos logit contributions | |
off | +0.008 |
two | +0.007 |
our | +0.007 |
some | +0.007 |
what | +0.006 |
Neg logit contributions | |
ho | -0.034 |
ited | -0.031 |
solar | -0.029 |
mer | -0.029 |
lifetime | -0.028 |
Token | again |
Token ID | 757 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
off | +0.002 |
some | +0.001 |
two | +0.001 |
on | +0.001 |
our | +0.001 |
Neg logit contributions | |
ho | -0.005 |
ited | -0.005 |
solar | -0.005 |
lifetime | -0.005 |
mer | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
ho | +0.007 |
ited | +0.007 |
solar | +0.006 |
years | +0.006 |
lifetime | +0.006 |
Neg logit contributions | |
off | -0.003 |
some | -0.002 |
on | -0.002 |
too | -0.002 |
two | -0.002 |
Token | They |
Token ID | 1119 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
off | +0.003 |
two | +0.003 |
our | +0.003 |
some | +0.002 |
what | +0.002 |
Neg logit contributions | |
ho | -0.006 |
ited | -0.005 |
solar | -0.005 |
mer | -0.004 |
thank | -0.004 |
Token | Tim |
Token ID | 5045 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
off | +0.002 |
our | +0.002 |
them | +0.002 |
what | +0.002 |
two | +0.002 |
Neg logit contributions | |
ho | -0.004 |
solar | -0.003 |
ited | -0.003 |
years | -0.003 |
mer | -0.003 |
Token | didn |
Token ID | 1422 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
ho | +0.008 |
ited | +0.008 |
solar | +0.007 |
mer | +0.007 |
lifetime | +0.006 |
Neg logit contributions | |
off | -0.007 |
two | -0.007 |
some | -0.007 |
our | -0.007 |
what | -0.007 |
Token | 't |
Token ID | 470 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
ho | +0.008 |
ited | +0.006 |
solar | +0.006 |
well | +0.006 |
ad | +0.006 |
Neg logit contributions | |
adoes | -0.005 |
friends | -0.005 |
dogs | -0.004 |
ags | -0.004 |
kids | -0.004 |
Token | like |
Token ID | 588 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
off | +0.031 |
our | +0.030 |
two | +0.030 |
adoes | +0.030 |
some | +0.029 |
Neg logit contributions | |
ho | -0.033 |
ited | -0.030 |
solar | -0.026 |
mer | -0.026 |
thank | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
ho | +0.051 |
ited | +0.047 |
solar | +0.045 |
mer | +0.043 |
years | +0.043 |
Neg logit contributions | |
off | -0.010 |
two | -0.009 |
our | -0.008 |
some | -0.008 |
adoes | -0.007 |
Token | seaw |
Token ID | 32085 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
ho | +0.036 |
ited | +0.033 |
years | +0.031 |
solar | +0.030 |
generation | +0.030 |
Neg logit contributions | |
two | -0.015 |
some | -0.014 |
off | -0.014 |
the | -0.013 |
friends | -0.013 |
Token | eed |
Token ID | 2308 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
ho | +0.097 |
ited | +0.091 |
solar | +0.083 |
years | +0.080 |
lifetime | +0.078 |
Neg logit contributions | |
off | -0.061 |
two | -0.057 |
some | -0.057 |
our | -0.055 |
friends | -0.054 |
Token | because |
Token ID | 780 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
ho | +0.023 |
ited | +0.023 |
solar | +0.022 |
years | +0.021 |
lifetime | +0.021 |
Neg logit contributions | |
off | -0.008 |
some | -0.008 |
on | -0.008 |
two | -0.008 |
too | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
ho | +0.007 |
solar | +0.006 |
ited | +0.006 |
years | +0.006 |
wished | +0.006 |
Neg logit contributions | |
ags | -0.005 |
off | -0.004 |
adoes | -0.004 |
< | -0.004 |
our | -0.004 |
Token | would |
Token ID | 561 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
ho | +0.023 |
ited | +0.022 |
solar | +0.020 |
lifetime | +0.019 |
years | +0.019 |
Neg logit contributions | |
off | -0.011 |
two | -0.010 |
some | -0.010 |
over | -0.009 |
Spot | -0.009 |
Token | get |
Token ID | 651 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
ho | +0.022 |
ited | +0.021 |
solar | +0.020 |
mer | +0.019 |
years | +0.019 |
Neg logit contributions | |
off | -0.009 |
some | -0.008 |
our | -0.008 |
two | -0.008 |
them | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
off | +0.011 |
adoes | +0.011 |
our | +0.010 |
two | +0.010 |
my | +0.009 |
Neg logit contributions | |
ho | -0.029 |
ited | -0.027 |
solar | -0.025 |
mer | -0.024 |
lifetime | -0.024 |
Token | As |
Token ID | 1722 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
off | +0.011 |
two | +0.011 |
some | +0.010 |
our | +0.010 |
what | +0.010 |
Neg logit contributions | |
ho | -0.024 |
ited | -0.022 |
solar | -0.020 |
mer | -0.020 |
lifetime | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
ho | +0.073 |
ited | +0.067 |
solar | +0.065 |
mer | +0.063 |
lifetime | +0.062 |
Neg logit contributions | |
off | -0.020 |
adoes | -0.019 |
ags | -0.018 |
two | -0.017 |
about | -0.016 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ho | +0.029 |
ited | +0.026 |
solar | +0.023 |
mer | +0.023 |
thank | +0.021 |
Neg logit contributions | |
off | -0.023 |
them | -0.022 |
what | -0.022 |
adoes | -0.021 |
our | -0.021 |
Token | began |
Token ID | 2540 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
ho | +0.050 |
ited | +0.041 |
mer | +0.037 |
thank | +0.035 |
solar | +0.032 |
Neg logit contributions | |
our | -0.062 |
what | -0.061 |
my | -0.060 |
ags | -0.059 |
about | -0.057 |
Token | to |
Token ID | 284 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ho | +0.127 |
ited | +0.116 |
solar | +0.110 |
mer | +0.108 |
lifetime | +0.106 |
Neg logit contributions | |
off | -0.024 |
two | -0.022 |
our | -0.021 |
some | -0.020 |
what | -0.020 |
Token | set |
Token ID | 900 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ho | +0.105 |
ited | +0.097 |
mer | +0.088 |
solar | +0.088 |
years | +0.088 |
Neg logit contributions | |
off | -0.059 |
two | -0.057 |
some | -0.056 |
them | -0.053 |
our | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
ho | +0.054 |
ited | +0.047 |
solar | +0.044 |
mer | +0.044 |
lifetime | +0.042 |
Neg logit contributions | |
off | -0.024 |
two | -0.024 |
our | -0.024 |
some | -0.023 |
what | -0.023 |
Token | Bear |
Token ID | 14732 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
ho | +0.018 |
ited | +0.016 |
solar | +0.016 |
mer | +0.015 |
lifetime | +0.015 |
Neg logit contributions | |
ags | -0.007 |
off | -0.007 |
adoes | -0.007 |
asuring | -0.006 |
uate | -0.006 |
Token | suggested |
Token ID | 5220 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
off | +0.017 |
two | +0.017 |
some | +0.016 |
friends | +0.016 |
them | +0.015 |
Neg logit contributions | |
ho | -0.026 |
ited | -0.024 |
solar | -0.022 |
years | -0.021 |
lifetime | -0.021 |
Token | they |
Token ID | 484 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
ags | +0.003 |
off | +0.003 |
adoes | +0.003 |
our | +0.003 |
uate | +0.003 |
Neg logit contributions | |
ho | -0.008 |
ited | -0.006 |
mer | -0.006 |
solar | -0.006 |
lifetime | -0.006 |
Token | Yes |
Token ID | 5297 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
ited | +0.037 |
ho | +0.036 |
years | +0.030 |
solar | +0.030 |
lifetime | +0.029 |
Neg logit contributions | |
two | -0.019 |
some | -0.017 |
Zip | -0.017 |
Rex | -0.016 |
Spot | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
ho | +0.002 |
ited | +0.002 |
solar | +0.002 |
mer | +0.002 |
lifetime | +0.002 |
Neg logit contributions | |
off | -0.001 |
two | -0.001 |
some | -0.001 |
adoes | -0.001 |
our | -0.001 |
Token | Mom |
Token ID | 11254 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
ho | +0.024 |
ited | +0.021 |
solar | +0.021 |
lifetime | +0.019 |
mer | +0.019 |
Neg logit contributions | |
off | -0.009 |
adoes | -0.008 |
ags | -0.008 |
two | -0.007 |
our | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
ho | +0.039 |
ited | +0.037 |
solar | +0.033 |
mer | +0.033 |
lifetime | +0.032 |
Neg logit contributions | |
off | -0.016 |
two | -0.016 |
some | -0.015 |
our | -0.015 |
what | -0.015 |
Token | That |
Token ID | 1320 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
ho | +0.043 |
ited | +0.039 |
solar | +0.036 |
mer | +0.035 |
lifetime | +0.034 |
Neg logit contributions | |
off | -0.021 |
two | -0.020 |
some | -0.019 |
our | -0.019 |
what | -0.018 |
Token | sounds |
Token ID | 5238 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ho | +0.019 |
ited | +0.018 |
years | +0.017 |
mer | +0.017 |
solar | +0.016 |
Neg logit contributions | |
two | -0.005 |
off | -0.005 |
some | -0.005 |
our | -0.004 |
friends | -0.004 |
Token | fun |
Token ID | 1257 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
ho | +0.101 |
ited | +0.092 |
solar | +0.082 |
mer | +0.081 |
lifetime | +0.079 |
Neg logit contributions | |
off | -0.063 |
two | -0.059 |
some | -0.059 |
our | -0.059 |
what | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
ho | +0.040 |
ited | +0.039 |
solar | +0.034 |
years | +0.033 |
mer | +0.033 |
Neg logit contributions | |
off | -0.015 |
some | -0.015 |
our | -0.014 |
two | -0.014 |
about | -0.014 |
Token | A |
Token ID | 317 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
ho | +0.033 |
ited | +0.029 |
solar | +0.029 |
mer | +0.027 |
lifetime | +0.026 |
Neg logit contributions | |
off | -0.021 |
two | -0.019 |
some | -0.019 |
our | -0.019 |
them | -0.019 |
Token | pink |
Token ID | 11398 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
ho | +0.038 |
ited | +0.037 |
years | +0.033 |
thank | +0.031 |
mer | +0.031 |
Neg logit contributions | |
two | -0.021 |
off | -0.021 |
friends | -0.020 |
our | -0.020 |
my | -0.020 |
Token | dragon |
Token ID | 10441 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
ho | +0.012 |
ited | +0.012 |
years | +0.010 |
solar | +0.010 |
mer | +0.010 |
Neg logit contributions | |
off | -0.007 |
two | -0.007 |
some | -0.007 |
our | -0.007 |
friends | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
off | +0.007 |
two | +0.006 |
our | +0.006 |
some | +0.006 |
adoes | +0.006 |
Neg logit contributions | |
ho | -0.023 |
ited | -0.021 |
solar | -0.020 |
mer | -0.019 |
lifetime | -0.019 |
Token | As |
Token ID | 1722 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
off | +0.005 |
two | +0.005 |
some | +0.005 |
our | +0.005 |
what | +0.005 |
Neg logit contributions | |
ho | -0.014 |
ited | -0.013 |
solar | -0.012 |
mer | -0.012 |
lifetime | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
ho | +0.068 |
ited | +0.063 |
solar | +0.059 |
mer | +0.057 |
lifetime | +0.056 |
Neg logit contributions | |
off | -0.020 |
two | -0.018 |
adoes | -0.018 |
some | -0.017 |
our | -0.017 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
ho | +0.027 |
ited | +0.026 |
solar | +0.023 |
thank | +0.022 |
lifetime | +0.022 |
Neg logit contributions | |
what | -0.018 |
off | -0.018 |
our | -0.018 |
them | -0.017 |
adoes | -0.017 |
Token | began |
Token ID | 2540 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
ho | +0.053 |
ited | +0.044 |
mer | +0.037 |
thank | +0.036 |
solar | +0.030 |
Neg logit contributions | |
our | -0.067 |
what | -0.065 |
ags | -0.063 |
my | -0.062 |
about | -0.062 |
Token | to |
Token ID | 284 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ho | +0.125 |
ited | +0.116 |
solar | +0.108 |
mer | +0.107 |
lifetime | +0.104 |
Neg logit contributions | |
off | -0.022 |
two | -0.020 |
our | -0.019 |
some | -0.019 |
what | -0.017 |
Token | set |
Token ID | 900 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ho | +0.105 |
ited | +0.097 |
solar | +0.091 |
years | +0.090 |
mer | +0.090 |
Neg logit contributions | |
off | -0.058 |
two | -0.055 |
some | -0.054 |
them | -0.052 |
our | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
ho | +0.055 |
ited | +0.049 |
mer | +0.045 |
solar | +0.045 |
lifetime | +0.043 |
Neg logit contributions | |
off | -0.023 |
two | -0.022 |
our | -0.021 |
some | -0.021 |
what | -0.021 |
Token | it |
Token ID | 340 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
ho | +0.014 |
ited | +0.012 |
solar | +0.012 |
mer | +0.012 |
wished | +0.011 |
Neg logit contributions | |
ags | -0.007 |
asuring | -0.006 |
off | -0.006 |
uate | -0.006 |
adoes | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
ho | +0.020 |
ited | +0.018 |
solar | +0.016 |
mer | +0.016 |
lifetime | +0.015 |
Neg logit contributions | |
off | -0.015 |
two | -0.015 |
some | -0.014 |
our | -0.014 |
them | -0.014 |
Token | time |
Token ID | 640 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
ho | +0.043 |
ited | +0.040 |
solar | +0.036 |
mer | +0.035 |
lifetime | +0.034 |
Neg logit contributions | |
off | -0.021 |
two | -0.019 |
our | -0.019 |
some | -0.019 |
adoes | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
off | +0.003 |
two | +0.002 |
some | +0.002 |
our | +0.002 |
adoes | +0.002 |
Neg logit contributions | |
ho | -0.010 |
ited | -0.009 |
solar | -0.008 |
mer | -0.008 |
lifetime | -0.008 |
Token | As |
Token ID | 1722 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
off | +0.001 |
two | +0.001 |
some | +0.001 |
our | +0.001 |
them | +0.001 |
Neg logit contributions | |
ho | -0.003 |
ited | -0.003 |
solar | -0.003 |
mer | -0.003 |
lifetime | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -8.30e-01 |
Pos logit contributions | |
ho | +0.069 |
ited | +0.064 |
solar | +0.059 |
mer | +0.058 |
lifetime | +0.057 |
Neg logit contributions | |
off | -0.024 |
adoes | -0.022 |
two | -0.021 |
ags | -0.020 |
some | -0.020 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
ho | +0.041 |
ited | +0.039 |
thank | +0.034 |
lifetime | +0.032 |
mer | +0.032 |
Neg logit contributions | |
adoes | -0.023 |
off | -0.023 |
our | -0.020 |
what | -0.020 |
Buddy | -0.020 |
Token | began |
Token ID | 2540 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
ho | +0.058 |
ited | +0.047 |
mer | +0.041 |
thank | +0.041 |
spe | +0.034 |
Neg logit contributions | |
our | -0.069 |
what | -0.067 |
ags | -0.067 |
my | -0.066 |
adoes | -0.065 |
Token | to |
Token ID | 284 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ho | +0.128 |
ited | +0.111 |
mer | +0.103 |
solar | +0.103 |
thank | +0.102 |
Neg logit contributions | |
our | -0.029 |
what | -0.029 |
two | -0.029 |
adoes | -0.028 |
off | -0.028 |
Token | set |
Token ID | 900 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ho | +0.098 |
ited | +0.090 |
solar | +0.083 |
mer | +0.081 |
years | +0.079 |
Neg logit contributions | |
off | -0.063 |
two | -0.060 |
some | -0.059 |
our | -0.058 |
them | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
ho | +0.061 |
ited | +0.055 |
mer | +0.051 |
solar | +0.050 |
lifetime | +0.048 |
Neg logit contributions | |
off | -0.024 |
two | -0.024 |
our | -0.023 |
some | -0.023 |
what | -0.022 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
ho | +0.019 |
ited | +0.016 |
mer | +0.015 |
solar | +0.015 |
de | +0.015 |
Neg logit contributions | |
ags | -0.012 |
asuring | -0.012 |
uate | -0.011 |
adoes | -0.011 |
off | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
ho | +0.012 |
ited | +0.011 |
solar | +0.010 |
mer | +0.010 |
years | +0.010 |
Neg logit contributions | |
off | -0.005 |
two | -0.005 |
some | -0.004 |
friends | -0.004 |
mom | -0.004 |
Token | Mitt |
Token ID | 16627 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
ho | +0.019 |
ited | +0.017 |
solar | +0.015 |
thank | +0.014 |
wished | +0.014 |
Neg logit contributions | |
off | -0.013 |
two | -0.012 |
ags | -0.012 |
our | -0.012 |
asuring | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
adoes | +0.004 |
off | +0.004 |
our | +0.003 |
cookies | +0.003 |
dogs | +0.003 |
Neg logit contributions | |
ho | -0.008 |
ited | -0.007 |
solar | -0.007 |
mer | -0.006 |
lifetime | -0.006 |
Token | As |
Token ID | 1722 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
off | +0.001 |
ags | +0.001 |
our | +0.001 |
two | +0.001 |
adoes | +0.001 |
Neg logit contributions | |
ho | -0.002 |
ited | -0.002 |
solar | -0.002 |
lifetime | -0.002 |
thank | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
ho | +0.062 |
ited | +0.055 |
lifetime | +0.052 |
solar | +0.051 |
wished | +0.048 |
Neg logit contributions | |
ags | -0.031 |
adoes | -0.031 |
asuring | -0.028 |
wounds | -0.026 |
off | -0.025 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ho | +0.049 |
ited | +0.045 |
solar | +0.042 |
mer | +0.040 |
lifetime | +0.040 |
Neg logit contributions | |
adoes | -0.025 |
off | -0.025 |
what | -0.025 |
Zip | -0.024 |
Buddy | -0.023 |
Token | began |
Token ID | 2540 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
ho | +0.054 |
ited | +0.045 |
mer | +0.040 |
thank | +0.038 |
lifetime | +0.033 |
Neg logit contributions | |
our | -0.071 |
my | -0.069 |
what | -0.069 |
ags | -0.069 |
Zip | -0.067 |
Token | to |
Token ID | 284 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ho | +0.125 |
ited | +0.113 |
solar | +0.107 |
mer | +0.105 |
lifetime | +0.103 |
Neg logit contributions | |
off | -0.025 |
two | -0.024 |
our | -0.023 |
what | -0.023 |
some | -0.022 |
Token | set |
Token ID | 900 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ho | +0.100 |
ited | +0.092 |
solar | +0.084 |
mer | +0.082 |
years | +0.080 |
Neg logit contributions | |
off | -0.062 |
two | -0.059 |
some | -0.058 |
our | -0.057 |
them | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
ho | +0.053 |
ited | +0.047 |
mer | +0.043 |
solar | +0.043 |
lifetime | +0.041 |
Neg logit contributions | |
two | -0.024 |
our | -0.024 |
off | -0.024 |
some | -0.023 |
adoes | -0.023 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
ho | +0.013 |
wished | +0.011 |
thank | +0.011 |
ited | +0.011 |
lifetime | +0.010 |
Neg logit contributions | |
ags | -0.010 |
asuring | -0.009 |
uate | -0.008 |
wounds | -0.008 |
adoes | -0.008 |
Token | my |
Token ID | 1820 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
ho | +0.001 |
ited | +0.001 |
solar | +0.001 |
mer | +0.001 |
lifetime | +0.001 |
Neg logit contributions | |
off | -0.000 |
two | -0.000 |
friends | -0.000 |
some | -0.000 |
what | -0.000 |
Token | 's |
Token ID | 338 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
ho | +0.011 |
ited | +0.010 |
solar | +0.009 |
mer | +0.009 |
lifetime | +0.008 |
Neg logit contributions | |
off | -0.007 |
two | -0.007 |
some | -0.007 |
our | -0.007 |
friends | -0.007 |
Token | Jonathan |
Token ID | 30365 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
off | +0.000 |
adoes | +0.000 |
dogs | +0.000 |
some | +0.000 |
friends | +0.000 |
Neg logit contributions | |
ho | -0.000 |
ited | -0.000 |
solar | -0.000 |
lifetime | -0.000 |
mer | -0.000 |
Token | happily |
Token ID | 18177 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
ho | +0.026 |
ited | +0.024 |
solar | +0.022 |
mer | +0.021 |
lifetime | +0.021 |
Neg logit contributions | |
off | -0.018 |
two | -0.017 |
some | -0.017 |
our | -0.016 |
friends | -0.016 |
Token | headed |
Token ID | 9153 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
ho | +0.019 |
ited | +0.018 |
solar | +0.017 |
mer | +0.016 |
years | +0.016 |
Neg logit contributions | |
off | -0.016 |
two | -0.015 |
some | -0.015 |
friends | -0.014 |
on | -0.014 |
Token | home |
Token ID | 1363 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
ho | +0.033 |
ited | +0.029 |
solar | +0.028 |
lifetime | +0.027 |
thank | +0.027 |
Neg logit contributions | |
adoes | -0.016 |
asuring | -0.014 |
dogs | -0.014 |
two | -0.014 |
cookies | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -5.48e-02 |
Pos logit contributions | |
ho | +0.030 |
ited | +0.028 |
solar | +0.026 |
mer | +0.025 |
lifetime | +0.025 |
Neg logit contributions | |
off | -0.008 |
two | -0.007 |
some | -0.007 |
our | -0.007 |
what | -0.007 |
Token | sav |
Token ID | 6799 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
ho | +0.003 |
ited | +0.002 |
solar | +0.002 |
mer | +0.002 |
years | +0.002 |
Neg logit contributions | |
off | -0.002 |
two | -0.002 |
some | -0.002 |
our | -0.002 |
what | -0.001 |
Token | oring |
Token ID | 3255 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
ho | +0.089 |
ited | +0.078 |
solar | +0.077 |
mer | +0.071 |
lifetime | +0.068 |
Neg logit contributions | |
off | -0.073 |
two | -0.066 |
some | -0.066 |
what | -0.066 |
our | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
off | +0.006 |
some | +0.005 |
two | +0.005 |
our | +0.005 |
what | +0.004 |
Neg logit contributions | |
ho | -0.027 |
ited | -0.026 |
solar | -0.024 |
mer | -0.023 |
lifetime | -0.023 |
Token | taste |
Token ID | 6938 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
ho | +0.022 |
ited | +0.020 |
solar | +0.019 |
mer | +0.018 |
lifetime | +0.018 |
Neg logit contributions | |
off | -0.012 |
two | -0.012 |
some | -0.012 |
our | -0.011 |
what | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | +7.98e-02 |
Pos logit contributions | |
ho | +0.038 |
ited | +0.036 |
solar | +0.035 |
years | +0.033 |
mer | +0.033 |
Neg logit contributions | |
off | -0.005 |
some | -0.004 |
two | -0.003 |
about | -0.003 |
on | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
off | +0.001 |
two | +0.001 |
some | +0.001 |
our | +0.001 |
what | +0.001 |
Neg logit contributions | |
ho | -0.005 |
ited | -0.005 |
solar | -0.005 |
mer | -0.005 |
lifetime | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
ho | +0.042 |
ited | +0.039 |
solar | +0.036 |
mer | +0.036 |
lifetime | +0.035 |
Neg logit contributions | |
off | -0.015 |
two | -0.014 |
some | -0.014 |
our | -0.013 |
what | -0.013 |
Token | " |
Token ID | 366 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
ho | +0.037 |
ited | +0.033 |
solar | +0.031 |
mer | +0.030 |
lifetime | +0.029 |
Neg logit contributions | |
off | -0.013 |
our | -0.011 |
two | -0.011 |
some | -0.011 |
adoes | -0.011 |
Token | Okay |
Token ID | 16454 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
ho | +0.045 |
ited | +0.044 |
solar | +0.040 |
wil | +0.037 |
yt | +0.037 |
Neg logit contributions | |
two | -0.026 |
some | -0.025 |
Zip | -0.025 |
Spot | -0.024 |
off | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
ho | +0.003 |
ited | +0.003 |
mer | +0.003 |
solar | +0.003 |
lifetime | +0.003 |
Neg logit contributions | |
off | -0.002 |
ags | -0.002 |
adoes | -0.002 |
uate | -0.002 |
some | -0.002 |
Token | that |
Token ID | 326 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
ho | +0.018 |
ited | +0.015 |
solar | +0.015 |
lifetime | +0.014 |
commented | +0.013 |
Neg logit contributions | |
ags | -0.010 |
adoes | -0.009 |
off | -0.009 |
uate | -0.008 |
snowball | -0.008 |
Token | sounds |
Token ID | 5238 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
ho | +0.031 |
ited | +0.030 |
years | +0.027 |
solar | +0.027 |
mer | +0.027 |
Neg logit contributions | |
off | -0.010 |
two | -0.010 |
some | -0.010 |
our | -0.009 |
friends | -0.009 |
Token | fun |
Token ID | 1257 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
ho | +0.096 |
ited | +0.088 |
solar | +0.079 |
mer | +0.078 |
lifetime | +0.075 |
Neg logit contributions | |
off | -0.064 |
two | -0.061 |
some | -0.060 |
our | -0.059 |
what | -0.058 |
Token | !" |
Token ID | 2474 |
Feature activation | -9.29e-01 |
Pos logit contributions | |
ho | +0.044 |
ited | +0.041 |
solar | +0.038 |
mer | +0.037 |
lifetime | +0.036 |
Neg logit contributions | |
off | -0.018 |
two | -0.017 |
some | -0.016 |
our | -0.016 |
what | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
ho | +0.054 |
ited | +0.050 |
solar | +0.047 |
mer | +0.045 |
lifetime | +0.045 |
Neg logit contributions | |
off | -0.017 |
two | -0.016 |
our | -0.015 |
some | -0.015 |
what | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
ho | +0.025 |
solar | +0.022 |
ited | +0.022 |
lifetime | +0.020 |
commented | +0.020 |
Neg logit contributions | |
off | -0.012 |
adoes | -0.012 |
two | -0.011 |
our | -0.010 |
asuring | -0.010 |
Token | As |
Token ID | 1722 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ho | +0.027 |
ited | +0.025 |
solar | +0.023 |
mer | +0.022 |
lifetime | +0.022 |
Neg logit contributions | |
off | -0.012 |
two | -0.011 |
some | -0.011 |
our | -0.010 |
what | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
off | +0.007 |
adoes | +0.007 |
two | +0.006 |
our | +0.006 |
my | +0.005 |
Neg logit contributions | |
ho | -0.018 |
ited | -0.016 |
solar | -0.016 |
mer | -0.015 |
lifetime | -0.015 |
Token | As |
Token ID | 1722 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
off | +0.006 |
adoes | +0.005 |
our | +0.005 |
two | +0.005 |
ags | +0.005 |
Neg logit contributions | |
ho | -0.010 |
ited | -0.009 |
solar | -0.008 |
mer | -0.008 |
thank | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -8.32e-01 |
Pos logit contributions | |
ho | +0.056 |
ited | +0.047 |
solar | +0.047 |
lifetime | +0.046 |
spe | +0.043 |
Neg logit contributions | |
ags | -0.031 |
adoes | -0.031 |
asuring | -0.028 |
wounds | -0.026 |
off | -0.025 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ho | +0.039 |
ited | +0.036 |
solar | +0.033 |
lifetime | +0.031 |
mer | +0.031 |
Neg logit contributions | |
off | -0.024 |
adoes | -0.022 |
what | -0.022 |
them | -0.022 |
our | -0.022 |
Token | began |
Token ID | 2540 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
ho | +0.054 |
ited | +0.045 |
mer | +0.040 |
thank | +0.038 |
solar | +0.038 |
Neg logit contributions | |
our | -0.060 |
what | -0.060 |
off | -0.058 |
my | -0.058 |
ags | -0.057 |
Token | to |
Token ID | 284 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
ho | +0.126 |
ited | +0.119 |
solar | +0.111 |
mer | +0.109 |
lifetime | +0.107 |
Neg logit contributions | |
off | -0.021 |
two | -0.018 |
some | -0.018 |
our | -0.017 |
what | -0.015 |
Token | set |
Token ID | 900 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
ho | +0.106 |
ited | +0.098 |
years | +0.091 |
solar | +0.090 |
mer | +0.090 |
Neg logit contributions | |
off | -0.057 |
two | -0.054 |
some | -0.053 |
them | -0.052 |
our | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
ho | +0.049 |
ited | +0.044 |
mer | +0.041 |
solar | +0.041 |
lifetime | +0.039 |
Neg logit contributions | |
off | -0.021 |
two | -0.021 |
our | -0.020 |
some | -0.020 |
what | -0.019 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
ho | +0.009 |
wished | +0.007 |
spe | +0.007 |
thank | +0.007 |
solar | +0.007 |
Neg logit contributions | |
ags | -0.008 |
uate | -0.007 |
asuring | -0.007 |
wounds | -0.007 |
adoes | -0.006 |
Token | knew |
Token ID | 2993 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
ho | +0.010 |
ited | +0.009 |
solar | +0.009 |
years | +0.009 |
mer | +0.009 |
Neg logit contributions | |
off | -0.003 |
two | -0.003 |
friends | -0.003 |
some | -0.003 |
the | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
ho | +0.022 |
wished | +0.018 |
lifetime | +0.018 |
tre | +0.017 |
reality | +0.017 |
Neg logit contributions | |
ags | -0.021 |
adoes | -0.018 |
uate | -0.017 |
off | -0.016 |
< | -0.016 |
Token | could |
Token ID | 714 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
ho | +0.010 |
ited | +0.010 |
solar | +0.009 |
lifetime | +0.009 |
mer | +0.009 |
Neg logit contributions | |
off | -0.009 |
two | -0.009 |
some | -0.009 |
the | -0.009 |
what | -0.009 |
Token | see |
Token ID | 766 |
Feature activation | +5.42e-02 |
Pos logit contributions | |
off | +0.013 |
adoes | +0.013 |
our | +0.013 |
cookies | +0.013 |
two | +0.012 |
Neg logit contributions | |
ho | -0.026 |
ited | -0.024 |
solar | -0.021 |
mer | -0.021 |
thank | -0.021 |
Token | all |
Token ID | 477 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
off | +0.001 |
some | +0.001 |
two | +0.000 |
what | +0.000 |
our | +0.000 |
Neg logit contributions | |
ho | -0.004 |
ited | -0.004 |
mer | -0.003 |
solar | -0.003 |
lifetime | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
off | +0.019 |
two | +0.018 |
some | +0.018 |
our | +0.018 |
what | +0.017 |
Neg logit contributions | |
ho | -0.019 |
ited | -0.017 |
solar | -0.015 |
mer | -0.014 |
lifetime | -0.014 |
Token | ig |
Token ID | 45329 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
ho | +0.012 |
ited | +0.011 |
solar | +0.010 |
mer | +0.010 |
lifetime | +0.010 |
Neg logit contributions | |
off | -0.005 |
two | -0.005 |
some | -0.005 |
our | -0.005 |
what | -0.004 |
Token | lo |
Token ID | 5439 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
off | +0.026 |
two | +0.024 |
some | +0.024 |
our | +0.024 |
Spot | +0.023 |
Neg logit contributions | |
ho | -0.033 |
ited | -0.030 |
mer | -0.026 |
solar | -0.026 |
lifetime | -0.025 |
Token | os |
Token ID | 418 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
off | +0.085 |
two | +0.081 |
some | +0.080 |
our | +0.080 |
what | +0.077 |
Neg logit contributions | |
ho | -0.093 |
ited | -0.083 |
mer | -0.073 |
solar | -0.073 |
lifetime | -0.068 |
Token | in |
Token ID | 287 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
off | +0.028 |
two | +0.026 |
some | +0.026 |
our | +0.025 |
what | +0.025 |
Neg logit contributions | |
ho | -0.053 |
ited | -0.049 |
solar | -0.045 |
mer | -0.043 |
lifetime | -0.043 |
Token | their |
Token ID | 511 |
Feature activation | -5.07e-02 |
Pos logit contributions | |
two | +0.001 |
off | +0.001 |
some | +0.001 |
our | +0.001 |
them | +0.001 |
Neg logit contributions | |
ho | -0.023 |
ited | -0.022 |
solar | -0.020 |
mer | -0.020 |
lifetime | -0.020 |
Token | bright |
Token ID | 6016 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
ho | +0.003 |
ited | +0.003 |
thank | +0.002 |
mer | +0.002 |
solar | +0.002 |
Neg logit contributions | |
off | -0.001 |
two | -0.001 |
friends | -0.001 |
our | -0.001 |
mom | -0.001 |
Token | colours |
Token ID | 18915 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
ho | +0.016 |
ited | +0.015 |
solar | +0.014 |
mer | +0.013 |
lifetime | +0.013 |
Neg logit contributions | |
off | -0.008 |
two | -0.008 |
some | -0.008 |
our | -0.008 |
what | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
off | +0.014 |
asuring | +0.013 |
ags | +0.012 |
two | +0.012 |
about | +0.011 |
Neg logit contributions | |
ho | -0.078 |
ited | -0.071 |
solar | -0.069 |
wished | -0.066 |
commented | -0.065 |
Token | coal |
Token ID | 5655 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
off | +0.009 |
two | +0.008 |
some | +0.008 |
our | +0.008 |
what | +0.008 |
Neg logit contributions | |
ho | -0.020 |
ited | -0.018 |
solar | -0.017 |
mer | -0.017 |
lifetime | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
off | +0.027 |
two | +0.026 |
our | +0.025 |
some | +0.025 |
what | +0.024 |
Neg logit contributions | |
ho | -0.060 |
ited | -0.054 |
solar | -0.050 |
mer | -0.049 |
lifetime | -0.047 |
Token | She |
Token ID | 1375 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
off | +0.028 |
two | +0.027 |
some | +0.026 |
our | +0.026 |
what | +0.025 |
Neg logit contributions | |
ho | -0.041 |
ited | -0.037 |
solar | -0.034 |
mer | -0.033 |
lifetime | -0.032 |
Token | is |
Token ID | 318 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
off | +0.048 |
icle | +0.046 |
adoes | +0.045 |
icles | +0.044 |
some | +0.043 |
Neg logit contributions | |
ho | -0.054 |
ited | -0.046 |
solar | -0.045 |
wished | -0.041 |
ad | -0.040 |
Token | not |
Token ID | 407 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
adoes | +0.036 |
icles | +0.035 |
off | +0.035 |
icle | +0.034 |
Zip | +0.032 |
Neg logit contributions | |
ho | -0.038 |
years | -0.033 |
wished | -0.033 |
ad | -0.032 |
ited | -0.032 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
off | +0.082 |
two | +0.078 |
some | +0.077 |
our | +0.076 |
what | +0.074 |
Neg logit contributions | |
ho | -0.101 |
ited | -0.092 |
solar | -0.082 |
mer | -0.080 |
lifetime | -0.078 |
Token | . |
Token ID | 13 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
off | +0.014 |
two | +0.014 |
our | +0.013 |
some | +0.013 |
Zip | +0.013 |
Neg logit contributions | |
ho | -0.021 |
ited | -0.019 |
solar | -0.017 |
mer | -0.017 |
thank | -0.016 |
Token | She |
Token ID | 1375 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
off | +0.020 |
two | +0.019 |
some | +0.019 |
our | +0.018 |
what | +0.018 |
Neg logit contributions | |
ho | -0.033 |
ited | -0.030 |
solar | -0.027 |
mer | -0.027 |
lifetime | -0.026 |
Token | tells |
Token ID | 4952 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
off | +0.047 |
adoes | +0.044 |
some | +0.043 |
our | +0.043 |
two | +0.042 |
Neg logit contributions | |
ho | -0.063 |
ited | -0.057 |
solar | -0.052 |
wished | -0.049 |
ad | -0.048 |
Token | Ben |
Token ID | 3932 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
asuring | +0.015 |
snowball | +0.015 |
adoes | +0.014 |
off | +0.014 |
< | +0.014 |
Neg logit contributions | |
ho | -0.057 |
ited | -0.047 |
years | -0.046 |
solar | -0.045 |
wished | -0.043 |
Token | joy |
Token ID | 8716 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
ho | +0.017 |
ited | +0.016 |
solar | +0.015 |
mer | +0.015 |
lifetime | +0.014 |
Neg logit contributions | |
off | -0.007 |
two | -0.006 |
some | -0.006 |
our | -0.006 |
what | -0.006 |
Token | with |
Token ID | 351 |
Feature activation | -9.81e-01 |
Pos logit contributions | |
Rex | +0.001 |
Buddy | +0.001 |
Zip | +0.001 |
uate | +0.001 |
dogs | +0.001 |
Neg logit contributions | |
ho | -0.002 |
ited | -0.002 |
mer | -0.002 |
thank | -0.002 |
ad | -0.002 |
Token | you |
Token ID | 345 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
ho | +0.060 |
ited | +0.056 |
solar | +0.052 |
mer | +0.052 |
lifetime | +0.050 |
Neg logit contributions | |
off | -0.015 |
two | -0.014 |
some | -0.013 |
our | -0.013 |
what | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
ho | +0.001 |
ited | +0.001 |
solar | +0.001 |
mer | +0.001 |
years | +0.001 |
Neg logit contributions | |
off | -0.000 |
two | -0.000 |
some | -0.000 |
our | -0.000 |
what | -0.000 |
Token | Aren |
Token ID | 9843 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
ho | +0.012 |
solar | +0.011 |
ited | +0.010 |
mer | +0.009 |
lifetime | +0.009 |
Neg logit contributions | |
off | -0.010 |
adoes | -0.009 |
ags | -0.009 |
them | -0.009 |
cookies | -0.009 |
Token | 't |
Token ID | 470 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
ho | +0.027 |
ited | +0.024 |
years | +0.024 |
thank | +0.023 |
well | +0.023 |
Neg logit contributions | |
adoes | -0.021 |
off | -0.020 |
snowball | -0.020 |
wounds | -0.019 |
sled | -0.019 |
Token | you |
Token ID | 345 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
ags | +0.072 |
off | +0.065 |
snowball | +0.064 |
< | +0.063 |
Zip | +0.062 |
Neg logit contributions | |
ho | -0.135 |
ited | -0.114 |
ad | -0.112 |
wished | -0.111 |
commented | -0.110 |
Token | glad |
Token ID | 9675 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
Zip | +0.022 |
Rex | +0.022 |
snowball | +0.021 |
off | +0.021 |
adoes | +0.021 |
Neg logit contributions | |
ho | -0.023 |
ited | -0.022 |
thank | -0.021 |
solar | -0.020 |
lifetime | -0.019 |
Token | that |
Token ID | 326 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
snowball | +0.012 |
ags | +0.011 |
< | +0.011 |
two | +0.010 |
off | +0.010 |
Neg logit contributions | |
ho | -0.018 |
ad | -0.014 |
commented | -0.014 |
solar | -0.014 |
wished | -0.014 |
Token | you |
Token ID | 345 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
off | +0.006 |
two | +0.006 |
some | +0.005 |
adoes | +0.005 |
what | +0.005 |
Neg logit contributions | |
ho | -0.017 |
ited | -0.015 |
solar | -0.014 |
mer | -0.014 |
lifetime | -0.014 |
Token | are |
Token ID | 389 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
off | +0.005 |
two | +0.005 |
some | +0.004 |
our | +0.004 |
what | +0.004 |
Neg logit contributions | |
ho | -0.008 |
ited | -0.008 |
solar | -0.007 |
mer | -0.007 |
lifetime | -0.007 |
Token | friends |
Token ID | 2460 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
ags | +0.009 |
adoes | +0.007 |
our | +0.007 |
snowball | +0.007 |
icles | +0.007 |
Neg logit contributions | |
ho | -0.037 |
solar | -0.032 |
ited | -0.031 |
ad | -0.031 |
wished | -0.031 |
Token | about |
Token ID | 546 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
off | +0.005 |
two | +0.004 |
our | +0.004 |
adoes | +0.003 |
some | +0.003 |
Neg logit contributions | |
ho | -0.042 |
ited | -0.039 |
solar | -0.036 |
mer | -0.035 |
lifetime | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
ho | +0.025 |
ited | +0.023 |
solar | +0.022 |
mer | +0.021 |
lifetime | +0.021 |
Neg logit contributions | |
off | -0.006 |
two | -0.005 |
our | -0.005 |
some | -0.005 |
adoes | -0.005 |
Token | weird |
Token ID | 7650 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
two | +0.006 |
friends | +0.006 |
some | +0.006 |
off | +0.006 |
mom | +0.006 |
Neg logit contributions | |
ho | -0.011 |
ited | -0.010 |
years | -0.009 |
mer | -0.009 |
solar | -0.009 |
Token | l |
Token ID | 300 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
off | +0.012 |
two | +0.012 |
some | +0.012 |
friends | +0.012 |
what | +0.011 |
Neg logit contributions | |
ho | -0.026 |
ited | -0.024 |
solar | -0.022 |
years | -0.021 |
mer | -0.021 |
Token | oll |
Token ID | 692 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
ho | +0.019 |
ited | +0.017 |
solar | +0.016 |
lifetime | +0.015 |
mer | +0.015 |
Neg logit contributions | |
off | -0.010 |
two | -0.010 |
some | -0.009 |
about | -0.009 |
friends | -0.009 |
Token | ipop |
Token ID | 42800 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
off | +0.076 |
two | +0.072 |
some | +0.072 |
what | +0.071 |
friends | +0.069 |
Neg logit contributions | |
ho | -0.115 |
ited | -0.107 |
solar | -0.103 |
mer | -0.095 |
lifetime | -0.094 |
Token | . |
Token ID | 13 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
off | +0.008 |
some | +0.008 |
on | +0.008 |
two | +0.008 |
about | +0.008 |
Neg logit contributions | |
ho | -0.024 |
ited | -0.023 |
solar | -0.022 |
years | -0.021 |
mer | -0.021 |
Token | They |
Token ID | 1119 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
ho | +0.014 |
ited | +0.014 |
mer | +0.012 |
solar | +0.012 |
lifetime | +0.012 |
Neg logit contributions | |
off | -0.007 |
two | -0.006 |
some | -0.006 |
Spot | -0.006 |
about | -0.006 |
Token | all |
Token ID | 477 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
two | +0.001 |
off | +0.001 |
some | +0.001 |
friends | +0.001 |
what | +0.001 |
Neg logit contributions | |
ho | -0.002 |
ited | -0.002 |
mer | -0.002 |
solar | -0.002 |
lifetime | -0.002 |
Token | thought |
Token ID | 1807 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
off | +0.015 |
about | +0.014 |
over | +0.014 |
two | +0.014 |
the | +0.014 |
Neg logit contributions | |
ho | -0.020 |
mer | -0.016 |
solar | -0.016 |
ited | -0.016 |
lifetime | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
off | +0.015 |
two | +0.014 |
ags | +0.014 |
adoes | +0.013 |
asuring | +0.013 |
Neg logit contributions | |
ho | -0.055 |
ited | -0.050 |
solar | -0.048 |
wished | -0.045 |
years | -0.045 |
Token | ring |
Token ID | 5858 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
off | +0.013 |
our | +0.011 |
some | +0.011 |
two | +0.011 |
what | +0.011 |
Neg logit contributions | |
ho | -0.022 |
ited | -0.020 |
solar | -0.019 |
mer | -0.018 |
lifetime | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
off | +0.004 |
two | +0.004 |
our | +0.004 |
some | +0.004 |
Buddy | +0.004 |
Neg logit contributions | |
ho | -0.011 |
ited | -0.009 |
mer | -0.009 |
solar | -0.009 |
lifetime | -0.008 |
Token | She |
Token ID | 1375 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
off | +0.026 |
two | +0.024 |
some | +0.024 |
our | +0.024 |
what | +0.023 |
Neg logit contributions | |
ho | -0.036 |
ited | -0.032 |
solar | -0.030 |
mer | -0.029 |
lifetime | -0.028 |
Token | is |
Token ID | 318 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
off | +0.044 |
icle | +0.042 |
adoes | +0.042 |
icles | +0.041 |
ags | +0.041 |
Neg logit contributions | |
ho | -0.054 |
ited | -0.045 |
solar | -0.044 |
wished | -0.041 |
ad | -0.040 |
Token | not |
Token ID | 407 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
adoes | +0.035 |
off | +0.034 |
icles | +0.033 |
Buddy | +0.031 |
icle | +0.031 |
Neg logit contributions | |
ho | -0.042 |
years | -0.035 |
ited | -0.035 |
ad | -0.034 |
wished | -0.034 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
off | +0.080 |
two | +0.076 |
some | +0.075 |
our | +0.074 |
what | +0.073 |
Neg logit contributions | |
ho | -0.111 |
ited | -0.101 |
solar | -0.092 |
mer | -0.089 |
lifetime | -0.086 |
Token | . |
Token ID | 13 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
off | +0.014 |
two | +0.013 |
our | +0.013 |
some | +0.013 |
adoes | +0.012 |
Neg logit contributions | |
ho | -0.021 |
ited | -0.018 |
solar | -0.017 |
mer | -0.016 |
thank | -0.016 |
Token | She |
Token ID | 1375 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
off | +0.017 |
two | +0.016 |
some | +0.015 |
our | +0.015 |
what | +0.015 |
Neg logit contributions | |
ho | -0.027 |
ited | -0.025 |
solar | -0.023 |
mer | -0.022 |
lifetime | -0.022 |
Token | tells |
Token ID | 4952 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
off | +0.042 |
adoes | +0.040 |
some | +0.039 |
our | +0.039 |
two | +0.038 |
Neg logit contributions | |
ho | -0.059 |
ited | -0.053 |
solar | -0.049 |
wished | -0.046 |
ad | -0.045 |
Token | Tom |
Token ID | 4186 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
asuring | +0.021 |
off | +0.021 |
adoes | +0.021 |
ags | +0.020 |
on | +0.019 |
Neg logit contributions | |
ho | -0.042 |
ited | -0.034 |
years | -0.033 |
solar | -0.032 |
generation | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
off | +0.003 |
two | +0.003 |
adoes | +0.003 |
our | +0.003 |
Zip | +0.002 |
Neg logit contributions | |
ho | -0.013 |
ited | -0.012 |
solar | -0.011 |
mer | -0.011 |
lifetime | -0.011 |
Token | scream |
Token ID | 8196 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
ho | +0.020 |
ited | +0.017 |
solar | +0.017 |
generation | +0.016 |
thank | +0.016 |
Neg logit contributions | |
adoes | -0.012 |
off | -0.011 |
ags | -0.011 |
two | -0.011 |
asuring | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
ho | +0.016 |
ited | +0.015 |
solar | +0.013 |
mer | +0.013 |
lifetime | +0.013 |
Neg logit contributions | |
off | -0.006 |
two | -0.006 |
our | -0.006 |
some | -0.006 |
what | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
ho | +0.015 |
ited | +0.013 |
solar | +0.012 |
lifetime | +0.012 |
mer | +0.012 |
Neg logit contributions | |
off | -0.007 |
our | -0.007 |
adoes | -0.007 |
two | -0.007 |
cookies | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
ho | +0.008 |
ited | +0.007 |
solar | +0.006 |
lifetime | +0.006 |
years | +0.006 |
Neg logit contributions | |
adoes | -0.003 |
off | -0.003 |
cookies | -0.003 |
our | -0.003 |
dogs | -0.003 |
Token | His |
Token ID | 6653 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
ho | +0.007 |
ited | +0.006 |
lifetime | +0.006 |
solar | +0.006 |
years | +0.005 |
Neg logit contributions | |
off | -0.004 |
adoes | -0.004 |
dogs | -0.004 |
cookies | -0.004 |
ags | -0.004 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
off | +0.007 |
our | +0.006 |
adoes | +0.006 |
them | +0.006 |
some | +0.006 |
Neg logit contributions | |
ho | -0.048 |
ited | -0.044 |
solar | -0.042 |
lifetime | -0.040 |
mer | -0.040 |
Token | went |
Token ID | 1816 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
ho | +0.009 |
ited | +0.008 |
solar | +0.007 |
mer | +0.007 |
lifetime | +0.007 |
Neg logit contributions | |
off | -0.007 |
two | -0.007 |
some | -0.006 |
our | -0.006 |
what | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
adoes | +0.012 |
asuring | +0.011 |
icles | +0.011 |
uate | +0.010 |
icle | +0.010 |
Neg logit contributions | |
ho | -0.026 |
ited | -0.022 |
mer | -0.021 |
solar | -0.021 |
years | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
adoes | +0.013 |
off | +0.012 |
asuring | +0.012 |
uate | +0.011 |
ags | +0.011 |
Neg logit contributions | |
ho | -0.031 |
ited | -0.028 |
solar | -0.026 |
commented | -0.025 |
thank | -0.025 |
Token | kitchen |
Token ID | 9592 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
off | +0.016 |
two | +0.015 |
some | +0.015 |
our | +0.014 |
what | +0.014 |
Neg logit contributions | |
ho | -0.028 |
ited | -0.026 |
solar | -0.023 |
mer | -0.023 |
lifetime | -0.022 |
Token | would |
Token ID | 561 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
ho | +0.000 |
ited | +0.000 |
solar | +0.000 |
lifetime | +0.000 |
years | +0.000 |
Neg logit contributions | |
two | -0.000 |
some | -0.000 |
what | -0.000 |
about | -0.000 |
off | -0.000 |
Token | like |
Token ID | 588 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
off | +0.015 |
some | +0.014 |
two | +0.014 |
our | +0.014 |
what | +0.014 |
Neg logit contributions | |
ho | -0.037 |
ited | -0.034 |
mer | -0.031 |
solar | -0.031 |
years | -0.030 |
Token | ?" |
Token ID | 1701 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
ho | +0.037 |
ited | +0.035 |
solar | +0.032 |
mer | +0.032 |
lifetime | +0.031 |
Neg logit contributions | |
off | -0.008 |
two | -0.007 |
some | -0.007 |
our | -0.007 |
what | -0.007 |
Token | Mom |
Token ID | 11254 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
off | +0.001 |
two | +0.001 |
adoes | +0.001 |
some | +0.001 |
our | +0.001 |
Neg logit contributions | |
ho | -0.004 |
ited | -0.004 |
solar | -0.004 |
mer | -0.003 |
years | -0.003 |
Token | said |
Token ID | 531 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
off | +0.001 |
our | +0.001 |
some | +0.001 |
adoes | +0.001 |
two | +0.001 |
Neg logit contributions | |
ho | -0.001 |
ited | -0.001 |
solar | -0.001 |
mer | -0.001 |
years | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
off | +0.022 |
some | +0.020 |
two | +0.019 |
about | +0.019 |
what | +0.018 |
Neg logit contributions | |
ho | -0.052 |
ited | -0.050 |
solar | -0.046 |
lifetime | -0.044 |
mer | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
off | +0.019 |
adoes | +0.018 |
our | +0.017 |
what | +0.016 |
some | +0.016 |
Neg logit contributions | |
ho | -0.045 |
ited | -0.040 |
solar | -0.039 |
mer | -0.037 |
commented | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
off | +0.010 |
adoes | +0.010 |
some | +0.008 |
two | +0.008 |
asuring | +0.008 |
Neg logit contributions | |
ho | -0.023 |
ited | -0.021 |
solar | -0.020 |
mer | -0.019 |
commented | -0.019 |
Token | Anna |
Token ID | 31160 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
off | +0.009 |
two | +0.009 |
some | +0.009 |
our | +0.009 |
what | +0.008 |
Neg logit contributions | |
ho | -0.017 |
ited | -0.015 |
solar | -0.014 |
mer | -0.014 |
lifetime | -0.013 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
ho | +0.026 |
ited | +0.024 |
solar | +0.022 |
mer | +0.021 |
lifetime | +0.021 |
Neg logit contributions | |
off | -0.012 |
two | -0.012 |
some | -0.012 |
our | -0.011 |
what | -0.011 |
Token | for |
Token ID | 329 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
ho | +0.010 |
ited | +0.009 |
solar | +0.009 |
mer | +0.009 |
lifetime | +0.008 |
Neg logit contributions | |
off | -0.003 |
two | -0.002 |
some | -0.002 |
our | -0.002 |
adoes | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
off | +0.001 |
adoes | +0.001 |
our | +0.001 |
two | +0.001 |
some | +0.001 |
Neg logit contributions | |
ho | -0.003 |
ited | -0.002 |
solar | -0.002 |
mer | -0.002 |
lifetime | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
off | +0.004 |
adoes | +0.003 |
our | +0.003 |
two | +0.003 |
some | +0.003 |
Neg logit contributions | |
ho | -0.022 |
ited | -0.020 |
solar | -0.019 |
mer | -0.019 |
lifetime | -0.018 |
Token | little |
Token ID | 1310 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
ho | +0.016 |
ited | +0.016 |
solar | +0.014 |
years | +0.014 |
mer | +0.014 |
Neg logit contributions | |
two | -0.004 |
mom | -0.004 |
Spot | -0.004 |
friends | -0.004 |
our | -0.004 |
Token | girl |
Token ID | 2576 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
ho | +0.016 |
ited | +0.014 |
solar | +0.013 |
mer | +0.013 |
lifetime | +0.012 |
Neg logit contributions | |
off | -0.012 |
two | -0.011 |
some | -0.011 |
our | -0.011 |
what | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | -8.32e-02 |
Pos logit contributions | |
ho | +0.016 |
ited | +0.016 |
lifetime | +0.014 |
mer | +0.014 |
solar | +0.014 |
Neg logit contributions | |
some | -0.009 |
on | -0.009 |
the | -0.009 |
two | -0.009 |
off | -0.008 |
Token | playing |
Token ID | 2712 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
ho | +0.005 |
ited | +0.005 |
mer | +0.004 |
solar | +0.004 |
lifetime | +0.004 |
Neg logit contributions | |
off | -0.002 |
two | -0.002 |
some | -0.002 |
friends | -0.002 |
our | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
off | +0.011 |
our | +0.010 |
two | +0.010 |
adoes | +0.009 |
what | +0.009 |
Neg logit contributions | |
ho | -0.040 |
ited | -0.037 |
solar | -0.035 |
mer | -0.035 |
thank | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
ho | +0.018 |
ited | +0.016 |
solar | +0.015 |
mer | +0.015 |
years | +0.015 |
Neg logit contributions | |
off | -0.006 |
two | -0.005 |
adoes | -0.005 |
our | -0.005 |
about | -0.005 |
Token | park |
Token ID | 3952 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
ho | +0.025 |
ited | +0.023 |
solar | +0.021 |
mer | +0.020 |
lifetime | +0.020 |
Neg logit contributions | |
off | -0.017 |
two | -0.016 |
some | -0.016 |
our | -0.016 |
what | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
ho | +0.026 |
ited | +0.026 |
solar | +0.024 |
lifetime | +0.024 |
mer | +0.023 |
Neg logit contributions | |
some | -0.007 |
two | -0.006 |
on | -0.006 |
off | -0.006 |
about | -0.005 |
Token | She |
Token ID | 1375 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
off | +0.002 |
two | +0.002 |
some | +0.002 |
our | +0.002 |
what | +0.002 |
Neg logit contributions | |
ho | -0.003 |
ited | -0.002 |
solar | -0.002 |
mer | -0.002 |
lifetime | -0.002 |
Token | Don |
Token ID | 3987 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
ho | +0.002 |
ited | +0.002 |
solar | +0.001 |
mer | +0.001 |
lifetime | +0.001 |
Neg logit contributions | |
off | -0.002 |
two | -0.002 |
some | -0.002 |
our | -0.002 |
what | -0.002 |
Token | 't |
Token ID | 470 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ho | +0.009 |
ited | +0.007 |
well | +0.007 |
mer | +0.007 |
lder | +0.006 |
Neg logit contributions | |
wounds | -0.007 |
adoes | -0.007 |
ags | -0.007 |
snowball | -0.006 |
what | -0.006 |
Token | worry |
Token ID | 5490 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ags | +0.046 |
some | +0.044 |
off | +0.044 |
two | +0.043 |
them | +0.043 |
Neg logit contributions | |
ho | -0.052 |
ited | -0.045 |
mer | -0.036 |
solar | -0.035 |
lifetime | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
ags | +0.038 |
two | +0.032 |
< | +0.032 |
some | +0.031 |
asuring | +0.031 |
Neg logit contributions | |
ho | -0.047 |
yt | -0.035 |
mer | -0.034 |
ited | -0.034 |
de | -0.034 |
Token | I |
Token ID | 314 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
ho | +0.006 |
ited | +0.005 |
spe | +0.005 |
wished | +0.005 |
mer | +0.005 |
Neg logit contributions | |
ags | -0.004 |
off | -0.003 |
< | -0.003 |
over | -0.003 |
adoes | -0.003 |
Token | will |
Token ID | 481 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
off | +0.008 |
two | +0.007 |
some | +0.007 |
our | +0.007 |
what | +0.007 |
Neg logit contributions | |
ho | -0.011 |
ited | -0.010 |
solar | -0.009 |
mer | -0.009 |
lifetime | -0.009 |
Token | help |
Token ID | 1037 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
off | +0.016 |
two | +0.015 |
some | +0.014 |
our | +0.014 |
what | +0.014 |
Neg logit contributions | |
ho | -0.037 |
ited | -0.034 |
solar | -0.032 |
mer | -0.031 |
lifetime | -0.030 |
Token | you |
Token ID | 345 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
adoes | +0.010 |
ags | +0.010 |
two | +0.009 |
off | +0.009 |
asuring | +0.009 |
Neg logit contributions | |
ho | -0.016 |
mer | -0.013 |
ited | -0.013 |
thank | -0.013 |
ad | -0.012 |
Token | ." |
Token ID | 526 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
Rex | +0.009 |
Spot | +0.009 |
adoes | +0.009 |
Buddy | +0.009 |
Zip | +0.008 |
Neg logit contributions | |
ho | -0.013 |
ited | -0.012 |
mer | -0.011 |
thank | -0.011 |
solar | -0.011 |
Token | So |
Token ID | 1406 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
ho | +0.025 |
ited | +0.022 |
thank | +0.021 |
mer | +0.021 |
commented | +0.020 |
Neg logit contributions | |
adoes | -0.012 |
off | -0.012 |
our | -0.011 |
ags | -0.011 |
two | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
ho | +0.022 |
ited | +0.019 |
mer | +0.017 |
solar | +0.017 |
lifetime | +0.017 |
Neg logit contributions | |
ags | -0.010 |
off | -0.009 |
adoes | -0.009 |
< | -0.009 |
our | -0.009 |
Token | were |
Token ID | 547 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
off | +0.007 |
two | +0.007 |
some | +0.007 |
what | +0.006 |
them | +0.006 |
Neg logit contributions | |
ho | -0.011 |
ited | -0.011 |
solar | -0.009 |
mer | -0.009 |
lifetime | -0.009 |
Token | swings |
Token ID | 26728 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
ho | +0.020 |
ited | +0.018 |
solar | +0.017 |
mer | +0.016 |
lifetime | +0.016 |
Neg logit contributions | |
off | -0.009 |
our | -0.009 |
two | -0.009 |
some | -0.009 |
adoes | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
ho | +0.019 |
ited | +0.017 |
solar | +0.016 |
mer | +0.016 |
lifetime | +0.015 |
Neg logit contributions | |
off | -0.005 |
two | -0.004 |
our | -0.004 |
some | -0.004 |
what | -0.004 |
Token | slides |
Token ID | 19392 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
off | +0.013 |
adoes | +0.012 |
ags | +0.011 |
our | +0.011 |
about | +0.011 |
Neg logit contributions | |
ho | -0.032 |
ited | -0.029 |
solar | -0.027 |
lifetime | -0.027 |
years | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
ho | +0.022 |
ited | +0.020 |
solar | +0.019 |
mer | +0.019 |
lifetime | +0.018 |
Neg logit contributions | |
off | -0.006 |
two | -0.005 |
some | -0.005 |
our | -0.005 |
what | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
ho | +0.016 |
ited | +0.015 |
solar | +0.014 |
mer | +0.014 |
lifetime | +0.013 |
Neg logit contributions | |
off | -0.006 |
our | -0.006 |
adoes | -0.006 |
two | -0.005 |
ags | -0.005 |
Token | he |
Token ID | 339 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
off | +0.017 |
our | +0.015 |
two | +0.014 |
some | +0.014 |
adoes | +0.014 |
Neg logit contributions | |
ho | -0.042 |
ited | -0.039 |
solar | -0.036 |
mer | -0.035 |
lifetime | -0.035 |
Token | was |
Token ID | 373 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
ho | +0.035 |
ited | +0.033 |
solar | +0.029 |
mer | +0.028 |
lifetime | +0.028 |
Neg logit contributions | |
off | -0.020 |
two | -0.020 |
some | -0.019 |
friends | -0.019 |
over | -0.018 |
Token | so |
Token ID | 523 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
ho | +0.009 |
ited | +0.008 |
solar | +0.007 |
mer | +0.007 |
lifetime | +0.007 |
Neg logit contributions | |
off | -0.004 |
two | -0.004 |
some | -0.004 |
our | -0.004 |
what | -0.004 |
Token | happy |
Token ID | 3772 |
Feature activation | +9.62e-02 |
Pos logit contributions | |
two | +0.004 |
off | +0.004 |
friends | +0.004 |
some | +0.004 |
the | +0.004 |
Neg logit contributions | |
ho | -0.006 |
ited | -0.006 |
solar | -0.005 |
mer | -0.005 |
generation | -0.005 |
Token | ! |
Token ID | 0 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
off | +0.003 |
two | +0.003 |
our | +0.002 |
some | +0.002 |
adoes | +0.002 |
Neg logit contributions | |
ho | -0.005 |
ited | -0.004 |
solar | -0.004 |
mer | -0.004 |
lifetime | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
ho | +0.034 |
ited | +0.031 |
solar | +0.030 |
mer | +0.029 |
years | +0.028 |
Neg logit contributions | |
off | -0.007 |
two | -0.006 |
our | -0.005 |
some | -0.005 |
what | -0.005 |
Token | but |
Token ID | 475 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
ho | +0.018 |
ited | +0.016 |
ad | +0.015 |
solar | +0.015 |
commented | +0.014 |
Neg logit contributions | |
off | -0.014 |
adoes | -0.014 |
ags | -0.014 |
our | -0.014 |
uate | -0.013 |
Token | today |
Token ID | 1909 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
ho | +0.024 |
ited | +0.021 |
solar | +0.020 |
mer | +0.019 |
lifetime | +0.018 |
Neg logit contributions | |
off | -0.014 |
two | -0.013 |
some | -0.013 |
our | -0.013 |
what | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
ho | +0.036 |
ited | +0.033 |
solar | +0.030 |
mer | +0.029 |
lifetime | +0.028 |
Neg logit contributions | |
off | -0.019 |
two | -0.019 |
our | -0.018 |
some | -0.018 |
adoes | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
ho | +0.015 |
ited | +0.013 |
solar | +0.012 |
mer | +0.012 |
lifetime | +0.012 |
Neg logit contributions | |
off | -0.008 |
two | -0.008 |
our | -0.008 |
some | -0.008 |
what | -0.008 |
Token | very |
Token ID | 845 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
ho | +0.040 |
ited | +0.037 |
solar | +0.033 |
mer | +0.033 |
lifetime | +0.032 |
Neg logit contributions | |
off | -0.021 |
two | -0.020 |
some | -0.020 |
our | -0.019 |
what | -0.019 |
Token | hot |
Token ID | 3024 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
off | +0.004 |
two | +0.004 |
some | +0.004 |
mom | +0.004 |
my | +0.003 |
Neg logit contributions | |
ho | -0.008 |
ited | -0.007 |
solar | -0.007 |
mer | -0.007 |
lifetime | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
ho | +0.049 |
ited | +0.045 |
solar | +0.042 |
mer | +0.041 |
thank | +0.039 |
Neg logit contributions | |
off | -0.018 |
two | -0.017 |
our | -0.017 |
some | -0.016 |
what | -0.016 |
Token | She |
Token ID | 1375 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
off | +0.008 |
our | +0.008 |
adoes | +0.008 |
two | +0.007 |
asuring | +0.007 |
Neg logit contributions | |
ho | -0.009 |
ited | -0.008 |
solar | -0.008 |
commented | -0.007 |
thank | -0.007 |
Token | asked |
Token ID | 1965 |
Feature activation | +7.80e-02 |
Pos logit contributions | |
off | +0.007 |
two | +0.006 |
some | +0.006 |
Spot | +0.006 |
friends | +0.006 |
Neg logit contributions | |
ho | -0.008 |
ited | -0.007 |
solar | -0.006 |
mer | -0.006 |
lifetime | -0.006 |
Token | her |
Token ID | 607 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
off | +0.002 |
two | +0.002 |
our | +0.002 |
adoes | +0.002 |
Zip | +0.002 |
Neg logit contributions | |
ho | -0.004 |
ited | -0.003 |
solar | -0.003 |
years | -0.003 |
ad | -0.003 |
Token | friendly |
Token ID | 8030 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
ho | +0.011 |
ited | +0.010 |
solar | +0.009 |
mer | +0.009 |
lifetime | +0.009 |
Neg logit contributions | |
off | -0.006 |
two | -0.005 |
our | -0.005 |
some | -0.005 |
adoes | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
ho | +0.029 |
ited | +0.028 |
solar | +0.026 |
mer | +0.025 |
lifetime | +0.025 |
Neg logit contributions | |
off | -0.007 |
some | -0.006 |
two | -0.006 |
about | -0.006 |
what | -0.006 |
Token | said |
Token ID | 531 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
off | +0.001 |
two | +0.001 |
some | +0.001 |
our | +0.001 |
what | +0.001 |
Neg logit contributions | |
ho | -0.002 |
ited | -0.002 |
solar | -0.002 |
mer | -0.002 |
years | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -6.40e-02 |
Pos logit contributions | |
ho | +0.007 |
ited | +0.006 |
solar | +0.006 |
mer | +0.006 |
lifetime | +0.006 |
Neg logit contributions | |
off | -0.003 |
two | -0.002 |
some | -0.002 |
our | -0.002 |
what | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ho | +0.004 |
ited | +0.003 |
solar | +0.003 |
mer | +0.003 |
lifetime | +0.003 |
Neg logit contributions | |
off | -0.001 |
two | -0.001 |
our | -0.001 |
some | -0.001 |
friends | -0.001 |
Token | Come |
Token ID | 16773 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
two | +0.004 |
off | +0.004 |
some | +0.004 |
them | +0.004 |
our | +0.004 |
Neg logit contributions | |
ho | -0.006 |
ited | -0.005 |
solar | -0.005 |
mer | -0.005 |
lifetime | -0.005 |
Token | closer |
Token ID | 5699 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
ho | +0.013 |
mer | +0.011 |
ited | +0.011 |
thank | +0.011 |
lifetime | +0.011 |
Neg logit contributions | |
adoes | -0.006 |
cables | -0.005 |
icles | -0.005 |
uate | -0.005 |
dogs | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
off | +0.003 |
two | +0.003 |
some | +0.003 |
our | +0.002 |
adoes | +0.002 |
Neg logit contributions | |
ho | -0.009 |
ited | -0.008 |
solar | -0.008 |
mer | -0.008 |
lifetime | -0.007 |
Token | join |
Token ID | 4654 |
Feature activation | -6.51e-02 |
Pos logit contributions | |
adoes | +0.013 |
ags | +0.012 |
off | +0.012 |
cookies | +0.012 |
icles | +0.012 |
Neg logit contributions | |
ho | -0.020 |
ited | -0.018 |
solar | -0.016 |
mer | -0.016 |
thank | -0.016 |
Token | me |
Token ID | 502 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
ho | +0.004 |
ited | +0.004 |
solar | +0.003 |
mer | +0.003 |
years | +0.003 |
Neg logit contributions | |
off | -0.001 |
adoes | -0.001 |
two | -0.001 |
some | -0.001 |
cookies | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | +7.83e-02 |
Pos logit contributions | |
off | +0.014 |
two | +0.013 |
some | +0.013 |
our | +0.013 |
adoes | +0.013 |
Neg logit contributions | |
ho | -0.032 |
ited | -0.029 |
solar | -0.027 |
mer | -0.027 |
lifetime | -0.026 |
Token | not |
Token ID | 407 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
ags | +0.021 |
uate | +0.016 |
our | +0.016 |
snowball | +0.015 |
< | +0.015 |
Neg logit contributions | |
ho | -0.047 |
solar | -0.037 |
ad | -0.037 |
wished | -0.036 |
lifetime | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
ags | +0.011 |
adoes | +0.010 |
two | +0.010 |
snowball | +0.010 |
icles | +0.010 |
Neg logit contributions | |
ho | -0.027 |
ited | -0.023 |
solar | -0.022 |
epad | -0.022 |
thank | -0.021 |
Token | play |
Token ID | 711 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
ho | +0.045 |
ited | +0.042 |
solar | +0.038 |
mer | +0.038 |
thank | +0.036 |
Neg logit contributions | |
off | -0.017 |
two | -0.016 |
some | -0.015 |
our | -0.015 |
adoes | -0.015 |
Token | in |
Token ID | 287 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
ho | +0.012 |
ited | +0.010 |
mer | +0.010 |
solar | +0.010 |
ad | +0.010 |
Neg logit contributions | |
off | -0.005 |
two | -0.005 |
our | -0.005 |
adoes | -0.005 |
uate | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
ho | +0.043 |
ited | +0.040 |
solar | +0.038 |
mer | +0.037 |
lifetime | +0.037 |
Neg logit contributions | |
off | -0.003 |
two | -0.002 |
some | -0.002 |
our | -0.002 |
what | -0.002 |
Token | fountain |
Token ID | 29420 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
ho | +0.027 |
ited | +0.024 |
solar | +0.023 |
mer | +0.022 |
lifetime | +0.020 |
Neg logit contributions | |
off | -0.021 |
adoes | -0.020 |
what | -0.020 |
about | -0.020 |
Mark | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
ho | +0.026 |
ited | +0.025 |
solar | +0.024 |
lifetime | +0.023 |
years | +0.023 |
Neg logit contributions | |
off | -0.010 |
some | -0.009 |
too | -0.009 |
about | -0.008 |
on | -0.008 |
Token | He |
Token ID | 679 |
Feature activation | -9.27e-02 |
Pos logit contributions | |
off | +0.014 |
two | +0.013 |
some | +0.013 |
Spot | +0.012 |
our | +0.012 |
Neg logit contributions | |
ho | -0.039 |
ited | -0.036 |
solar | -0.034 |
mer | -0.033 |
lifetime | -0.032 |
Token | said |
Token ID | 531 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
ho | +0.004 |
ited | +0.003 |
solar | +0.003 |
mer | +0.003 |
lifetime | +0.003 |
Neg logit contributions | |
off | -0.003 |
two | -0.003 |
our | -0.003 |
some | -0.003 |
what | -0.003 |
Token | that |
Token ID | 326 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
ags | +0.002 |
off | +0.002 |
adoes | +0.001 |
two | +0.001 |
snowball | +0.001 |
Neg logit contributions | |
ho | -0.003 |
ited | -0.002 |
solar | -0.002 |
wished | -0.002 |
years | -0.002 |
Token | if |
Token ID | 611 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
off | +0.000 |
ags | +0.000 |
two | +0.000 |
our | +0.000 |
adoes | +0.000 |
Neg logit contributions | |
ho | -0.001 |
ited | -0.001 |
solar | -0.001 |
mer | -0.001 |
ad | -0.001 |
Token | size |
Token ID | 2546 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
ho | +0.035 |
ited | +0.032 |
solar | +0.029 |
years | +0.029 |
mer | +0.028 |
Neg logit contributions | |
off | -0.020 |
two | -0.019 |
some | -0.019 |
friends | -0.018 |
our | -0.018 |
Token | as |
Token ID | 355 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
ho | +0.057 |
ited | +0.055 |
solar | +0.051 |
years | +0.049 |
lifetime | +0.049 |
Neg logit contributions | |
off | -0.015 |
two | -0.013 |
some | -0.013 |
on | -0.012 |
about | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
ho | +0.059 |
ited | +0.058 |
solar | +0.051 |
mer | +0.051 |
years | +0.050 |
Neg logit contributions | |
two | -0.010 |
off | -0.010 |
some | -0.010 |
the | -0.009 |
our | -0.008 |
Token | silver |
Token ID | 8465 |
Feature activation | -9.33e-01 |
Pos logit contributions | |
ho | +0.025 |
ited | +0.023 |
solar | +0.021 |
mer | +0.021 |
years | +0.021 |
Neg logit contributions | |
two | -0.012 |
some | -0.011 |
off | -0.011 |
friends | -0.010 |
mom | -0.010 |
Token | coin |
Token ID | 10752 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
ho | +0.044 |
ited | +0.039 |
mer | +0.036 |
solar | +0.035 |
thank | +0.034 |
Neg logit contributions | |
off | -0.028 |
our | -0.027 |
two | -0.026 |
what | -0.025 |
some | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -6.37e-03 |
Pos logit contributions | |
ho | +0.063 |
ited | +0.062 |
solar | +0.059 |
years | +0.058 |
lifetime | +0.054 |
Neg logit contributions | |
off | -0.033 |
on | -0.031 |
two | -0.030 |
some | -0.030 |
the | -0.029 |
Token | |
Token ID | 220 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
ho | +0.000 |
ited | +0.000 |
solar | +0.000 |
lifetime | +0.000 |
mer | +0.000 |
Neg logit contributions | |
off | -0.000 |
adoes | -0.000 |
our | -0.000 |
what | -0.000 |
friends | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
ho | +0.015 |
solar | +0.013 |
ited | +0.013 |
mer | +0.012 |
commented | +0.012 |
Neg logit contributions | |
off | -0.008 |
adoes | -0.008 |
cookies | -0.008 |
our | -0.008 |
dogs | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
off | +0.003 |
adoes | +0.003 |
our | +0.003 |
two | +0.003 |
some | +0.003 |
Neg logit contributions | |
ho | -0.009 |
ited | -0.008 |
solar | -0.008 |
mer | -0.007 |
lifetime | -0.007 |
Token | The |
Token ID | 464 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
off | +0.003 |
our | +0.003 |
some | +0.003 |
two | +0.003 |
adoes | +0.003 |
Neg logit contributions | |
ho | -0.007 |
ited | -0.006 |
solar | -0.006 |
mer | -0.006 |
lifetime | -0.006 |
Token | old |
Token ID | 1468 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
two | +0.006 |
some | +0.005 |
mom | +0.005 |
friends | +0.005 |
what | +0.005 |
Neg logit contributions | |
ho | -0.012 |
ited | -0.011 |
mer | -0.010 |
solar | -0.010 |
years | -0.009 |
Token | hand |
Token ID | 1021 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
ho | +0.017 |
ited | +0.016 |
mer | +0.014 |
solar | +0.014 |
thank | +0.014 |
Neg logit contributions | |
off | -0.006 |
two | -0.005 |
some | -0.005 |
our | -0.005 |
friends | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
ho | +0.015 |
ited | +0.015 |
solar | +0.013 |
mer | +0.013 |
lifetime | +0.013 |
Neg logit contributions | |
off | -0.007 |
two | -0.006 |
some | -0.006 |
what | -0.006 |
our | -0.006 |
Token | A |
Token ID | 317 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
ho | +0.007 |
ited | +0.006 |
solar | +0.006 |
mer | +0.006 |
lifetime | +0.006 |
Neg logit contributions | |
off | -0.003 |
our | -0.003 |
adoes | -0.003 |
friends | -0.003 |
two | -0.003 |
Token | big |
Token ID | 1263 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
ho | +0.033 |
ited | +0.031 |
solar | +0.028 |
mer | +0.027 |
years | +0.026 |
Neg logit contributions | |
off | -0.018 |
two | -0.018 |
some | -0.017 |
our | -0.017 |
what | -0.016 |
Token | father |
Token ID | 2988 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
ho | +0.033 |
ited | +0.031 |
solar | +0.028 |
mer | +0.027 |
lifetime | +0.026 |
Neg logit contributions | |
off | -0.017 |
some | -0.016 |
two | -0.016 |
our | -0.016 |
adoes | -0.015 |
Token | smiled |
Token ID | 13541 |
Feature activation | -5.82e-02 |
Pos logit contributions | |
ho | +0.013 |
ited | +0.011 |
solar | +0.011 |
mer | +0.010 |
lifetime | +0.010 |
Neg logit contributions | |
off | -0.008 |
two | -0.008 |
some | -0.008 |
what | -0.008 |
our | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
ho | +0.004 |
ited | +0.004 |
solar | +0.003 |
mer | +0.003 |
lifetime | +0.003 |
Neg logit contributions | |
off | -0.001 |
two | -0.001 |
some | -0.001 |
what | -0.000 |
about | -0.000 |
Token | said |
Token ID | 531 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
off | +0.007 |
two | +0.007 |
some | +0.007 |
our | +0.007 |
what | +0.007 |
Neg logit contributions | |
ho | -0.009 |
ited | -0.009 |
solar | -0.008 |
mer | -0.008 |
lifetime | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
off | +0.006 |
two | +0.006 |
our | +0.006 |
some | +0.006 |
adoes | +0.005 |
Neg logit contributions | |
ho | -0.017 |
ited | -0.015 |
solar | -0.014 |
mer | -0.014 |
lifetime | -0.013 |
Token | |
Token ID | 220 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
off | +0.004 |
our | +0.004 |
two | +0.004 |
some | +0.004 |
adoes | +0.004 |
Neg logit contributions | |
ho | -0.012 |
ited | -0.011 |
solar | -0.010 |
mer | -0.010 |
lifetime | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +1.08e-03 |
Pos logit contributions | |
ho | +0.018 |
ited | +0.016 |
solar | +0.015 |
mer | +0.015 |
lifetime | +0.015 |
Neg logit contributions | |
off | -0.006 |
adoes | -0.006 |
our | -0.006 |
some | -0.006 |
cookies | -0.006 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
ags | +0.009 |
asuring | +0.008 |
uate | +0.007 |
wounds | +0.007 |
arks | +0.007 |
Neg logit contributions | |
ho | -0.010 |
wished | -0.009 |
solar | -0.009 |
ited | -0.008 |
generation | -0.008 |
Token | my |
Token ID | 1820 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
ho | +0.001 |
ited | +0.001 |
solar | +0.001 |
mer | +0.001 |
lifetime | +0.001 |
Neg logit contributions | |
off | -0.000 |
two | -0.000 |
some | -0.000 |
our | -0.000 |
what | -0.000 |
Token | fell |
Token ID | 3214 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
ho | +0.004 |
ited | +0.004 |
solar | +0.003 |
mer | +0.003 |
lifetime | +0.003 |
Neg logit contributions | |
off | -0.004 |
our | -0.004 |
ags | -0.004 |
adoes | -0.004 |
some | -0.004 |
Token | down |
Token ID | 866 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
ho | +0.018 |
ited | +0.016 |
solar | +0.015 |
mer | +0.015 |
thank | +0.014 |
Neg logit contributions | |
our | -0.004 |
what | -0.004 |
two | -0.004 |
some | -0.004 |
them | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
ho | +0.041 |
ited | +0.040 |
solar | +0.038 |
lifetime | +0.037 |
mer | +0.037 |
Neg logit contributions | |
off | -0.005 |
some | -0.004 |
on | -0.004 |
two | -0.004 |
too | -0.003 |
Token | hurt |
Token ID | 5938 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ho | +0.019 |
ited | +0.018 |
solar | +0.016 |
mer | +0.016 |
lifetime | +0.016 |
Neg logit contributions | |
off | -0.009 |
some | -0.008 |
two | -0.008 |
our | -0.008 |
Spot | -0.008 |
Token | his |
Token ID | 465 |
Feature activation | -8.33e-02 |
Pos logit contributions | |
ho | +0.054 |
ited | +0.049 |
years | +0.046 |
solar | +0.045 |
mer | +0.045 |
Neg logit contributions | |
our | -0.017 |
asuring | -0.016 |
uate | -0.016 |
cookies | -0.016 |
adoes | -0.016 |
Token | knee |
Token ID | 10329 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
ho | +0.004 |
ited | +0.004 |
solar | +0.004 |
mer | +0.004 |
lifetime | +0.004 |
Neg logit contributions | |
off | -0.002 |
them | -0.002 |
our | -0.002 |
what | -0.002 |
two | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
ho | +0.029 |
ited | +0.028 |
solar | +0.027 |
years | +0.026 |
mer | +0.026 |
Neg logit contributions | |
off | -0.012 |
on | -0.010 |
too | -0.009 |
some | -0.009 |
two | -0.009 |
Token | Max |
Token ID | 5436 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ho | +0.007 |
solar | +0.006 |
wished | +0.006 |
ited | +0.006 |
sav | +0.006 |
Neg logit contributions | |
our | -0.005 |
off | -0.005 |
what | -0.004 |
asuring | -0.004 |
them | -0.004 |
Token | bark |
Token ID | 21405 |
Feature activation | -9.52e-01 |
Pos logit contributions | |
ho | +0.048 |
ited | +0.044 |
solar | +0.041 |
mer | +0.039 |
lifetime | +0.038 |
Neg logit contributions | |
off | -0.032 |
two | -0.030 |
some | -0.030 |
our | -0.029 |
Spot | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ho | +0.007 |
ited | +0.006 |
mer | +0.006 |
solar | +0.006 |
thank | +0.006 |
Neg logit contributions | |
off | -0.003 |
adoes | -0.003 |
two | -0.003 |
our | -0.003 |
what | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
off | +0.003 |
adoes | +0.003 |
two | +0.003 |
our | +0.003 |
some | +0.003 |
Neg logit contributions | |
ho | -0.009 |
ited | -0.008 |
solar | -0.008 |
mer | -0.008 |
lifetime | -0.007 |
Token | One |
Token ID | 3198 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
off | +0.001 |
two | +0.001 |
some | +0.001 |
our | +0.001 |
about | +0.001 |
Neg logit contributions | |
ho | -0.002 |
ited | -0.002 |
solar | -0.001 |
mer | -0.001 |
lifetime | -0.001 |
Token | day |
Token ID | 1110 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
ho | +0.002 |
ited | +0.002 |
solar | +0.002 |
mer | +0.002 |
lifetime | +0.002 |
Neg logit contributions | |
off | -0.003 |
adoes | -0.003 |
two | -0.003 |
our | -0.003 |
some | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
ho | +0.015 |
ited | +0.012 |
mer | +0.011 |
solar | +0.011 |
thank | +0.010 |
Neg logit contributions | |
adoes | -0.010 |
ags | -0.010 |
wounds | -0.010 |
< | -0.009 |
off | -0.009 |
Token | Tom |
Token ID | 4186 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
ags | +0.006 |
off | +0.006 |
adoes | +0.006 |
< | +0.006 |
uate | +0.006 |
Neg logit contributions | |
ho | -0.017 |
ited | -0.015 |
thank | -0.014 |
mer | -0.014 |
solar | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
ho | +0.054 |
ited | +0.050 |
solar | +0.046 |
mer | +0.045 |
lifetime | +0.045 |
Neg logit contributions | |
off | -0.022 |
two | -0.021 |
some | -0.020 |
friends | -0.019 |
our | -0.019 |
Token | Lily |
Token ID | 20037 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
ho | +0.028 |
ited | +0.027 |
mer | +0.024 |
solar | +0.024 |
thank | +0.024 |
Neg logit contributions | |
off | -0.010 |
our | -0.009 |
adoes | -0.009 |
two | -0.009 |
ags | -0.009 |
Token | decided |
Token ID | 3066 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
ho | +0.035 |
ited | +0.033 |
lifetime | +0.032 |
mer | +0.032 |
years | +0.031 |
Neg logit contributions | |
two | -0.024 |
off | -0.023 |
over | -0.021 |
mom | -0.021 |
the | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
ho | +0.029 |
ited | +0.024 |
solar | +0.024 |
wished | +0.023 |
lifetime | +0.023 |
Neg logit contributions | |
ags | -0.010 |
snowball | -0.008 |
two | -0.008 |
adoes | -0.008 |
off | -0.008 |
Token | play |
Token ID | 711 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
ho | +0.042 |
ited | +0.037 |
solar | +0.036 |
thank | +0.033 |
mer | +0.033 |
Neg logit contributions | |
off | -0.023 |
two | -0.022 |
some | -0.022 |
our | -0.022 |
what | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +8.22e-02 |
Pos logit contributions | |
off | +0.005 |
adoes | +0.005 |
our | +0.004 |
some | +0.004 |
two | +0.004 |
Neg logit contributions | |
ho | -0.013 |
ited | -0.011 |
solar | -0.011 |
mer | -0.010 |
lifetime | -0.010 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
off | +0.002 |
two | +0.002 |
some | +0.002 |
our | +0.002 |
adoes | +0.002 |
Neg logit contributions | |
ho | -0.004 |
ited | -0.004 |
solar | -0.003 |
mer | -0.003 |
lifetime | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
ho | +0.022 |
ited | +0.020 |
solar | +0.019 |
mer | +0.018 |
lifetime | +0.018 |
Neg logit contributions | |
ags | -0.011 |
off | -0.010 |
adoes | -0.010 |
our | -0.009 |
about | -0.009 |
Token | Sammy |
Token ID | 44067 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
ags | +0.012 |
adoes | +0.010 |
off | +0.010 |
uate | +0.010 |
about | +0.010 |
Neg logit contributions | |
ho | -0.029 |
ited | -0.026 |
solar | -0.025 |
lifetime | -0.024 |
mer | -0.024 |
Token | 's |
Token ID | 338 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
two | +0.008 |
off | +0.008 |
some | +0.008 |
on | +0.007 |
over | +0.007 |
Neg logit contributions | |
ho | -0.011 |
ited | -0.010 |
solar | -0.010 |
mer | -0.009 |
lifetime | -0.009 |
Token | eyes |
Token ID | 2951 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
off | +0.002 |
two | +0.002 |
some | +0.002 |
friends | +0.001 |
mom | +0.001 |
Neg logit contributions | |
ho | -0.007 |
ited | -0.007 |
solar | -0.006 |
mer | -0.006 |
lifetime | -0.006 |
Token | lit |
Token ID | 6578 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
ho | +0.046 |
ited | +0.040 |
solar | +0.039 |
mer | +0.037 |
lifetime | +0.037 |
Neg logit contributions | |
off | -0.040 |
two | -0.038 |
some | -0.037 |
on | -0.036 |
them | -0.035 |
Token | up |
Token ID | 510 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
off | +0.005 |
two | +0.004 |
our | +0.004 |
some | +0.004 |
what | +0.004 |
Neg logit contributions | |
ho | -0.040 |
ited | -0.037 |
solar | -0.035 |
mer | -0.035 |
lifetime | -0.034 |
Token | ! |
Token ID | 0 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
off | +0.011 |
some | +0.010 |
two | +0.010 |
what | +0.009 |
our | +0.009 |
Neg logit contributions | |
ho | -0.036 |
ited | -0.034 |
solar | -0.032 |
mer | -0.031 |
lifetime | -0.031 |
Token | He |
Token ID | 679 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ho | +0.005 |
ited | +0.005 |
solar | +0.005 |
mer | +0.005 |
lifetime | +0.004 |
Neg logit contributions | |
off | -0.002 |
our | -0.002 |
two | -0.002 |
some | -0.002 |
what | -0.002 |
Token | got |
Token ID | 1392 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
ho | +0.008 |
ited | +0.007 |
solar | +0.006 |
mer | +0.006 |
thank | +0.006 |
Neg logit contributions | |
two | -0.006 |
off | -0.006 |
some | -0.006 |
what | -0.006 |
friends | -0.006 |
Token | started |
Token ID | 2067 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
ho | +0.006 |
ited | +0.005 |
solar | +0.005 |
mer | +0.004 |
lifetime | +0.004 |
Neg logit contributions | |
off | -0.005 |
two | -0.005 |
some | -0.005 |
our | -0.005 |
what | -0.005 |
Token | m |
Token ID | 285 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
ho | +0.026 |
ited | +0.024 |
solar | +0.022 |
mer | +0.021 |
years | +0.021 |
Neg logit contributions | |
off | -0.006 |
adoes | -0.006 |
two | -0.006 |
our | -0.006 |
ags | -0.005 |
Token | unch |
Token ID | 3316 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
off | +0.010 |
two | +0.009 |
some | +0.009 |
our | +0.009 |
what | +0.009 |
Neg logit contributions | |
ho | -0.012 |
ited | -0.011 |
solar | -0.010 |
mer | -0.009 |
lifetime | -0.009 |
Token | ing |
Token ID | 278 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
off | +0.007 |
two | +0.006 |
some | +0.006 |
our | +0.006 |
what | +0.005 |
Neg logit contributions | |
ho | -0.026 |
ited | -0.024 |
solar | -0.023 |
mer | -0.022 |
lifetime | -0.022 |
Token | on |
Token ID | 319 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
off | +0.004 |
two | +0.004 |
our | +0.004 |
adoes | +0.003 |
what | +0.003 |
Neg logit contributions | |
ho | -0.018 |
ited | -0.017 |
mer | -0.015 |
solar | -0.015 |
thank | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ho | +0.015 |
ited | +0.014 |
solar | +0.013 |
mer | +0.013 |
lifetime | +0.012 |
Neg logit contributions | |
off | -0.003 |
two | -0.002 |
our | -0.002 |
some | -0.002 |
adoes | -0.002 |
Token | carrot |
Token ID | 40562 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
ho | +0.053 |
ited | +0.050 |
solar | +0.047 |
years | +0.045 |
mer | +0.045 |
Neg logit contributions | |
off | -0.025 |
two | -0.023 |
some | -0.023 |
our | -0.022 |
friends | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -6.77e-02 |
Pos logit contributions | |
off | +0.004 |
some | +0.003 |
two | +0.003 |
on | +0.003 |
too | +0.003 |
Neg logit contributions | |
ited | -0.009 |
ho | -0.009 |
solar | -0.008 |
years | -0.008 |
mer | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
ho | +0.003 |
ited | +0.003 |
solar | +0.003 |
mer | +0.003 |
lifetime | +0.002 |
Neg logit contributions | |
off | -0.002 |
adoes | -0.002 |
our | -0.002 |
asuring | -0.002 |
dogs | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
adoes | +0.007 |
off | +0.006 |
cookies | +0.006 |
dogs | +0.006 |
our | +0.006 |
Neg logit contributions | |
ho | -0.012 |
ited | -0.010 |
solar | -0.010 |
mer | -0.010 |
commented | -0.009 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
off | +0.004 |
our | +0.004 |
cookies | +0.004 |
dogs | +0.004 |
adoes | +0.004 |
Neg logit contributions | |
ho | -0.006 |
ited | -0.005 |
mer | -0.005 |
solar | -0.005 |
lifetime | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
ho | +0.026 |
ited | +0.024 |
solar | +0.023 |
mer | +0.022 |
lifetime | +0.022 |
Neg logit contributions | |
off | -0.008 |
two | -0.007 |
our | -0.007 |
some | -0.006 |
adoes | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
ho | +0.018 |
ited | +0.017 |
solar | +0.016 |
mer | +0.015 |
lifetime | +0.015 |
Neg logit contributions | |
off | -0.005 |
two | -0.004 |
some | -0.004 |
our | -0.004 |
what | -0.004 |
Token | L |
Token ID | 43 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
ho | +0.031 |
ited | +0.029 |
solar | +0.026 |
mer | +0.025 |
lifetime | +0.025 |
Neg logit contributions | |
two | -0.014 |
our | -0.013 |
off | -0.013 |
some | -0.013 |
my | -0.013 |
Token | ily |
Token ID | 813 |
Feature activation | -9.70e-02 |
Pos logit contributions | |
ho | +0.028 |
ited | +0.026 |
solar | +0.024 |
mer | +0.023 |
lifetime | +0.022 |
Neg logit contributions | |
off | -0.017 |
two | -0.016 |
some | -0.015 |
our | -0.015 |
what | -0.015 |
Token | smiled |
Token ID | 13541 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
ho | +0.004 |
ited | +0.004 |
solar | +0.003 |
mer | +0.003 |
lifetime | +0.003 |
Neg logit contributions | |
off | -0.003 |
two | -0.003 |
some | -0.003 |
our | -0.003 |
what | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
ho | +0.029 |
ited | +0.028 |
solar | +0.026 |
mer | +0.025 |
lifetime | +0.025 |
Neg logit contributions | |
off | -0.008 |
two | -0.007 |
some | -0.007 |
our | -0.007 |
what | -0.006 |
Token | nodded |
Token ID | 14464 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
ho | +0.043 |
ited | +0.039 |
solar | +0.036 |
mer | +0.035 |
lifetime | +0.034 |
Neg logit contributions | |
off | -0.032 |
two | -0.031 |
some | -0.031 |
what | -0.030 |
our | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
ho | +0.035 |
ited | +0.033 |
solar | +0.031 |
lifetime | +0.030 |
mer | +0.030 |
Neg logit contributions | |
off | -0.014 |
some | -0.014 |
two | -0.013 |
them | -0.013 |
what | -0.013 |
Token | She |
Token ID | 1375 |
Feature activation | -3.46e-03 |
Pos logit contributions | |
ho | +0.022 |
ited | +0.022 |
mer | +0.019 |
solar | +0.018 |
lifetime | +0.018 |
Neg logit contributions | |
off | -0.011 |
two | -0.011 |
some | -0.010 |
Spot | -0.010 |
what | -0.010 |
Token | took |
Token ID | 1718 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
ho | +0.000 |
ited | +0.000 |
solar | +0.000 |
mer | +0.000 |
lifetime | +0.000 |
Neg logit contributions | |
two | -0.000 |
some | -0.000 |
off | -0.000 |
what | -0.000 |
about | -0.000 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
asuring | +0.014 |
adoes | +0.014 |
about | +0.013 |
< | +0.013 |
what | +0.012 |
Neg logit contributions | |
ho | -0.057 |
ited | -0.052 |
solar | -0.050 |
years | -0.048 |
mer | -0.048 |