Token | . |
Token ID | 13 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
diary | +0.057 |
shield | +0.056 |
oc | +0.055 |
es | +0.051 |
journal | +0.051 |
Neg logit contributions | |
oe | -0.041 |
aa | -0.039 |
oes | -0.037 |
Kids | -0.033 |
round | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
diary | +0.003 |
shield | +0.003 |
oc | +0.003 |
es | +0.003 |
house | +0.003 |
Neg logit contributions | |
aa | -0.005 |
oe | -0.005 |
oes | -0.005 |
Kids | -0.005 |
ora | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
aa | +0.003 |
oes | +0.002 |
oe | +0.002 |
round | +0.002 |
Kids | +0.002 |
Neg logit contributions | |
oc | -0.002 |
es | -0.002 |
diary | -0.002 |
shield | -0.002 |
house | -0.002 |
Token | " |
Token ID | 1 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
diary | +0.050 |
shield | +0.050 |
oc | +0.048 |
es | +0.048 |
house | +0.044 |
Neg logit contributions | |
aa | -0.049 |
oe | -0.046 |
Kids | -0.046 |
oes | -0.045 |
round | -0.042 |
Token | Tom |
Token ID | 13787 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
diary | +0.026 |
shield | +0.025 |
es | +0.025 |
oc | +0.024 |
journal | +0.023 |
Neg logit contributions | |
aa | -0.019 |
Kids | -0.019 |
oe | -0.019 |
oes | -0.018 |
round | -0.017 |
Token | my |
Token ID | 1820 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
diary | +0.089 |
shield | +0.088 |
es | +0.085 |
oc | +0.084 |
shields | +0.084 |
Neg logit contributions | |
aa | -0.045 |
oe | -0.044 |
oes | -0.040 |
Kids | -0.036 |
round | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
diary | +0.145 |
shield | +0.144 |
shields | +0.144 |
istered | +0.136 |
onel | +0.135 |
Neg logit contributions | |
aa | -0.105 |
oe | -0.100 |
oes | -0.082 |
to | -0.080 |
sur | -0.076 |
Token | what |
Token ID | 644 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
es | +0.055 |
oc | +0.055 |
istered | +0.051 |
diary | +0.050 |
shields | +0.050 |
Neg logit contributions | |
Kids | -0.041 |
aa | -0.041 |
oe | -0.037 |
oes | -0.036 |
Su | -0.036 |
Token | 's |
Token ID | 338 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
oc | +0.028 |
shield | +0.027 |
diary | +0.027 |
webs | +0.026 |
Majesty | +0.026 |
Neg logit contributions | |
aa | -0.026 |
Kids | -0.025 |
oes | -0.025 |
oe | -0.024 |
sur | -0.022 |
Token | wrong |
Token ID | 2642 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
aa | +0.011 |
oe | +0.011 |
oes | +0.010 |
Kids | +0.010 |
sur | +0.010 |
Neg logit contributions | |
oc | -0.011 |
es | -0.010 |
shield | -0.009 |
diary | -0.009 |
house | -0.009 |
Token | ?" |
Token ID | 1701 |
Feature activation | -7.58e-02 |
Pos logit contributions | |
diary | +0.039 |
shield | +0.039 |
es | +0.038 |
oc | +0.037 |
shields | +0.035 |
Neg logit contributions | |
aa | -0.042 |
oe | -0.041 |
Kids | -0.039 |
oes | -0.038 |
round | -0.036 |
Token | lot |
Token ID | 1256 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
es | +0.054 |
diary | +0.050 |
shield | +0.049 |
house | +0.048 |
oc | +0.047 |
Neg logit contributions | |
aa | -0.050 |
oe | -0.045 |
Kids | -0.043 |
oes | -0.041 |
round | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
aa | +0.010 |
oe | +0.010 |
Kids | +0.009 |
oes | +0.009 |
round | +0.009 |
Neg logit contributions | |
diary | -0.011 |
shield | -0.011 |
es | -0.011 |
oc | -0.011 |
journal | -0.010 |
Token | She |
Token ID | 1375 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
shield | +0.062 |
es | +0.059 |
diary | +0.058 |
oc | +0.058 |
shields | +0.057 |
Neg logit contributions | |
aa | -0.039 |
Kids | -0.037 |
oe | -0.036 |
oes | -0.036 |
round | -0.031 |
Token | missed |
Token ID | 6825 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
es | +0.053 |
diary | +0.053 |
shield | +0.052 |
oc | +0.052 |
vel | +0.050 |
Neg logit contributions | |
aa | -0.039 |
Kids | -0.038 |
oe | -0.035 |
oes | -0.032 |
crowded | -0.030 |
Token | her |
Token ID | 607 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
shield | +0.010 |
diary | +0.010 |
es | +0.009 |
oc | +0.009 |
shields | +0.009 |
Neg logit contributions | |
aa | -0.008 |
oe | -0.008 |
Kids | -0.008 |
oes | -0.007 |
round | -0.007 |
Token | mug |
Token ID | 25152 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
oc | +0.008 |
es | +0.008 |
shield | +0.007 |
vel | +0.007 |
onel | +0.007 |
Neg logit contributions | |
aa | -0.007 |
oe | -0.007 |
Kids | -0.006 |
oes | -0.006 |
weekend | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Majesty | +0.174 |
oc | +0.172 |
es | +0.161 |
istered | +0.159 |
vel | +0.159 |
Neg logit contributions | |
to | -0.062 |
oe | -0.061 |
aa | -0.052 |
oes | -0.047 |
slowly | -0.041 |
Token | her |
Token ID | 607 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
oc | +0.073 |
vel | +0.070 |
es | +0.066 |
istered | +0.065 |
diary | +0.063 |
Neg logit contributions | |
Kids | -0.037 |
aa | -0.036 |
to | -0.035 |
Su | -0.032 |
Kay | -0.031 |
Token | pretty |
Token ID | 2495 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
oc | +0.033 |
es | +0.031 |
vel | +0.029 |
shield | +0.028 |
onel | +0.027 |
Neg logit contributions | |
aa | -0.021 |
oe | -0.021 |
Kids | -0.019 |
weekend | -0.018 |
oes | -0.018 |
Token | flowers |
Token ID | 12734 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
oc | +0.005 |
shield | +0.005 |
es | +0.004 |
onel | +0.004 |
diary | +0.004 |
Neg logit contributions | |
oe | -0.004 |
aa | -0.004 |
oes | -0.004 |
Kids | -0.003 |
round | -0.003 |
Token | didn |
Token ID | 1422 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
oc | +0.062 |
diary | +0.060 |
shield | +0.060 |
Majesty | +0.058 |
es | +0.057 |
Neg logit contributions | |
oe | -0.044 |
aa | -0.043 |
oes | -0.040 |
Kids | -0.037 |
ho | -0.035 |
Token | from |
Token ID | 422 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
diary | +0.033 |
oc | +0.033 |
shield | +0.032 |
es | +0.032 |
shields | +0.030 |
Neg logit contributions | |
aa | -0.027 |
oe | -0.026 |
oes | -0.025 |
Kids | -0.024 |
round | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
es | +0.027 |
diary | +0.027 |
shield | +0.026 |
oc | +0.026 |
vel | +0.024 |
Neg logit contributions | |
oe | -0.021 |
aa | -0.021 |
oes | -0.019 |
Kids | -0.019 |
round | -0.018 |
Token | sunshine |
Token ID | 34488 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
aa | +0.006 |
oe | +0.006 |
Kids | +0.006 |
oes | +0.005 |
round | +0.005 |
Neg logit contributions | |
shield | -0.007 |
diary | -0.007 |
es | -0.006 |
oc | -0.006 |
journal | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
aa | +0.015 |
Kids | +0.015 |
oe | +0.015 |
oes | +0.014 |
round | +0.013 |
Neg logit contributions | |
shield | -0.013 |
diary | -0.013 |
es | -0.013 |
oc | -0.012 |
journal | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
shield | +0.069 |
diary | +0.068 |
es | +0.066 |
oc | +0.066 |
onel | +0.064 |
Neg logit contributions | |
Kids | -0.042 |
oe | -0.041 |
aa | -0.040 |
oes | -0.039 |
round | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
diary | +0.040 |
shield | +0.040 |
es | +0.039 |
oc | +0.038 |
shields | +0.036 |
Neg logit contributions | |
aa | -0.031 |
oe | -0.030 |
Kids | -0.029 |
oes | -0.028 |
round | -0.026 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
shield | +0.148 |
diary | +0.147 |
es | +0.141 |
onel | +0.140 |
Majesty | +0.138 |
Neg logit contributions | |
Kids | -0.091 |
oe | -0.086 |
round | -0.078 |
aa | -0.071 |
weekend | -0.070 |
Token | , |
Token ID | 11 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
oc | +0.170 |
onel | +0.168 |
istered | +0.167 |
Majesty | +0.161 |
diary | +0.160 |
Neg logit contributions | |
oe | -0.066 |
to | -0.064 |
aa | -0.050 |
Kay | -0.046 |
guard | -0.040 |
Token | he |
Token ID | 339 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
oc | +0.112 |
Majesty | +0.108 |
onel | +0.107 |
istered | +0.101 |
web | +0.100 |
Neg logit contributions | |
oe | -0.059 |
to | -0.058 |
weekend | -0.054 |
crowded | -0.051 |
Kids | -0.050 |
Token | heard |
Token ID | 2982 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
diary | +0.047 |
shield | +0.046 |
oc | +0.046 |
es | +0.044 |
journal | +0.042 |
Neg logit contributions | |
aa | -0.035 |
oe | -0.033 |
Kids | -0.032 |
oes | -0.030 |
sur | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
oc | +0.073 |
diary | +0.071 |
istered | +0.070 |
es | +0.069 |
shield | +0.069 |
Neg logit contributions | |
aa | -0.074 |
Kids | -0.072 |
oe | -0.068 |
Kay | -0.067 |
oes | -0.066 |
Token | , |
Token ID | 11 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
diary | +0.020 |
shield | +0.020 |
oc | +0.019 |
es | +0.019 |
shields | +0.018 |
Neg logit contributions | |
aa | -0.023 |
oe | -0.023 |
Kids | -0.022 |
oes | -0.021 |
round | -0.020 |
Token | " |
Token ID | 366 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
aa | +0.034 |
oe | +0.034 |
oes | +0.034 |
Kids | +0.033 |
ora | +0.032 |
Neg logit contributions | |
es | -0.019 |
shield | -0.018 |
diary | -0.018 |
oc | -0.017 |
Mickey | -0.015 |
Token | Wow |
Token ID | 22017 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
aa | +0.037 |
oe | +0.035 |
oes | +0.033 |
sur | +0.031 |
round | +0.031 |
Neg logit contributions | |
oc | -0.031 |
diary | -0.029 |
es | -0.029 |
shield | -0.028 |
house | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
oc | +0.109 |
diary | +0.107 |
shield | +0.104 |
shields | +0.102 |
traps | +0.102 |
Neg logit contributions | |
oe | -0.056 |
aa | -0.050 |
Su | -0.039 |
to | -0.039 |
Kay | -0.036 |
Token | you |
Token ID | 345 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
aa | +0.004 |
Kids | +0.004 |
oe | +0.004 |
oes | +0.003 |
Kay | +0.003 |
Neg logit contributions | |
es | -0.004 |
diary | -0.004 |
oc | -0.004 |
shield | -0.004 |
istered | -0.004 |
Token | boys |
Token ID | 6510 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
shield | +0.103 |
diary | +0.099 |
oc | +0.096 |
traps | +0.094 |
shields | +0.093 |
Neg logit contributions | |
oe | -0.066 |
aa | -0.062 |
Kids | -0.058 |
crowded | -0.053 |
sur | -0.053 |
Token | did |
Token ID | 750 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
shield | +0.123 |
diary | +0.117 |
shields | +0.113 |
oc | +0.111 |
es | +0.106 |
Neg logit contributions | |
oe | -0.126 |
aa | -0.123 |
oes | -0.110 |
Kids | -0.109 |
round | -0.104 |
Token | a |
Token ID | 257 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
oc | +0.041 |
onel | +0.040 |
es | +0.040 |
shield | +0.039 |
diary | +0.038 |
Neg logit contributions | |
oe | -0.020 |
to | -0.019 |
Kay | -0.017 |
Su | -0.017 |
weekend | -0.015 |
Token | great |
Token ID | 1049 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
es | +0.041 |
diary | +0.036 |
shield | +0.036 |
oc | +0.035 |
onel | +0.035 |
Neg logit contributions | |
oe | -0.031 |
aa | -0.030 |
Kids | -0.028 |
sur | -0.028 |
weekend | -0.027 |
Token | job |
Token ID | 1693 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
shield | +0.004 |
es | +0.004 |
diary | +0.004 |
shields | +0.004 |
onel | +0.004 |
Neg logit contributions | |
aa | -0.005 |
oe | -0.005 |
oes | -0.004 |
Kids | -0.004 |
round | -0.004 |
Token | decor |
Token ID | 11705 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
aa | +0.011 |
Kids | +0.010 |
oe | +0.010 |
oes | +0.010 |
round | +0.009 |
Neg logit contributions | |
diary | -0.007 |
shield | -0.007 |
es | -0.007 |
oc | -0.007 |
journal | -0.006 |
Token | hard |
Token ID | 1327 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
aa | +0.014 |
oe | +0.013 |
Kids | +0.013 |
oes | +0.013 |
round | +0.012 |
Neg logit contributions | |
diary | -0.020 |
shield | -0.019 |
es | -0.019 |
oc | -0.019 |
shields | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
aa | +0.001 |
oe | +0.001 |
Kids | +0.001 |
oes | +0.001 |
round | +0.001 |
Neg logit contributions | |
diary | -0.001 |
shield | -0.001 |
es | -0.001 |
oc | -0.001 |
shields | -0.001 |
Token | had |
Token ID | 550 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
aa | +0.029 |
oe | +0.027 |
Kids | +0.027 |
oes | +0.027 |
round | +0.025 |
Neg logit contributions | |
shield | -0.032 |
diary | -0.032 |
es | -0.031 |
oc | -0.030 |
shields | -0.029 |
Token | no |
Token ID | 645 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
oc | +0.049 |
diary | +0.046 |
es | +0.046 |
shield | +0.045 |
house | +0.043 |
Neg logit contributions | |
aa | -0.052 |
oe | -0.049 |
oes | -0.049 |
Kids | -0.048 |
round | -0.045 |
Token | eyes |
Token ID | 2951 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
es | +0.059 |
oc | +0.054 |
onel | +0.054 |
vel | +0.052 |
diary | +0.050 |
Neg logit contributions | |
aa | -0.064 |
oes | -0.063 |
oe | -0.063 |
weekend | -0.056 |
round | -0.056 |
Token | or |
Token ID | 393 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
diary | +0.024 |
shield | +0.024 |
es | +0.023 |
oc | +0.022 |
shields | +0.021 |
Neg logit contributions | |
aa | -0.026 |
Kids | -0.025 |
oe | -0.025 |
oes | -0.024 |
round | -0.023 |
Token | nose |
Token ID | 9686 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
oc | +0.110 |
es | +0.106 |
onel | +0.104 |
vel | +0.102 |
house | +0.102 |
Neg logit contributions | |
aa | -0.110 |
oes | -0.105 |
to | -0.104 |
se | -0.102 |
sur | -0.099 |
Token | . |
Token ID | 13 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
diary | +0.014 |
shield | +0.014 |
oc | +0.013 |
es | +0.013 |
journal | +0.012 |
Neg logit contributions | |
aa | -0.014 |
oe | -0.013 |
oes | -0.012 |
Kids | -0.012 |
round | -0.012 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
aa | +0.065 |
oes | +0.062 |
oe | +0.061 |
round | +0.058 |
Kids | +0.058 |
Neg logit contributions | |
es | -0.056 |
diary | -0.055 |
shield | -0.055 |
oc | -0.054 |
house | -0.050 |
Token | thought |
Token ID | 1807 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
aa | +0.025 |
oe | +0.023 |
Kids | +0.023 |
oes | +0.022 |
round | +0.021 |
Neg logit contributions | |
diary | -0.037 |
shield | -0.037 |
es | -0.035 |
oc | -0.035 |
shields | -0.033 |
Token | it |
Token ID | 340 |
Feature activation | -6.48e-02 |
Pos logit contributions | |
aa | +0.007 |
oe | +0.007 |
Kids | +0.007 |
oes | +0.006 |
round | +0.006 |
Neg logit contributions | |
diary | -0.008 |
oc | -0.008 |
shield | -0.008 |
es | -0.008 |
house | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
es | +0.027 |
diary | +0.027 |
shield | +0.026 |
oc | +0.026 |
vel | +0.024 |
Neg logit contributions | |
oe | -0.021 |
aa | -0.021 |
oes | -0.019 |
Kids | -0.019 |
round | -0.018 |
Token | sunshine |
Token ID | 34488 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
aa | +0.006 |
oe | +0.006 |
Kids | +0.006 |
oes | +0.005 |
round | +0.005 |
Neg logit contributions | |
shield | -0.007 |
diary | -0.007 |
es | -0.006 |
oc | -0.006 |
journal | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
aa | +0.015 |
Kids | +0.015 |
oe | +0.015 |
oes | +0.014 |
round | +0.013 |
Neg logit contributions | |
shield | -0.013 |
diary | -0.013 |
es | -0.013 |
oc | -0.012 |
journal | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
shield | +0.069 |
diary | +0.068 |
es | +0.066 |
oc | +0.066 |
onel | +0.064 |
Neg logit contributions | |
Kids | -0.042 |
oe | -0.041 |
aa | -0.040 |
oes | -0.039 |
round | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
diary | +0.040 |
shield | +0.040 |
es | +0.039 |
oc | +0.038 |
shields | +0.036 |
Neg logit contributions | |
aa | -0.031 |
oe | -0.030 |
Kids | -0.029 |
oes | -0.028 |
round | -0.026 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
shield | +0.148 |
diary | +0.147 |
es | +0.141 |
onel | +0.140 |
Majesty | +0.138 |
Neg logit contributions | |
Kids | -0.091 |
oe | -0.086 |
round | -0.078 |
aa | -0.071 |
weekend | -0.070 |
Token | , |
Token ID | 11 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
oc | +0.170 |
onel | +0.168 |
istered | +0.167 |
Majesty | +0.161 |
diary | +0.160 |
Neg logit contributions | |
oe | -0.066 |
to | -0.064 |
aa | -0.050 |
Kay | -0.046 |
guard | -0.040 |
Token | he |
Token ID | 339 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
oc | +0.112 |
Majesty | +0.108 |
onel | +0.107 |
istered | +0.101 |
web | +0.100 |
Neg logit contributions | |
oe | -0.059 |
to | -0.058 |
weekend | -0.054 |
crowded | -0.051 |
Kids | -0.050 |
Token | heard |
Token ID | 2982 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
diary | +0.047 |
shield | +0.046 |
oc | +0.046 |
es | +0.044 |
journal | +0.042 |
Neg logit contributions | |
aa | -0.035 |
oe | -0.033 |
Kids | -0.032 |
oes | -0.030 |
sur | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
oc | +0.073 |
diary | +0.071 |
istered | +0.070 |
es | +0.069 |
shield | +0.069 |
Neg logit contributions | |
aa | -0.074 |
Kids | -0.072 |
oe | -0.068 |
Kay | -0.067 |
oes | -0.066 |
Token | soft |
Token ID | 2705 |
Feature activation | +8.83e-03 |
Pos logit contributions | |
shield | +0.020 |
diary | +0.020 |
oc | +0.019 |
es | +0.018 |
journal | +0.017 |
Neg logit contributions | |
aa | -0.024 |
oe | -0.024 |
oes | -0.024 |
Kids | -0.023 |
round | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
aa | +0.019 |
oe | +0.019 |
oes | +0.018 |
round | +0.018 |
Kids | +0.017 |
Neg logit contributions | |
diary | -0.016 |
es | -0.016 |
oc | -0.015 |
shield | -0.015 |
journal | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
aa | +0.007 |
oe | +0.006 |
oes | +0.006 |
Kids | +0.006 |
round | +0.006 |
Neg logit contributions | |
diary | -0.006 |
es | -0.006 |
shield | -0.006 |
oc | -0.006 |
journal | -0.006 |
Token | " |
Token ID | 1 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
diary | +0.015 |
shield | +0.014 |
es | +0.014 |
oc | +0.014 |
shields | +0.013 |
Neg logit contributions | |
aa | -0.018 |
oe | -0.017 |
Kids | -0.017 |
oes | -0.016 |
round | -0.016 |
Token | Tom |
Token ID | 13787 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
aa | +0.001 |
oes | +0.001 |
oe | +0.001 |
round | +0.000 |
weekend | +0.000 |
Neg logit contributions | |
es | -0.000 |
diary | -0.000 |
shield | -0.000 |
oc | -0.000 |
traps | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
diary | +0.054 |
shield | +0.054 |
es | +0.051 |
oc | +0.051 |
shields | +0.048 |
Neg logit contributions | |
aa | -0.052 |
oe | -0.050 |
Kids | -0.048 |
oes | -0.047 |
round | -0.045 |
Token | Sam |
Token ID | 3409 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
aa | +0.027 |
oe | +0.026 |
Kids | +0.025 |
oes | +0.025 |
round | +0.023 |
Neg logit contributions | |
diary | -0.024 |
shield | -0.024 |
es | -0.023 |
oc | -0.023 |
journal | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
shield | +0.142 |
diary | +0.140 |
shields | +0.132 |
journal | +0.127 |
oc | +0.126 |
Neg logit contributions | |
aa | -0.104 |
oe | -0.101 |
Kids | -0.088 |
oes | -0.087 |
round | -0.081 |
Token | what |
Token ID | 644 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
diary | +0.019 |
shield | +0.019 |
oc | +0.019 |
es | +0.019 |
shields | +0.017 |
Neg logit contributions | |
aa | -0.028 |
Kids | -0.027 |
oe | -0.026 |
oes | -0.025 |
round | -0.024 |
Token | are |
Token ID | 389 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
shield | +0.014 |
diary | +0.013 |
oc | +0.013 |
shields | +0.012 |
es | +0.012 |
Neg logit contributions | |
aa | -0.017 |
Kids | -0.017 |
oe | -0.016 |
oes | -0.016 |
sur | -0.015 |
Token | you |
Token ID | 345 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
aa | +0.008 |
oe | +0.008 |
Kids | +0.007 |
oes | +0.007 |
round | +0.007 |
Neg logit contributions | |
shield | -0.007 |
diary | -0.007 |
oc | -0.006 |
es | -0.006 |
shields | -0.006 |
Token | doing |
Token ID | 1804 |
Feature activation | +9.95e-01 |
Pos logit contributions | |
diary | +0.051 |
shield | +0.051 |
es | +0.049 |
oc | +0.048 |
shields | +0.045 |
Neg logit contributions | |
aa | -0.061 |
oe | -0.059 |
Kids | -0.058 |
oes | -0.057 |
round | -0.054 |
Token | an |
Token ID | 281 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
es | +0.061 |
oc | +0.060 |
onel | +0.059 |
diary | +0.059 |
istered | +0.058 |
Neg logit contributions | |
oe | -0.040 |
aa | -0.040 |
Kids | -0.038 |
weekend | -0.036 |
Kay | -0.035 |
Token | unfamiliar |
Token ID | 22594 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
diary | +0.032 |
shield | +0.032 |
es | +0.031 |
oc | +0.030 |
shields | +0.029 |
Neg logit contributions | |
aa | -0.020 |
oe | -0.019 |
Kids | -0.019 |
oes | -0.018 |
round | -0.017 |
Token | forest |
Token ID | 8222 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
diary | +0.026 |
shield | +0.026 |
es | +0.026 |
oc | +0.025 |
shields | +0.024 |
Neg logit contributions | |
aa | -0.018 |
oe | -0.017 |
Kids | -0.017 |
oes | -0.016 |
round | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
diary | +0.025 |
shield | +0.025 |
es | +0.024 |
oc | +0.023 |
Majesty | +0.023 |
Neg logit contributions | |
oe | -0.018 |
aa | -0.018 |
oes | -0.018 |
round | -0.016 |
Kids | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
diary | +0.088 |
shield | +0.087 |
istered | +0.084 |
onel | +0.082 |
shields | +0.081 |
Neg logit contributions | |
Kids | -0.048 |
aa | -0.048 |
oe | -0.046 |
oes | -0.045 |
round | -0.042 |
Token |
|
Token ID | 198 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
diary | +0.049 |
shield | +0.049 |
es | +0.047 |
oc | +0.046 |
shields | +0.045 |
Neg logit contributions | |
aa | -0.034 |
oe | -0.033 |
Kids | -0.032 |
oes | -0.031 |
round | -0.029 |
Token | Will |
Token ID | 8743 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
diary | +0.147 |
shield | +0.142 |
istered | +0.137 |
onel | +0.136 |
Majesty | +0.136 |
Neg logit contributions | |
Kids | -0.081 |
oe | -0.074 |
aa | -0.069 |
weekend | -0.061 |
Ice | -0.060 |
Token | tried |
Token ID | 3088 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
diary | +0.050 |
shield | +0.048 |
oc | +0.047 |
shields | +0.046 |
istered | +0.046 |
Neg logit contributions | |
aa | -0.043 |
oe | -0.040 |
oes | -0.036 |
Kids | -0.034 |
round | -0.034 |
Token | his |
Token ID | 465 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
aa | +0.002 |
oe | +0.002 |
Kids | +0.002 |
oes | +0.001 |
round | +0.001 |
Neg logit contributions | |
shield | -0.006 |
diary | -0.006 |
es | -0.006 |
oc | -0.005 |
shields | -0.005 |
Token | best |
Token ID | 1266 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
diary | +0.007 |
shield | +0.007 |
es | +0.006 |
oc | +0.006 |
shields | +0.006 |
Neg logit contributions | |
aa | -0.007 |
oe | -0.007 |
Kids | -0.007 |
oes | -0.007 |
round | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
aa | +0.013 |
oe | +0.012 |
Kids | +0.012 |
oes | +0.012 |
round | +0.011 |
Neg logit contributions | |
diary | -0.021 |
shield | -0.020 |
es | -0.020 |
oc | -0.020 |
shields | -0.019 |
Token | The |
Token ID | 464 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
shield | +0.082 |
diary | +0.078 |
oc | +0.076 |
es | +0.075 |
shields | +0.075 |
Neg logit contributions | |
Kids | -0.056 |
oe | -0.052 |
aa | -0.051 |
oes | -0.046 |
round | -0.045 |
Token | mouse |
Token ID | 10211 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
es | +0.048 |
vel | +0.044 |
vered | +0.042 |
oc | +0.042 |
Majesty | +0.042 |
Neg logit contributions | |
weekend | -0.025 |
oe | -0.023 |
week | -0.023 |
elderly | -0.023 |
first | -0.021 |
Token | lived |
Token ID | 5615 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
diary | +0.055 |
shield | +0.052 |
istered | +0.051 |
es | +0.051 |
vel | +0.050 |
Neg logit contributions | |
aa | -0.036 |
oe | -0.036 |
Kids | -0.034 |
oes | -0.030 |
sur | -0.030 |
Token | in |
Token ID | 287 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
diary | +0.039 |
shield | +0.039 |
oc | +0.038 |
es | +0.036 |
shields | +0.036 |
Neg logit contributions | |
oe | -0.029 |
aa | -0.026 |
Kids | -0.024 |
oes | -0.023 |
sur | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
shield | +0.067 |
vel | +0.066 |
Majesty | +0.066 |
oc | +0.066 |
es | +0.065 |
Neg logit contributions | |
oe | -0.038 |
Kay | -0.032 |
to | -0.032 |
aa | -0.032 |
Kids | -0.032 |
Token | diary |
Token ID | 26339 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
es | +0.097 |
vel | +0.082 |
rum | +0.081 |
ities | +0.081 |
rums | +0.079 |
Neg logit contributions | |
weekend | -0.044 |
oe | -0.044 |
week | -0.042 |
distance | -0.041 |
Kids | -0.038 |
Token | for |
Token ID | 329 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
oc | +0.136 |
istered | +0.135 |
shield | +0.133 |
diary | +0.131 |
shields | +0.131 |
Neg logit contributions | |
oe | -0.087 |
to | -0.074 |
oes | -0.072 |
weekend | -0.072 |
aa | -0.072 |
Token | a |
Token ID | 257 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
shield | +0.045 |
oc | +0.044 |
diary | +0.043 |
es | +0.041 |
istered | +0.040 |
Neg logit contributions | |
Kids | -0.043 |
oe | -0.042 |
aa | -0.042 |
weekend | -0.039 |
Kay | -0.038 |
Token | long |
Token ID | 890 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
diary | +0.011 |
shield | +0.011 |
es | +0.010 |
oc | +0.010 |
shields | +0.010 |
Neg logit contributions | |
aa | -0.008 |
oe | -0.008 |
Kids | -0.008 |
oes | -0.008 |
round | -0.007 |
Token | time |
Token ID | 640 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
aa | +0.021 |
oe | +0.020 |
Kids | +0.019 |
oes | +0.018 |
round | +0.018 |
Neg logit contributions | |
es | -0.034 |
diary | -0.033 |
shield | -0.033 |
oc | -0.032 |
istered | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
shield | +0.008 |
diary | +0.008 |
oc | +0.007 |
es | +0.007 |
shields | +0.007 |
Neg logit contributions | |
oe | -0.006 |
aa | -0.006 |
oes | -0.005 |
Kids | -0.005 |
round | -0.005 |
Token | be |
Token ID | 307 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
diary | +0.025 |
shield | +0.025 |
es | +0.024 |
oc | +0.024 |
journal | +0.022 |
Neg logit contributions | |
aa | -0.018 |
oe | -0.017 |
Kids | -0.017 |
oes | -0.016 |
round | -0.015 |
Token | found |
Token ID | 1043 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
diary | +0.033 |
oc | +0.033 |
shield | +0.032 |
es | +0.030 |
journal | +0.029 |
Neg logit contributions | |
oe | -0.030 |
aa | -0.030 |
Kids | -0.027 |
oes | -0.026 |
round | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
diary | +0.041 |
shield | +0.041 |
oc | +0.039 |
es | +0.038 |
Majesty | +0.038 |
Neg logit contributions | |
oe | -0.030 |
aa | -0.030 |
oes | -0.028 |
Kids | -0.027 |
round | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
shield | +0.075 |
diary | +0.072 |
onel | +0.069 |
es | +0.068 |
oc | +0.067 |
Neg logit contributions | |
oe | -0.046 |
Kids | -0.044 |
oes | -0.041 |
Kay | -0.037 |
aa | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
shield | +0.064 |
diary | +0.063 |
es | +0.059 |
oc | +0.058 |
shields | +0.058 |
Neg logit contributions | |
oe | -0.035 |
Kids | -0.033 |
aa | -0.033 |
oes | -0.030 |
round | -0.027 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
shield | +0.113 |
diary | +0.108 |
Majesty | +0.104 |
webs | +0.104 |
onel | +0.104 |
Neg logit contributions | |
Kids | -0.086 |
oe | -0.084 |
round | -0.070 |
weekend | -0.066 |
crowded | -0.066 |
Token | , |
Token ID | 11 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
oc | +0.166 |
onel | +0.165 |
istered | +0.161 |
cod | +0.157 |
diary | +0.156 |
Neg logit contributions | |
oe | -0.067 |
to | -0.064 |
Kay | -0.047 |
slowly | -0.044 |
guard | -0.041 |
Token | he |
Token ID | 339 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
oc | +0.095 |
onel | +0.089 |
Majesty | +0.088 |
cod | +0.085 |
webs | +0.085 |
Neg logit contributions | |
oe | -0.067 |
to | -0.061 |
weekend | -0.058 |
Kay | -0.055 |
crowded | -0.055 |
Token | heard |
Token ID | 2982 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
diary | +0.050 |
oc | +0.050 |
shield | +0.049 |
es | +0.047 |
shields | +0.045 |
Neg logit contributions | |
aa | -0.038 |
oe | -0.037 |
Kids | -0.035 |
oes | -0.031 |
sur | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
oc | +0.084 |
istered | +0.081 |
diary | +0.080 |
es | +0.078 |
shield | +0.078 |
Neg logit contributions | |
aa | -0.077 |
Kids | -0.076 |
oe | -0.073 |
Kay | -0.073 |
to | -0.070 |
Token | little |
Token ID | 1310 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
shield | +0.019 |
diary | +0.019 |
oc | +0.018 |
es | +0.017 |
journal | +0.016 |
Neg logit contributions | |
aa | -0.022 |
oe | -0.021 |
Kids | -0.021 |
oes | -0.021 |
round | -0.020 |
Token | be |
Token ID | 307 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
aa | +0.029 |
oe | +0.028 |
Kids | +0.028 |
oes | +0.027 |
round | +0.025 |
Neg logit contributions | |
diary | -0.031 |
shield | -0.030 |
es | -0.029 |
oc | -0.029 |
shields | -0.027 |
Token | dangerous |
Token ID | 4923 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
aa | +0.068 |
oe | +0.065 |
Kids | +0.065 |
oes | +0.063 |
round | +0.060 |
Neg logit contributions | |
diary | -0.057 |
shield | -0.057 |
es | -0.054 |
oc | -0.053 |
shields | -0.050 |
Token | ". |
Token ID | 1911 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
aa | +0.009 |
oe | +0.009 |
Kids | +0.008 |
oes | +0.008 |
round | +0.008 |
Neg logit contributions | |
diary | -0.010 |
shield | -0.010 |
es | -0.010 |
oc | -0.009 |
shields | -0.009 |
Token | |
Token ID | 220 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
shield | +0.074 |
diary | +0.071 |
onel | +0.070 |
vel | +0.065 |
es | +0.064 |
Neg logit contributions | |
oe | -0.071 |
Kids | -0.068 |
oes | -0.064 |
to | -0.061 |
round | -0.061 |
Token |
|
Token ID | 198 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
shield | +0.017 |
diary | +0.017 |
shields | +0.015 |
journal | +0.015 |
oc | +0.015 |
Neg logit contributions | |
oe | -0.008 |
aa | -0.008 |
Kids | -0.008 |
oes | -0.008 |
round | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
shield | +0.096 |
diary | +0.096 |
es | +0.089 |
oc | +0.088 |
shields | +0.087 |
Neg logit contributions | |
oe | -0.057 |
Kids | -0.057 |
aa | -0.056 |
oes | -0.051 |
round | -0.048 |
Token | James |
Token ID | 14731 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
shield | +0.124 |
diary | +0.123 |
onel | +0.115 |
Majesty | +0.114 |
webs | +0.110 |
Neg logit contributions | |
Kids | -0.112 |
oe | -0.105 |
round | -0.094 |
aa | -0.088 |
guard | -0.087 |
Token | understood |
Token ID | 7247 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
aa | +0.006 |
oe | +0.006 |
Kids | +0.006 |
oes | +0.005 |
round | +0.005 |
Neg logit contributions | |
diary | -0.006 |
shield | -0.006 |
es | -0.006 |
oc | -0.006 |
shields | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
shield | +0.002 |
diary | +0.002 |
es | +0.002 |
oc | +0.002 |
journal | +0.002 |
Neg logit contributions | |
aa | -0.002 |
oe | -0.002 |
Kids | -0.002 |
oes | -0.002 |
round | -0.002 |
Token | message |
Token ID | 3275 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
oe | +0.044 |
aa | +0.044 |
Kids | +0.041 |
oes | +0.040 |
round | +0.039 |
Neg logit contributions | |
shield | -0.045 |
diary | -0.045 |
oc | -0.044 |
es | -0.041 |
journal | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
diary | +0.044 |
shield | +0.044 |
es | +0.042 |
oc | +0.042 |
shields | +0.040 |
Neg logit contributions | |
aa | -0.027 |
oe | -0.026 |
Kids | -0.025 |
oes | -0.024 |
round | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
diary | +0.003 |
es | +0.003 |
shield | +0.002 |
oc | +0.002 |
journal | +0.002 |
Neg logit contributions | |
aa | -0.002 |
oe | -0.002 |
oes | -0.002 |
Kids | -0.002 |
round | -0.002 |
Token | " |
Token ID | 1 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
shield | +0.031 |
diary | +0.031 |
es | +0.029 |
oc | +0.028 |
shields | +0.028 |
Neg logit contributions | |
aa | -0.032 |
oe | -0.031 |
Kids | -0.031 |
oes | -0.029 |
round | -0.027 |
Token | L |
Token ID | 43 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
diary | +0.004 |
es | +0.004 |
shield | +0.004 |
oc | +0.004 |
journal | +0.004 |
Neg logit contributions | |
aa | -0.005 |
oes | -0.005 |
oe | -0.005 |
round | -0.005 |
weekend | -0.004 |
Token | ily |
Token ID | 813 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
aa | +0.039 |
oe | +0.038 |
Kids | +0.038 |
oes | +0.036 |
round | +0.034 |
Neg logit contributions | |
shield | -0.039 |
diary | -0.039 |
oc | -0.037 |
es | -0.037 |
shields | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
shield | +0.067 |
diary | +0.066 |
oc | +0.062 |
shields | +0.061 |
es | +0.061 |
Neg logit contributions | |
aa | -0.059 |
oe | -0.057 |
Kids | -0.053 |
oes | -0.051 |
round | -0.049 |
Token | Tom |
Token ID | 4186 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
aa | +0.006 |
Kids | +0.006 |
oe | +0.006 |
oes | +0.006 |
round | +0.005 |
Neg logit contributions | |
oc | -0.010 |
shield | -0.010 |
es | -0.010 |
diary | -0.010 |
webs | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
shield | +0.139 |
diary | +0.137 |
shields | +0.131 |
oc | +0.128 |
journal | +0.124 |
Neg logit contributions | |
aa | -0.098 |
oe | -0.095 |
Kids | -0.083 |
oes | -0.081 |
Su | -0.075 |
Token | how |
Token ID | 703 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
oc | +0.017 |
shield | +0.017 |
diary | +0.016 |
es | +0.016 |
shields | +0.015 |
Neg logit contributions | |
aa | -0.027 |
Kids | -0.026 |
oe | -0.025 |
oes | -0.024 |
round | -0.023 |
Token | could |
Token ID | 714 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
aa | +0.005 |
Kids | +0.004 |
oe | +0.004 |
oes | +0.004 |
round | +0.004 |
Neg logit contributions | |
shield | -0.005 |
diary | -0.005 |
oc | -0.004 |
es | -0.004 |
shields | -0.004 |
Token | you |
Token ID | 345 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
aa | +0.006 |
oe | +0.006 |
Kids | +0.006 |
oes | +0.006 |
round | +0.005 |
Neg logit contributions | |
diary | -0.006 |
shield | -0.006 |
oc | -0.006 |
es | -0.006 |
shields | -0.006 |
Token | be |
Token ID | 307 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
aa | +0.005 |
oe | +0.005 |
oes | +0.005 |
Kids | +0.005 |
round | +0.004 |
Neg logit contributions | |
diary | -0.006 |
shield | -0.006 |
es | -0.006 |
oc | -0.006 |
shields | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
aa | +0.004 |
oe | +0.004 |
oes | +0.004 |
Kids | +0.004 |
round | +0.004 |
Neg logit contributions | |
diary | -0.004 |
shield | -0.004 |
es | -0.004 |
oc | -0.004 |
journal | -0.004 |
Token | " |
Token ID | 1 |
Feature activation | -8.53e-02 |
Pos logit contributions | |
shield | +0.031 |
diary | +0.031 |
es | +0.029 |
oc | +0.029 |
shields | +0.028 |
Neg logit contributions | |
aa | -0.028 |
Kids | -0.027 |
oe | -0.027 |
oes | -0.025 |
round | -0.023 |
Token | L |
Token ID | 43 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
aa | +0.003 |
oes | +0.003 |
oe | +0.003 |
round | +0.002 |
weekend | +0.002 |
Neg logit contributions | |
diary | -0.002 |
es | -0.002 |
shield | -0.002 |
oc | -0.002 |
journal | -0.002 |
Token | ily |
Token ID | 813 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
aa | +0.047 |
oe | +0.045 |
Kids | +0.044 |
oes | +0.044 |
round | +0.042 |
Neg logit contributions | |
diary | -0.039 |
shield | -0.039 |
es | -0.038 |
oc | -0.037 |
journal | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
shield | +0.055 |
diary | +0.054 |
oc | +0.051 |
shields | +0.051 |
es | +0.050 |
Neg logit contributions | |
aa | -0.050 |
oe | -0.049 |
Kids | -0.045 |
oes | -0.043 |
round | -0.042 |
Token | Sam |
Token ID | 3409 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
aa | +0.005 |
Kids | +0.005 |
oes | +0.004 |
oe | +0.004 |
Su | +0.004 |
Neg logit contributions | |
oc | -0.008 |
es | -0.007 |
diary | -0.007 |
shield | -0.007 |
istered | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
shield | +0.138 |
diary | +0.137 |
shields | +0.132 |
oc | +0.131 |
es | +0.124 |
Neg logit contributions | |
aa | -0.095 |
oe | -0.094 |
Kids | -0.082 |
oes | -0.079 |
Su | -0.075 |
Token | you |
Token ID | 345 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
oc | +0.019 |
shield | +0.019 |
diary | +0.018 |
es | +0.018 |
shields | +0.017 |
Neg logit contributions | |
aa | -0.023 |
Kids | -0.022 |
oe | -0.021 |
oes | -0.020 |
Su | -0.019 |
Token | need |
Token ID | 761 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
diary | +0.090 |
shield | +0.087 |
oc | +0.084 |
Majesty | +0.081 |
journal | +0.080 |
Neg logit contributions | |
aa | -0.065 |
Kids | -0.061 |
oe | -0.058 |
crowded | -0.053 |
oes | -0.052 |
Token | to |
Token ID | 284 |
Feature activation | +1.28e-03 |
Pos logit contributions | |
aa | +0.009 |
oe | +0.008 |
Kids | +0.008 |
oes | +0.007 |
round | +0.007 |
Neg logit contributions | |
diary | -0.023 |
shield | -0.023 |
es | -0.022 |
shields | -0.021 |
journal | -0.021 |
Token | share |
Token ID | 2648 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
diary | +0.000 |
shield | +0.000 |
es | +0.000 |
oc | +0.000 |
shields | +0.000 |
Neg logit contributions | |
aa | -0.000 |
oe | -0.000 |
Kids | -0.000 |
oes | -0.000 |
round | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
diary | +0.011 |
oc | +0.011 |
shield | +0.011 |
es | +0.011 |
journal | +0.010 |
Neg logit contributions | |
aa | -0.011 |
oes | -0.010 |
round | -0.010 |
Kids | -0.010 |
oe | -0.009 |
Token | room |
Token ID | 2119 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
es | +0.039 |
shield | +0.037 |
oc | +0.037 |
diary | +0.036 |
vel | +0.035 |
Neg logit contributions | |
oe | -0.039 |
aa | -0.038 |
Kids | -0.038 |
oes | -0.036 |
weekend | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
diary | +0.025 |
es | +0.024 |
shield | +0.024 |
oc | +0.023 |
house | +0.022 |
Neg logit contributions | |
aa | -0.031 |
Kids | -0.029 |
oe | -0.028 |
oes | -0.028 |
round | -0.027 |
Token | " |
Token ID | 366 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
diary | +0.005 |
shield | +0.005 |
es | +0.005 |
oc | +0.005 |
journal | +0.005 |
Neg logit contributions | |
aa | -0.006 |
oe | -0.006 |
Kids | -0.006 |
oes | -0.006 |
round | -0.005 |
Token | Hi |
Token ID | 17250 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
aa | +0.015 |
oe | +0.014 |
oes | +0.014 |
Kids | +0.013 |
round | +0.013 |
Neg logit contributions | |
diary | -0.017 |
shield | -0.017 |
oc | -0.016 |
es | -0.016 |
journal | -0.015 |
Token | girls |
Token ID | 4813 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
shield | +0.043 |
oc | +0.043 |
es | +0.041 |
diary | +0.041 |
shields | +0.040 |
Neg logit contributions | |
oe | -0.036 |
aa | -0.034 |
Kids | -0.033 |
Kay | -0.029 |
Su | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
diary | +0.135 |
shield | +0.135 |
shields | +0.130 |
traps | +0.125 |
istered | +0.124 |
Neg logit contributions | |
aa | -0.096 |
oe | -0.095 |
round | -0.080 |
oes | -0.077 |
sur | -0.075 |
Token | how |
Token ID | 703 |
Feature activation | -1.00e-03 |
Pos logit contributions | |
aa | +0.006 |
Kids | +0.006 |
oe | +0.006 |
oes | +0.006 |
round | +0.006 |
Neg logit contributions | |
es | -0.005 |
shield | -0.005 |
oc | -0.005 |
diary | -0.005 |
shields | -0.005 |
Token | 's |
Token ID | 338 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
aa | +0.000 |
oes | +0.000 |
oe | +0.000 |
Kids | +0.000 |
round | +0.000 |
Neg logit contributions | |
shield | -0.000 |
oc | -0.000 |
diary | -0.000 |
es | -0.000 |
shields | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
oe | +0.010 |
aa | +0.010 |
oes | +0.009 |
weekend | +0.009 |
Kids | +0.009 |
Neg logit contributions | |
oc | -0.014 |
es | -0.014 |
shield | -0.013 |
diary | -0.013 |
istered | -0.012 |
Token | puzzle |
Token ID | 15027 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
es | +0.040 |
oc | +0.038 |
istered | +0.030 |
shield | +0.029 |
onel | +0.028 |
Neg logit contributions | |
oe | -0.055 |
weekend | -0.054 |
oes | -0.050 |
week | -0.049 |
Kids | -0.048 |
Token | said |
Token ID | 531 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
oes | +0.016 |
oe | +0.014 |
aa | +0.014 |
round | +0.014 |
weekend | +0.013 |
Neg logit contributions | |
es | -0.013 |
diary | -0.013 |
shield | -0.013 |
oc | -0.013 |
house | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
aa | +0.006 |
oe | +0.006 |
oes | +0.006 |
Kids | +0.006 |
round | +0.005 |
Neg logit contributions | |
diary | -0.005 |
es | -0.005 |
shield | -0.005 |
oc | -0.005 |
journal | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
aa | +0.029 |
oe | +0.029 |
oes | +0.028 |
Kids | +0.028 |
round | +0.027 |
Neg logit contributions | |
diary | -0.021 |
shield | -0.021 |
es | -0.021 |
oc | -0.019 |
journal | -0.018 |
Token | Tom |
Token ID | 13787 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
aa | +0.017 |
oes | +0.016 |
oe | +0.016 |
round | +0.016 |
sur | +0.014 |
Neg logit contributions | |
es | -0.017 |
diary | -0.017 |
oc | -0.016 |
shield | -0.016 |
traps | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
diary | +0.020 |
shield | +0.020 |
es | +0.020 |
oc | +0.019 |
journal | +0.018 |
Neg logit contributions | |
aa | -0.014 |
oe | -0.014 |
Kids | -0.014 |
oes | -0.013 |
round | -0.012 |
Token | Sam |
Token ID | 3409 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
aa | +0.021 |
Kids | +0.020 |
oe | +0.020 |
oes | +0.019 |
round | +0.018 |
Neg logit contributions | |
diary | -0.024 |
shield | -0.023 |
es | -0.023 |
oc | -0.023 |
shields | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
shield | +0.140 |
diary | +0.136 |
shields | +0.133 |
oc | +0.132 |
journal | +0.125 |
Neg logit contributions | |
aa | -0.095 |
oe | -0.092 |
Kids | -0.083 |
oes | -0.079 |
to | -0.074 |
Token | you |
Token ID | 345 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
diary | +0.015 |
shield | +0.015 |
oc | +0.014 |
es | +0.014 |
shields | +0.013 |
Neg logit contributions | |
aa | -0.019 |
Kids | -0.019 |
oe | -0.018 |
oes | -0.018 |
round | -0.017 |
Token | were |
Token ID | 547 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
diary | +0.091 |
shield | +0.090 |
Majesty | +0.089 |
oc | +0.083 |
journal | +0.082 |
Neg logit contributions | |
aa | -0.063 |
Kids | -0.058 |
oe | -0.057 |
oes | -0.049 |
to | -0.049 |
Token | very |
Token ID | 845 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
oc | +0.051 |
shield | +0.046 |
diary | +0.046 |
es | +0.043 |
shields | +0.043 |
Neg logit contributions | |
oe | -0.036 |
aa | -0.035 |
Kids | -0.033 |
oes | -0.030 |
sur | -0.030 |
Token | naughty |
Token ID | 45128 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
shield | +0.015 |
diary | +0.015 |
es | +0.014 |
oc | +0.014 |
shields | +0.013 |
Neg logit contributions | |
aa | -0.023 |
oe | -0.022 |
Kids | -0.021 |
oes | -0.021 |
round | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
aa | +0.031 |
oe | +0.029 |
Kids | +0.029 |
oes | +0.028 |
round | +0.027 |
Neg logit contributions | |
shield | -0.025 |
diary | -0.024 |
es | -0.024 |
oc | -0.023 |
house | -0.022 |
Token | very |
Token ID | 845 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
Kids | +0.070 |
aa | +0.068 |
round | +0.063 |
oes | +0.063 |
oe | +0.062 |
Neg logit contributions | |
shield | -0.062 |
diary | -0.057 |
shields | -0.051 |
house | -0.051 |
webs | -0.050 |
Token | bright |
Token ID | 6016 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
Kids | +0.085 |
round | +0.080 |
aa | +0.076 |
oes | +0.076 |
aren | +0.072 |
Neg logit contributions | |
shield | -0.058 |
diary | -0.051 |
istered | -0.049 |
nightmare | -0.048 |
journal | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
aa | +0.001 |
Kids | +0.001 |
oe | +0.001 |
oes | +0.001 |
round | +0.001 |
Neg logit contributions | |
shield | -0.001 |
diary | -0.001 |
es | -0.001 |
oc | -0.001 |
journal | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
shield | +0.093 |
onel | +0.092 |
diary | +0.091 |
es | +0.090 |
oc | +0.088 |
Neg logit contributions | |
Kids | -0.056 |
oes | -0.055 |
oe | -0.054 |
round | -0.052 |
weekend | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
diary | +0.034 |
shield | +0.034 |
es | +0.033 |
oc | +0.032 |
shields | +0.030 |
Neg logit contributions | |
aa | -0.027 |
oe | -0.025 |
Kids | -0.025 |
oes | -0.024 |
round | -0.023 |
Token | James |
Token ID | 14731 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
shield | +0.143 |
onel | +0.142 |
diary | +0.141 |
Majesty | +0.140 |
es | +0.135 |
Neg logit contributions | |
Kids | -0.083 |
oe | -0.076 |
round | -0.073 |
crowded | -0.067 |
weekend | -0.065 |
Token | ran |
Token ID | 4966 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
diary | +0.008 |
shield | +0.008 |
es | +0.008 |
oc | +0.008 |
shields | +0.007 |
Neg logit contributions | |
aa | -0.007 |
oe | -0.006 |
Kids | -0.006 |
oes | -0.006 |
round | -0.006 |
Token | around |
Token ID | 1088 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
aa | +0.026 |
Kids | +0.026 |
oes | +0.024 |
oe | +0.022 |
Abbey | +0.021 |
Neg logit contributions | |
shield | -0.033 |
diary | -0.031 |
es | -0.031 |
webs | -0.031 |
shields | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
diary | +0.034 |
shield | +0.033 |
es | +0.032 |
oc | +0.032 |
shields | +0.030 |
Neg logit contributions | |
aa | -0.026 |
oe | -0.025 |
Kids | -0.024 |
oes | -0.024 |
round | -0.022 |
Token | garden |
Token ID | 11376 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
aa | +0.011 |
Kids | +0.011 |
oe | +0.011 |
oes | +0.010 |
round | +0.010 |
Neg logit contributions | |
shield | -0.008 |
diary | -0.008 |
oc | -0.008 |
house | -0.007 |
journal | -0.007 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
diary | +0.032 |
shield | +0.032 |
es | +0.031 |
oc | +0.031 |
shields | +0.029 |
Neg logit contributions | |
aa | -0.030 |
oe | -0.028 |
Kids | -0.028 |
oes | -0.027 |
round | -0.025 |
Token | that |
Token ID | 326 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
diary | +0.019 |
shield | +0.019 |
oc | +0.018 |
es | +0.018 |
shields | +0.017 |
Neg logit contributions | |
aa | -0.011 |
oe | -0.010 |
Kids | -0.010 |
oes | -0.009 |
round | -0.009 |
Token | he |
Token ID | 339 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
es | +0.033 |
diary | +0.033 |
oc | +0.033 |
istered | +0.033 |
webs | +0.032 |
Neg logit contributions | |
Kids | -0.021 |
aa | -0.021 |
oes | -0.020 |
oe | -0.020 |
sur | -0.019 |
Token | hugged |
Token ID | 41130 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
aa | +0.002 |
oe | +0.002 |
Kids | +0.002 |
oes | +0.002 |
round | +0.001 |
Neg logit contributions | |
diary | -0.002 |
shield | -0.002 |
es | -0.002 |
oc | -0.002 |
shields | -0.002 |
Token | his |
Token ID | 465 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
diary | +0.009 |
shield | +0.009 |
es | +0.009 |
oc | +0.009 |
shields | +0.008 |
Neg logit contributions | |
aa | -0.009 |
oe | -0.008 |
Kids | -0.008 |
oes | -0.008 |
round | -0.007 |
Token | robot |
Token ID | 9379 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
es | +0.040 |
onel | +0.039 |
vel | +0.038 |
istered | +0.037 |
endings | +0.036 |
Neg logit contributions | |
oe | -0.057 |
aa | -0.053 |
oes | -0.052 |
to | -0.048 |
Kids | -0.048 |
Token | toy |
Token ID | 13373 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
onel | +0.153 |
endings | +0.153 |
es | +0.153 |
istered | +0.152 |
traps | +0.148 |
Neg logit contributions | |
oe | -0.056 |
to | -0.055 |
round | -0.051 |
aa | -0.048 |
towards | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Majesty | +0.123 |
vel | +0.121 |
es | +0.121 |
istered | +0.119 |
diary | +0.117 |
Neg logit contributions | |
aa | -0.067 |
oe | -0.066 |
oes | -0.066 |
to | -0.065 |
round | -0.060 |
Token | played |
Token ID | 2826 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
diary | +0.062 |
oc | +0.061 |
es | +0.060 |
vel | +0.060 |
shield | +0.059 |
Neg logit contributions | |
aa | -0.034 |
Kids | -0.033 |
oe | -0.031 |
sur | -0.029 |
oes | -0.029 |
Token | with |
Token ID | 351 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
istered | +0.071 |
ience | +0.070 |
diary | +0.070 |
oc | +0.068 |
es | +0.068 |
Neg logit contributions | |
to | -0.026 |
oe | -0.025 |
sur | -0.021 |
towards | -0.019 |
straight | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
istered | +0.090 |
diary | +0.089 |
vel | +0.087 |
onel | +0.087 |
es | +0.087 |
Neg logit contributions | |
to | -0.030 |
oe | -0.028 |
aa | -0.026 |
Kids | -0.024 |
Su | -0.023 |
Token | 't |
Token ID | 470 |
Feature activation | -9.38e-01 |
Pos logit contributions | |
aa | +0.023 |
oe | +0.022 |
Kids | +0.022 |
oes | +0.021 |
round | +0.020 |
Neg logit contributions | |
diary | -0.019 |
shield | -0.019 |
es | -0.018 |
oc | -0.018 |
shields | -0.016 |
Token | stand |
Token ID | 1302 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
aa | +0.027 |
oe | +0.026 |
Kids | +0.025 |
oes | +0.025 |
round | +0.023 |
Neg logit contributions | |
diary | -0.029 |
shield | -0.029 |
es | -0.028 |
oc | -0.028 |
shields | -0.026 |
Token | it |
Token ID | 340 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
aa | +0.042 |
Kids | +0.041 |
oe | +0.040 |
oes | +0.039 |
round | +0.038 |
Neg logit contributions | |
shield | -0.041 |
diary | -0.041 |
es | -0.040 |
oc | -0.038 |
shields | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
diary | +0.005 |
shield | +0.004 |
oc | +0.004 |
es | +0.004 |
journal | +0.004 |
Neg logit contributions | |
aa | -0.004 |
oe | -0.004 |
oes | -0.004 |
Kids | -0.004 |
round | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
shield | +0.075 |
diary | +0.074 |
onel | +0.069 |
es | +0.069 |
oc | +0.068 |
Neg logit contributions | |
oe | -0.061 |
Kids | -0.061 |
oes | -0.058 |
aa | -0.055 |
round | -0.054 |
Token |
|
Token ID | 198 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
diary | +0.036 |
shield | +0.036 |
es | +0.035 |
oc | +0.034 |
shields | +0.032 |
Neg logit contributions | |
aa | -0.029 |
oe | -0.028 |
Kids | -0.027 |
oes | -0.027 |
round | -0.025 |
Token | One |
Token ID | 3198 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
shield | +0.138 |
diary | +0.135 |
onel | +0.133 |
Majesty | +0.130 |
es | +0.127 |
Neg logit contributions | |
Kids | -0.089 |
oe | -0.087 |
round | -0.075 |
weekend | -0.073 |
crowded | -0.070 |
Token | day |
Token ID | 1110 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
aa | +0.013 |
oe | +0.012 |
Kids | +0.012 |
oes | +0.012 |
round | +0.011 |
Neg logit contributions | |
shield | -0.023 |
diary | -0.023 |
oc | -0.023 |
es | -0.022 |
journal | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
onel | +0.124 |
diary | +0.122 |
webs | +0.122 |
shield | +0.122 |
Majesty | +0.118 |
Neg logit contributions | |
oe | -0.075 |
Kids | -0.064 |
to | -0.063 |
aa | -0.058 |
weekend | -0.057 |
Token | James |
Token ID | 3700 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
onel | +0.077 |
oc | +0.074 |
Majesty | +0.074 |
webs | +0.073 |
diary | +0.073 |
Neg logit contributions | |
oe | -0.071 |
to | -0.066 |
weekend | -0.066 |
Kids | -0.064 |
week | -0.062 |
Token | 's |
Token ID | 338 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
diary | +0.010 |
shield | +0.010 |
es | +0.010 |
oc | +0.009 |
journal | +0.009 |
Neg logit contributions | |
aa | -0.009 |
oe | -0.009 |
Kids | -0.009 |
oes | -0.009 |
round | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +9.67e-02 |
Pos logit contributions | |
shield | +0.015 |
diary | +0.015 |
oc | +0.015 |
es | +0.015 |
shields | +0.014 |
Neg logit contributions | |
aa | -0.008 |
oe | -0.007 |
Kids | -0.007 |
oes | -0.006 |
round | -0.006 |
Token | said |
Token ID | 531 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
diary | +0.003 |
shield | +0.003 |
es | +0.003 |
oc | +0.003 |
journal | +0.003 |
Neg logit contributions | |
aa | -0.003 |
oe | -0.002 |
Kids | -0.002 |
oes | -0.002 |
round | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
shield | +0.040 |
diary | +0.039 |
oc | +0.039 |
es | +0.037 |
shields | +0.036 |
Neg logit contributions | |
aa | -0.039 |
oe | -0.038 |
Kids | -0.036 |
oes | -0.034 |
round | -0.032 |
Token | " |
Token ID | 366 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
aa | +0.050 |
oe | +0.049 |
oes | +0.048 |
Kids | +0.048 |
ora | +0.044 |
Neg logit contributions | |
shield | -0.031 |
es | -0.031 |
diary | -0.031 |
oc | -0.030 |
Mickey | -0.026 |
Token | Look |
Token ID | 8567 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
aa | +0.002 |
oe | +0.002 |
oes | +0.002 |
Kids | +0.002 |
round | +0.002 |
Neg logit contributions | |
diary | -0.002 |
shield | -0.002 |
oc | -0.002 |
es | -0.002 |
house | -0.002 |
Token | Max |
Token ID | 5436 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
oc | +0.103 |
shield | +0.098 |
shields | +0.098 |
traps | +0.097 |
istered | +0.093 |
Neg logit contributions | |
aa | -0.074 |
oe | -0.069 |
to | -0.058 |
Su | -0.057 |
Kay | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | +9.19e-01 |
Pos logit contributions | |
shield | +0.136 |
diary | +0.133 |
shields | +0.133 |
oc | +0.131 |
onel | +0.131 |
Neg logit contributions | |
oe | -0.091 |
aa | -0.091 |
Kids | -0.071 |
to | -0.070 |
oes | -0.062 |
Token | I |
Token ID | 314 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
oc | +0.032 |
es | +0.031 |
istered | +0.030 |
onel | +0.028 |
webs | +0.028 |
Neg logit contributions | |
Kids | -0.022 |
aa | -0.021 |
oe | -0.020 |
to | -0.019 |
oes | -0.019 |
Token | found |
Token ID | 1043 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
shield | +0.030 |
diary | +0.030 |
shields | +0.029 |
es | +0.029 |
traps | +0.028 |
Neg logit contributions | |
oe | -0.021 |
aa | -0.021 |
Kids | -0.021 |
sur | -0.019 |
oes | -0.018 |
Token | my |
Token ID | 616 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
oc | +0.057 |
istered | +0.055 |
house | +0.053 |
shield | +0.051 |
ities | +0.050 |
Neg logit contributions | |
to | -0.034 |
aa | -0.031 |
oe | -0.031 |
Kay | -0.029 |
Sara | -0.026 |
Token | bow |
Token ID | 9563 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
es | +0.045 |
oc | +0.044 |
vel | +0.042 |
onel | +0.041 |
istered | +0.038 |
Neg logit contributions | |
oe | -0.023 |
aa | -0.020 |
oes | -0.020 |
to | -0.019 |
weekend | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
diary | +0.025 |
shield | +0.025 |
es | +0.024 |
oc | +0.023 |
shields | +0.022 |
Neg logit contributions | |
aa | -0.021 |
oe | -0.020 |
Kids | -0.020 |
oes | -0.019 |
round | -0.018 |
Token | said |
Token ID | 531 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
oc | +0.022 |
diary | +0.022 |
es | +0.022 |
shield | +0.021 |
vel | +0.020 |
Neg logit contributions | |
aa | -0.020 |
Kids | -0.018 |
oe | -0.018 |
oes | -0.017 |
round | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
oc | +0.067 |
diary | +0.067 |
shield | +0.066 |
es | +0.064 |
shields | +0.062 |
Neg logit contributions | |
aa | -0.040 |
oe | -0.038 |
to | -0.034 |
oes | -0.034 |
Kids | -0.032 |
Token | " |
Token ID | 366 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
aa | +0.027 |
oe | +0.027 |
Kids | +0.026 |
oes | +0.026 |
round | +0.025 |
Neg logit contributions | |
shield | -0.021 |
diary | -0.021 |
es | -0.020 |
oc | -0.019 |
shields | -0.018 |
Token | Mom |
Token ID | 29252 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
diary | +0.025 |
shield | +0.025 |
es | +0.025 |
oc | +0.024 |
shields | +0.023 |
Neg logit contributions | |
aa | -0.016 |
oe | -0.015 |
Kids | -0.015 |
oes | -0.014 |
round | -0.013 |
Token | my |
Token ID | 1820 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
shield | +0.090 |
diary | +0.090 |
es | +0.087 |
oc | +0.086 |
shields | +0.083 |
Neg logit contributions | |
aa | -0.057 |
oe | -0.056 |
oes | -0.053 |
Kids | -0.051 |
round | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
shield | +0.134 |
shields | +0.132 |
diary | +0.131 |
es | +0.128 |
onel | +0.127 |
Neg logit contributions | |
aa | -0.097 |
oe | -0.094 |
oes | -0.078 |
Kids | -0.074 |
to | -0.071 |
Token | boat |
Token ID | 8848 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
es | +0.043 |
oc | +0.043 |
istered | +0.039 |
diary | +0.039 |
shields | +0.038 |
Neg logit contributions | |
aa | -0.031 |
oes | -0.030 |
Kids | -0.029 |
oe | -0.029 |
to | -0.028 |
Token | broke |
Token ID | 6265 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
diary | +0.042 |
shield | +0.040 |
es | +0.040 |
vel | +0.038 |
shields | +0.038 |
Neg logit contributions | |
aa | -0.040 |
oe | -0.039 |
oes | -0.036 |
Kids | -0.032 |
guard | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
diary | +0.009 |
shield | +0.009 |
es | +0.008 |
oc | +0.008 |
shields | +0.008 |
Neg logit contributions | |
aa | -0.011 |
oe | -0.010 |
Kids | -0.010 |
oes | -0.010 |
round | -0.010 |
Token | Can |
Token ID | 1680 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
shield | +0.060 |
diary | +0.059 |
es | +0.058 |
shields | +0.055 |
oc | +0.054 |
Neg logit contributions | |
aa | -0.049 |
Kids | -0.048 |
oes | -0.047 |
oe | -0.046 |
round | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
aa | +0.020 |
Kids | +0.020 |
round | +0.020 |
oe | +0.019 |
oes | +0.019 |
Neg logit contributions | |
diary | -0.014 |
es | -0.014 |
shield | -0.014 |
traps | -0.013 |
webs | -0.013 |
Token | pool |
Token ID | 5933 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
aa | +0.012 |
oe | +0.011 |
Kids | +0.011 |
oes | +0.011 |
round | +0.010 |
Neg logit contributions | |
diary | -0.018 |
shield | -0.018 |
es | -0.017 |
oc | -0.017 |
shields | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
aa | +0.034 |
Kids | +0.032 |
oe | +0.031 |
oes | +0.030 |
round | +0.029 |
Neg logit contributions | |
es | -0.023 |
shield | -0.023 |
diary | -0.023 |
oc | -0.022 |
house | -0.021 |
Token | She |
Token ID | 1375 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
aa | +0.010 |
oe | +0.010 |
Kids | +0.010 |
oes | +0.009 |
round | +0.009 |
Neg logit contributions | |
diary | -0.010 |
shield | -0.009 |
es | -0.009 |
oc | -0.009 |
house | -0.009 |
Token | let |
Token ID | 1309 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
oes | +0.034 |
aa | +0.034 |
oe | +0.032 |
Kids | +0.031 |
round | +0.030 |
Neg logit contributions | |
shield | -0.038 |
es | -0.037 |
oc | -0.036 |
diary | -0.036 |
shields | -0.034 |
Token | go |
Token ID | 467 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
aa | +0.004 |
oe | +0.004 |
Kids | +0.003 |
oes | +0.003 |
round | +0.003 |
Neg logit contributions | |
diary | -0.004 |
shield | -0.004 |
es | -0.004 |
oc | -0.004 |
house | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
pastor | +0.170 |
Kids | +0.167 |
groom | +0.166 |
Abbey | +0.163 |
iya | +0.161 |
Neg logit contributions | |
oc | -0.107 |
es | -0.097 |
house | -0.088 |
shield | -0.078 |
weapon | -0.075 |
Token | her |
Token ID | 607 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
aa | +0.090 |
oe | +0.088 |
Kids | +0.087 |
oes | +0.086 |
round | +0.086 |
Neg logit contributions | |
shield | -0.066 |
es | -0.065 |
diary | -0.065 |
traps | -0.059 |
webs | -0.059 |
Token | unicorn |
Token ID | 44986 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
aa | +0.004 |
oe | +0.004 |
oes | +0.004 |
Kids | +0.004 |
round | +0.003 |
Neg logit contributions | |
es | -0.004 |
vel | -0.004 |
shield | -0.004 |
diary | -0.004 |
oc | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
aa | +0.022 |
oe | +0.021 |
oes | +0.019 |
Kids | +0.018 |
round | +0.018 |
Neg logit contributions | |
diary | -0.030 |
shield | -0.029 |
oc | -0.029 |
es | -0.028 |
Majesty | -0.028 |
Token | ran |
Token ID | 4966 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
aa | +0.008 |
oe | +0.007 |
Kids | +0.007 |
oes | +0.007 |
round | +0.006 |
Neg logit contributions | |
shield | -0.012 |
diary | -0.012 |
es | -0.011 |
oc | -0.011 |
shields | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
Kids | +0.068 |
aa | +0.065 |
weekend | +0.060 |
oe | +0.060 |
oes | +0.059 |
Neg logit contributions | |
es | -0.039 |
oc | -0.032 |
shield | -0.031 |
house | -0.030 |
diary | -0.030 |
Token | They |
Token ID | 1119 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
oe | +0.054 |
aa | +0.053 |
Kids | +0.049 |
oes | +0.048 |
guard | +0.048 |
Neg logit contributions | |
diary | -0.042 |
es | -0.042 |
oc | -0.041 |
shield | -0.040 |
house | -0.040 |
Token | sit |
Token ID | 1650 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
shield | +0.005 |
diary | +0.005 |
es | +0.005 |
oc | +0.005 |
shields | +0.004 |
Neg logit contributions | |
aa | -0.004 |
oe | -0.004 |
Kids | -0.004 |
oes | -0.004 |
round | -0.004 |
Token | on |
Token ID | 319 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
Kids | +0.091 |
aa | +0.086 |
oes | +0.083 |
leaf | +0.082 |
Kay | +0.080 |
Neg logit contributions | |
es | -0.057 |
shield | -0.047 |
diary | -0.046 |
house | -0.045 |
oc | -0.041 |
Token | each |
Token ID | 1123 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
aa | +0.020 |
Kids | +0.019 |
oes | +0.019 |
oe | +0.019 |
round | +0.018 |
Neg logit contributions | |
shield | -0.017 |
diary | -0.017 |
es | -0.016 |
oc | -0.016 |
shields | -0.015 |
Token | end |
Token ID | 886 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
aa | +0.034 |
Kids | +0.033 |
oe | +0.032 |
oes | +0.030 |
sur | +0.030 |
Neg logit contributions | |
oc | -0.019 |
shield | -0.018 |
es | -0.018 |
diary | -0.017 |
house | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
please | +0.208 |
Kids | +0.202 |
leaf | +0.202 |
aa | +0.202 |
round | +0.202 |
Neg logit contributions | |
es | -0.060 |
house | -0.043 |
diary | -0.043 |
traps | -0.038 |
something | -0.037 |
Token | They |
Token ID | 1119 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
oe | +0.061 |
aa | +0.059 |
guard | +0.057 |
round | +0.057 |
oes | +0.055 |
Neg logit contributions | |
es | -0.041 |
Something | -0.040 |
diary | -0.039 |
oc | -0.038 |
house | -0.037 |
Token | push |
Token ID | 4574 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
diary | +0.025 |
shield | +0.024 |
es | +0.024 |
oc | +0.023 |
shields | +0.022 |
Neg logit contributions | |
aa | -0.022 |
oe | -0.021 |
Kids | -0.020 |
oes | -0.020 |
round | -0.019 |
Token | with |
Token ID | 351 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
aa | +0.046 |
oe | +0.046 |
Kids | +0.046 |
oes | +0.045 |
weekend | +0.043 |
Neg logit contributions | |
es | -0.048 |
shield | -0.044 |
diary | -0.044 |
oc | -0.044 |
webs | -0.041 |
Token | their |
Token ID | 511 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
diary | +0.006 |
shield | +0.005 |
oc | +0.005 |
es | +0.005 |
house | +0.005 |
Neg logit contributions | |
aa | -0.004 |
oe | -0.003 |
Kids | -0.003 |
oes | -0.003 |
round | -0.003 |
Token | fish |
Token ID | 5916 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
aa | +0.011 |
oe | +0.010 |
Kids | +0.010 |
oes | +0.010 |
round | +0.009 |
Neg logit contributions | |
shield | -0.017 |
diary | -0.017 |
es | -0.017 |
oc | -0.016 |
shields | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
Kids | +0.059 |
aa | +0.058 |
oe | +0.057 |
oes | +0.055 |
round | +0.053 |
Neg logit contributions | |
es | -0.050 |
shield | -0.048 |
diary | -0.047 |
oc | -0.046 |
house | -0.042 |
Token | They |
Token ID | 1119 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
aa | +0.082 |
oes | +0.077 |
oe | +0.075 |
sur | +0.072 |
round | +0.072 |
Neg logit contributions | |
house | -0.056 |
es | -0.056 |
oc | -0.055 |
diary | -0.055 |
Mickey | -0.052 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
oe | +0.052 |
aa | +0.051 |
oes | +0.050 |
Kids | +0.049 |
round | +0.046 |
Neg logit contributions | |
shield | -0.053 |
es | -0.050 |
diary | -0.050 |
oc | -0.047 |
shields | -0.047 |
Token | to |
Token ID | 284 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
oe | +0.071 |
Kids | +0.071 |
aa | +0.070 |
round | +0.066 |
ora | +0.063 |
Neg logit contributions | |
something | -0.077 |
traps | -0.075 |
shield | -0.075 |
no | -0.072 |
nothing | -0.072 |
Token | go |
Token ID | 467 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
Kids | +0.068 |
aa | +0.067 |
oe | +0.066 |
oes | +0.060 |
round | +0.058 |
Neg logit contributions | |
shield | -0.051 |
oc | -0.047 |
house | -0.047 |
diary | -0.045 |
shields | -0.042 |
Token | closer |
Token ID | 5699 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
Kids | +0.169 |
pastor | +0.163 |
Abbey | +0.149 |
aa | +0.149 |
iza | +0.144 |
Neg logit contributions | |
house | -0.106 |
shield | -0.098 |
oc | -0.098 |
es | -0.095 |
weapon | -0.090 |
Token | and |
Token ID | 290 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
Kids | +0.090 |
aa | +0.081 |
oe | +0.073 |
sur | +0.072 |
Ice | +0.071 |
Neg logit contributions | |
es | -0.083 |
shield | -0.074 |
diary | -0.069 |
oc | -0.068 |
house | -0.067 |
Token | feed |
Token ID | 3745 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
aa | +0.021 |
Kids | +0.020 |
oe | +0.019 |
oes | +0.018 |
round | +0.017 |
Neg logit contributions | |
shield | -0.022 |
diary | -0.021 |
oc | -0.020 |
house | -0.019 |
es | -0.019 |
Token | them |
Token ID | 606 |
Feature activation | -9.90e-01 |
Pos logit contributions | |
aa | +0.084 |
Kids | +0.083 |
oe | +0.083 |
sur | +0.079 |
round | +0.076 |
Neg logit contributions | |
es | -0.080 |
oc | -0.072 |
shield | -0.071 |
diary | -0.067 |
traps | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
aa | +0.030 |
oe | +0.029 |
Kids | +0.027 |
oes | +0.027 |
round | +0.026 |
Neg logit contributions | |
diary | -0.030 |
shield | -0.029 |
es | -0.028 |
oc | -0.028 |
journal | -0.026 |
Token | down |
Token ID | 866 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
aa | +0.047 |
Kids | +0.043 |
oe | +0.043 |
oes | +0.040 |
ora | +0.039 |
Neg logit contributions | |
shield | -0.042 |
diary | -0.040 |
es | -0.038 |
house | -0.037 |
webs | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
aa | +0.049 |
Kids | +0.047 |
oes | +0.044 |
round | +0.043 |
iki | +0.042 |
Neg logit contributions | |
es | -0.019 |
shield | -0.017 |
diary | -0.016 |
traps | -0.016 |
house | -0.016 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
aa | +0.037 |
oe | +0.036 |
Kids | +0.035 |
oes | +0.034 |
round | +0.032 |
Neg logit contributions | |
diary | -0.042 |
shield | -0.042 |
es | -0.041 |
oc | -0.040 |
shields | -0.038 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
oes | +0.072 |
aa | +0.071 |
oe | +0.070 |
Kids | +0.069 |
round | +0.064 |
Neg logit contributions | |
es | -0.068 |
shield | -0.066 |
oc | -0.066 |
diary | -0.065 |
house | -0.062 |
Token | to |
Token ID | 284 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
aa | +0.052 |
oe | +0.052 |
Kids | +0.051 |
round | +0.048 |
ora | +0.047 |
Neg logit contributions | |
diary | -0.064 |
something | -0.064 |
shield | -0.064 |
es | -0.060 |
nothing | -0.059 |
Token | go |
Token ID | 467 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
Kids | +0.079 |
aa | +0.075 |
oe | +0.074 |
oes | +0.066 |
ora | +0.064 |
Neg logit contributions | |
shield | -0.059 |
house | -0.053 |
diary | -0.052 |
oc | -0.049 |
brain | -0.046 |
Token | closer |
Token ID | 5699 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
Kids | +0.183 |
pastor | +0.168 |
aney | +0.158 |
aa | +0.154 |
Abbey | +0.151 |
Neg logit contributions | |
house | -0.094 |
something | -0.079 |
shield | -0.078 |
whatever | -0.075 |
anywhere | -0.075 |
Token | and |
Token ID | 290 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
Kids | +0.088 |
aa | +0.082 |
oe | +0.075 |
oes | +0.074 |
leaf | +0.072 |
Neg logit contributions | |
es | -0.071 |
shield | -0.065 |
diary | -0.062 |
oc | -0.057 |
house | -0.056 |
Token | see |
Token ID | 766 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
aa | +0.023 |
Kids | +0.023 |
oe | +0.022 |
oes | +0.020 |
round | +0.019 |
Neg logit contributions | |
shield | -0.025 |
diary | -0.024 |
house | -0.022 |
journal | -0.022 |
oc | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
aa | +0.015 |
oe | +0.014 |
Kids | +0.014 |
oes | +0.014 |
round | +0.013 |
Neg logit contributions | |
diary | -0.010 |
shield | -0.010 |
es | -0.009 |
oc | -0.009 |
shields | -0.008 |
Token | water |
Token ID | 1660 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
aa | +0.074 |
oes | +0.068 |
Kids | +0.065 |
round | +0.064 |
oe | +0.059 |
Neg logit contributions | |
shield | -0.071 |
diary | -0.071 |
wishes | -0.070 |
webs | -0.068 |
journal | -0.065 |
Token | swing |
Token ID | 9628 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
aa | +0.001 |
oe | +0.001 |
Kids | +0.001 |
oes | +0.001 |
round | +0.001 |
Neg logit contributions | |
diary | -0.001 |
shield | -0.001 |
es | -0.001 |
oc | -0.001 |
shields | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
aa | +0.024 |
Kids | +0.024 |
oe | +0.022 |
oes | +0.022 |
sur | +0.020 |
Neg logit contributions | |
diary | -0.021 |
es | -0.021 |
shield | -0.021 |
oc | -0.020 |
house | -0.020 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
aa | +0.043 |
oe | +0.040 |
oes | +0.039 |
Kids | +0.039 |
round | +0.037 |
Neg logit contributions | |
diary | -0.031 |
es | -0.031 |
shield | -0.031 |
oc | -0.031 |
house | -0.029 |
Token | wants |
Token ID | 3382 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
aa | +0.047 |
oe | +0.045 |
Kids | +0.045 |
oes | +0.043 |
round | +0.041 |
Neg logit contributions | |
shield | -0.035 |
es | -0.035 |
diary | -0.035 |
oc | -0.034 |
shields | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
Kids | +0.061 |
aa | +0.059 |
ora | +0.058 |
oe | +0.058 |
sur | +0.053 |
Neg logit contributions | |
shield | -0.078 |
traps | -0.076 |
shields | -0.075 |
es | -0.074 |
bones | -0.074 |
Token | go |
Token ID | 467 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
Kids | +0.079 |
aa | +0.075 |
oe | +0.071 |
oes | +0.067 |
round | +0.066 |
Neg logit contributions | |
shield | -0.057 |
diary | -0.053 |
house | -0.052 |
es | -0.048 |
webs | -0.047 |
Token | on |
Token ID | 319 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Kids | +0.188 |
pastor | +0.167 |
iya | +0.165 |
Ice | +0.163 |
Abbey | +0.161 |
Neg logit contributions | |
house | -0.092 |
shield | -0.078 |
es | -0.074 |
diary | -0.071 |
weapon | -0.071 |
Token | the |
Token ID | 262 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
aa | +0.040 |
Kids | +0.039 |
oes | +0.038 |
oe | +0.037 |
round | +0.035 |
Neg logit contributions | |
shield | -0.031 |
diary | -0.030 |
es | -0.028 |
shields | -0.027 |
oc | -0.027 |
Token | swing |
Token ID | 9628 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
aa | +0.040 |
Kids | +0.039 |
oe | +0.037 |
oes | +0.036 |
sur | +0.034 |
Neg logit contributions | |
shield | -0.041 |
diary | -0.041 |
webs | -0.036 |
house | -0.036 |
journal | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Kids | +0.070 |
aa | +0.068 |
oe | +0.062 |
oes | +0.060 |
sur | +0.059 |
Neg logit contributions | |
es | -0.046 |
shield | -0.045 |
diary | -0.044 |
oc | -0.044 |
house | -0.043 |
Token | He |
Token ID | 679 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
aa | +0.061 |
oe | +0.058 |
Kids | +0.058 |
oes | +0.056 |
weekend | +0.055 |
Neg logit contributions | |
oc | -0.032 |
es | -0.030 |
shield | -0.028 |
house | -0.028 |
diary | -0.028 |
Token | Tom |
Token ID | 4186 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
aa | +0.047 |
oe | +0.047 |
Kids | +0.045 |
oes | +0.044 |
round | +0.041 |
Neg logit contributions | |
shield | -0.044 |
diary | -0.044 |
es | -0.043 |
oc | -0.042 |
shields | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
aa | +0.056 |
oe | +0.055 |
Kids | +0.053 |
oes | +0.052 |
round | +0.048 |
Neg logit contributions | |
shield | -0.068 |
es | -0.068 |
diary | -0.066 |
oc | -0.066 |
shields | -0.061 |
Token | Sam |
Token ID | 3409 |
Feature activation | -5.86e-02 |
Pos logit contributions | |
aa | +0.047 |
oe | +0.047 |
Kids | +0.045 |
oes | +0.044 |
round | +0.042 |
Neg logit contributions | |
shield | -0.036 |
diary | -0.036 |
es | -0.035 |
oc | -0.034 |
shields | -0.032 |
Token | want |
Token ID | 765 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
aa | +0.002 |
oe | +0.002 |
Kids | +0.002 |
oes | +0.002 |
round | +0.002 |
Neg logit contributions | |
diary | -0.002 |
shield | -0.002 |
es | -0.002 |
oc | -0.002 |
journal | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
oe | +0.060 |
aa | +0.055 |
Kids | +0.054 |
round | +0.051 |
ora | +0.051 |
Neg logit contributions | |
shield | -0.074 |
traps | -0.073 |
es | -0.073 |
something | -0.071 |
bones | -0.068 |
Token | go |
Token ID | 467 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
Kids | +0.079 |
oe | +0.075 |
aa | +0.075 |
oes | +0.068 |
round | +0.066 |
Neg logit contributions | |
shield | -0.065 |
oc | -0.059 |
diary | -0.058 |
house | -0.058 |
shields | -0.055 |
Token | near |
Token ID | 1474 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
Kids | +0.162 |
pastor | +0.149 |
aa | +0.145 |
Abbey | +0.141 |
iza | +0.136 |
Neg logit contributions | |
house | -0.109 |
shield | -0.104 |
oc | -0.101 |
es | -0.098 |
weapon | -0.095 |
Token | the |
Token ID | 262 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
aa | +0.051 |
oe | +0.048 |
Kids | +0.047 |
oes | +0.046 |
round | +0.043 |
Neg logit contributions | |
diary | -0.057 |
shield | -0.056 |
es | -0.055 |
oc | -0.054 |
shields | -0.050 |
Token | pond |
Token ID | 16723 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
aa | +0.051 |
Kids | +0.049 |
oe | +0.048 |
oes | +0.048 |
round | +0.044 |
Neg logit contributions | |
shield | -0.068 |
diary | -0.066 |
oc | -0.065 |
es | -0.064 |
traps | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
Kids | +0.047 |
aa | +0.047 |
oe | +0.043 |
oes | +0.042 |
round | +0.041 |
Neg logit contributions | |
shield | -0.033 |
es | -0.032 |
diary | -0.031 |
oc | -0.030 |
house | -0.029 |
Token | feed |
Token ID | 3745 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
aa | +0.019 |
oe | +0.018 |
Kids | +0.018 |
oes | +0.017 |
round | +0.016 |
Neg logit contributions | |
shield | -0.021 |
diary | -0.020 |
es | -0.019 |
oc | -0.019 |
shields | -0.018 |
Token | ducks |
Token ID | 39694 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
aa | +0.057 |
oe | +0.056 |
Kids | +0.055 |
oes | +0.053 |
round | +0.049 |
Neg logit contributions | |
shield | -0.096 |
diary | -0.093 |
oc | -0.093 |
es | -0.093 |
traps | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
aa | +0.065 |
Kids | +0.064 |
oe | +0.062 |
oes | +0.059 |
round | +0.057 |
Neg logit contributions | |
shield | -0.052 |
es | -0.051 |
diary | -0.051 |
oc | -0.049 |
house | -0.045 |
Token | Rex |
Token ID | 17853 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
aa | +0.062 |
oe | +0.061 |
Kids | +0.058 |
oes | +0.056 |
sur | +0.054 |
Neg logit contributions | |
es | -0.053 |
oc | -0.053 |
house | -0.050 |
shield | -0.050 |
diary | -0.048 |
Token | wants |
Token ID | 3382 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
aa | +0.069 |
oe | +0.068 |
oes | +0.066 |
Kids | +0.066 |
round | +0.061 |
Neg logit contributions | |
shield | -0.073 |
es | -0.071 |
diary | -0.070 |
oc | -0.069 |
shields | -0.065 |
Token | to |
Token ID | 284 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
oe | +0.070 |
Kids | +0.063 |
round | +0.063 |
aa | +0.062 |
sur | +0.059 |
Neg logit contributions | |
traps | -0.086 |
es | -0.085 |
shield | -0.084 |
something | -0.082 |
bones | -0.082 |
Token | go |
Token ID | 467 |
Feature activation | -4.59e+00 |
Pos logit contributions | |
Kids | +0.080 |
oe | +0.078 |
aa | +0.077 |
oes | +0.072 |
round | +0.069 |
Neg logit contributions | |
shield | -0.077 |
oc | -0.072 |
diary | -0.071 |
house | -0.069 |
es | -0.067 |
Token | too |
Token ID | 1165 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
Kids | +0.178 |
pastor | +0.165 |
leaf | +0.151 |
Abbey | +0.151 |
aa | +0.150 |
Neg logit contributions | |
house | -0.102 |
oc | -0.098 |
shield | -0.086 |
es | -0.083 |
weapon | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
Kids | +0.084 |
aa | +0.076 |
oes | +0.073 |
oe | +0.071 |
round | +0.070 |
Neg logit contributions | |
shield | -0.043 |
oc | -0.041 |
es | -0.040 |
diary | -0.038 |
traps | -0.036 |
Token | He |
Token ID | 679 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
aa | +0.075 |
oe | +0.074 |
oes | +0.071 |
Kids | +0.071 |
round | +0.067 |
Neg logit contributions | |
oc | -0.050 |
es | -0.049 |
shield | -0.045 |
house | -0.043 |
diary | -0.043 |
Token | likes |
Token ID | 7832 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
aa | +0.055 |
oe | +0.053 |
Kids | +0.053 |
oes | +0.051 |
round | +0.048 |
Neg logit contributions | |
shield | -0.062 |
diary | -0.060 |
es | -0.058 |
oc | -0.057 |
shields | -0.055 |
Token | water |
Token ID | 1660 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
oe | +0.127 |
Kids | +0.111 |
aa | +0.106 |
oes | +0.106 |
ok | +0.106 |
Neg logit contributions | |
shield | -0.097 |
traps | -0.096 |
shields | -0.091 |
bones | -0.088 |
knights | -0.085 |
Token | likes |
Token ID | 7832 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
aa | +0.003 |
oe | +0.003 |
Kids | +0.003 |
oes | +0.003 |
round | +0.002 |
Neg logit contributions | |
diary | -0.003 |
shield | -0.003 |
es | -0.003 |
oc | -0.003 |
journal | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
oe | +0.103 |
aa | +0.100 |
Kids | +0.098 |
oes | +0.094 |
round | +0.093 |
Neg logit contributions | |
shield | -0.087 |
diary | -0.083 |
es | -0.079 |
shields | -0.077 |
webs | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
diary | +0.039 |
oc | +0.038 |
shield | +0.038 |
es | +0.036 |
shields | +0.036 |
Neg logit contributions | |
oes | -0.023 |
aa | -0.023 |
oe | -0.022 |
Kids | -0.019 |
round | -0.019 |
Token | He |
Token ID | 679 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
aa | +0.039 |
oe | +0.037 |
Kids | +0.037 |
oes | +0.035 |
round | +0.034 |
Neg logit contributions | |
shield | -0.026 |
diary | -0.026 |
oc | -0.025 |
es | -0.025 |
house | -0.023 |
Token | lets |
Token ID | 8781 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
aa | +0.027 |
oe | +0.026 |
Kids | +0.025 |
oes | +0.025 |
round | +0.023 |
Neg logit contributions | |
diary | -0.027 |
shield | -0.027 |
es | -0.026 |
oc | -0.025 |
shields | -0.024 |
Token | go |
Token ID | 467 |
Feature activation | -4.59e+00 |
Pos logit contributions | |
aa | +0.043 |
Kids | +0.042 |
oe | +0.042 |
oes | +0.040 |
round | +0.038 |
Neg logit contributions | |
shield | -0.044 |
diary | -0.044 |
es | -0.043 |
oc | -0.042 |
house | -0.039 |
Token | of |
Token ID | 286 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
Kids | +0.155 |
Abbey | +0.151 |
pastor | +0.149 |
Kay | +0.146 |
Fre | +0.145 |
Neg logit contributions | |
oc | -0.120 |
es | -0.105 |
house | -0.093 |
shield | -0.086 |
weapon | -0.078 |
Token | the |
Token ID | 262 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
aa | +0.065 |
oe | +0.062 |
Kids | +0.061 |
oes | +0.059 |
round | +0.055 |
Neg logit contributions | |
diary | -0.076 |
shield | -0.075 |
es | -0.074 |
oc | -0.073 |
journal | -0.068 |
Token | car |
Token ID | 1097 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
aa | +0.071 |
oes | +0.068 |
Kids | +0.068 |
oe | +0.068 |
round | +0.063 |
Neg logit contributions | |
shield | -0.076 |
diary | -0.074 |
oc | -0.071 |
es | -0.070 |
house | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
Kids | +0.072 |
aa | +0.069 |
oe | +0.065 |
Abbey | +0.062 |
Ab | +0.062 |
Neg logit contributions | |
shield | -0.063 |
es | -0.062 |
diary | -0.061 |
oc | -0.060 |
house | -0.059 |
Token | reaches |
Token ID | 12229 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
aa | +0.009 |
oe | +0.009 |
Kids | +0.009 |
oes | +0.008 |
round | +0.008 |
Neg logit contributions | |
diary | -0.012 |
shield | -0.012 |
es | -0.012 |
oc | -0.012 |
journal | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
aa | +0.059 |
Kids | +0.055 |
oe | +0.055 |
oes | +0.055 |
round | +0.051 |
Neg logit contributions | |
shield | -0.051 |
diary | -0.050 |
es | -0.049 |
oc | -0.049 |
shields | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
aa | +0.027 |
Kids | +0.027 |
oe | +0.026 |
oes | +0.025 |
round | +0.024 |
Neg logit contributions | |
shield | -0.022 |
diary | -0.022 |
es | -0.021 |
oc | -0.020 |
house | -0.019 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
aa | +0.061 |
oes | +0.057 |
oe | +0.057 |
Kids | +0.055 |
round | +0.054 |
Neg logit contributions | |
diary | -0.049 |
es | -0.048 |
shield | -0.047 |
oc | -0.046 |
house | -0.046 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
aa | +0.044 |
oe | +0.043 |
oes | +0.042 |
Kids | +0.042 |
round | +0.039 |
Neg logit contributions | |
shield | -0.047 |
es | -0.047 |
diary | -0.046 |
oc | -0.046 |
house | -0.042 |
Token | to |
Token ID | 284 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
oe | +0.082 |
Kids | +0.078 |
arl | +0.076 |
aa | +0.076 |
round | +0.074 |
Neg logit contributions | |
something | -0.079 |
no | -0.071 |
traps | -0.070 |
shield | -0.069 |
es | -0.068 |
Token | go |
Token ID | 467 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
Kids | +0.075 |
oe | +0.072 |
aa | +0.071 |
oes | +0.063 |
round | +0.062 |
Neg logit contributions | |
shield | -0.054 |
oc | -0.048 |
house | -0.047 |
diary | -0.045 |
shields | -0.043 |
Token | on |
Token ID | 319 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Kids | +0.166 |
pastor | +0.156 |
aa | +0.145 |
Abbey | +0.145 |
aney | +0.142 |
Neg logit contributions | |
house | -0.099 |
shield | -0.097 |
oc | -0.093 |
weapon | -0.090 |
es | -0.087 |
Token | the |
Token ID | 262 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
aa | +0.065 |
oes | +0.062 |
Kids | +0.062 |
oe | +0.061 |
round | +0.058 |
Neg logit contributions | |
shield | -0.040 |
diary | -0.038 |
es | -0.036 |
shields | -0.034 |
traps | -0.034 |
Token | water |
Token ID | 1660 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Kids | +0.056 |
aa | +0.055 |
oe | +0.053 |
oes | +0.051 |
round | +0.047 |
Neg logit contributions | |
shield | -0.063 |
diary | -0.057 |
traps | -0.057 |
oc | -0.057 |
webs | -0.057 |
Token | in |
Token ID | 287 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Kids | +0.081 |
aa | +0.078 |
oe | +0.073 |
leaf | +0.069 |
oes | +0.069 |
Neg logit contributions | |
shield | -0.047 |
es | -0.045 |
diary | -0.042 |
house | -0.041 |
oc | -0.041 |
Token | a |
Token ID | 257 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
aa | +0.035 |
Kids | +0.033 |
oe | +0.033 |
oes | +0.032 |
round | +0.031 |
Neg logit contributions | |
diary | -0.033 |
shield | -0.032 |
es | -0.031 |
oc | -0.030 |
house | -0.028 |
Token | plant |
Token ID | 4618 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
aa | +0.026 |
oe | +0.024 |
Kids | +0.024 |
oes | +0.024 |
round | +0.022 |
Neg logit contributions | |
diary | -0.026 |
shield | -0.026 |
es | -0.024 |
oc | -0.024 |
journal | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
aa | +0.009 |
oe | +0.008 |
Kids | +0.008 |
oes | +0.008 |
round | +0.008 |
Neg logit contributions | |
diary | -0.014 |
shield | -0.013 |
es | -0.013 |
oc | -0.013 |
journal | -0.012 |
Token | each |
Token ID | 1123 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
diary | +0.011 |
shield | +0.011 |
es | +0.010 |
oc | +0.010 |
shields | +0.010 |
Neg logit contributions | |
aa | -0.008 |
oe | -0.007 |
Kids | -0.007 |
oes | -0.007 |
round | -0.007 |
Token | grab |
Token ID | 5552 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
aa | +0.037 |
Kids | +0.036 |
oe | +0.034 |
round | +0.034 |
oes | +0.033 |
Neg logit contributions | |
shield | -0.043 |
diary | -0.042 |
oc | -0.041 |
es | -0.040 |
journal | -0.038 |
Token | one |
Token ID | 530 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
aa | +0.022 |
Kids | +0.021 |
oe | +0.021 |
oes | +0.020 |
round | +0.019 |
Neg logit contributions | |
shield | -0.018 |
diary | -0.018 |
es | -0.018 |
oc | -0.017 |
shields | -0.016 |
Token | end |
Token ID | 886 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
Kids | +0.070 |
aa | +0.069 |
oe | +0.064 |
oes | +0.061 |
round | +0.061 |
Neg logit contributions | |
diary | -0.056 |
shield | -0.056 |
es | -0.053 |
oc | -0.052 |
journal | -0.049 |
Token | of |
Token ID | 286 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
Kids | +0.194 |
aa | +0.184 |
round | +0.176 |
sur | +0.176 |
pastor | +0.169 |
Neg logit contributions | |
es | -0.091 |
diary | -0.078 |
house | -0.073 |
shield | -0.072 |
journal | -0.067 |
Token | the |
Token ID | 262 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
aa | +0.072 |
round | +0.069 |
oes | +0.068 |
Kids | +0.065 |
oe | +0.063 |
Neg logit contributions | |
shield | -0.041 |
es | -0.040 |
diary | -0.039 |
Mickey | -0.037 |
oc | -0.035 |
Token | squash |
Token ID | 34613 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
aa | +0.054 |
Kids | +0.051 |
oe | +0.051 |
oes | +0.049 |
round | +0.048 |
Neg logit contributions | |
diary | -0.052 |
shield | -0.051 |
es | -0.049 |
oc | -0.048 |
journal | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
aa | +0.030 |
Kids | +0.029 |
oe | +0.028 |
oes | +0.027 |
round | +0.026 |
Neg logit contributions | |
diary | -0.026 |
shield | -0.026 |
es | -0.026 |
oc | -0.025 |
journal | -0.023 |
Token | They |
Token ID | 1119 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
aa | +0.029 |
oe | +0.027 |
oes | +0.027 |
Kids | +0.026 |
round | +0.025 |
Neg logit contributions | |
es | -0.026 |
diary | -0.026 |
shield | -0.025 |
oc | -0.024 |
house | -0.023 |
Token | think |
Token ID | 892 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
aa | +0.038 |
oe | +0.037 |
Kids | +0.036 |
oes | +0.035 |
round | +0.033 |
Neg logit contributions | |
diary | -0.045 |
shield | -0.045 |
es | -0.044 |
oc | -0.043 |
shields | -0.041 |
Token | we |
Token ID | 356 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
aa | +0.051 |
Kids | +0.050 |
oe | +0.049 |
oes | +0.046 |
round | +0.045 |
Neg logit contributions | |
diary | -0.038 |
shield | -0.037 |
es | -0.036 |
journal | -0.033 |
oc | -0.032 |
Token | can |
Token ID | 460 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
aa | +0.012 |
oes | +0.012 |
oe | +0.011 |
Kids | +0.011 |
round | +0.010 |
Neg logit contributions | |
diary | -0.014 |
es | -0.013 |
shield | -0.013 |
oc | -0.013 |
shields | -0.012 |
Token | find |
Token ID | 1064 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
aa | +0.045 |
Kids | +0.043 |
oe | +0.043 |
oes | +0.040 |
round | +0.039 |
Neg logit contributions | |
shield | -0.046 |
diary | -0.045 |
es | -0.044 |
oc | -0.043 |
journal | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
aa | +0.006 |
oe | +0.006 |
Kids | +0.006 |
oes | +0.006 |
round | +0.006 |
Neg logit contributions | |
diary | -0.006 |
shield | -0.006 |
es | -0.005 |
oc | -0.005 |
shields | -0.005 |
Token | end |
Token ID | 886 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
aa | +0.024 |
Kids | +0.022 |
oe | +0.020 |
round | +0.020 |
oes | +0.019 |
Neg logit contributions | |
diary | -0.032 |
shield | -0.032 |
journal | -0.029 |
webs | -0.029 |
oc | -0.028 |
Token | of |
Token ID | 286 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
aa | +0.157 |
sur | +0.156 |
Kids | +0.156 |
Abbey | +0.143 |
Fre | +0.138 |
Neg logit contributions | |
es | -0.117 |
house | -0.116 |
diary | -0.111 |
journal | -0.098 |
oc | -0.093 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
aa | +0.044 |
Kids | +0.042 |
oe | +0.041 |
oes | +0.040 |
round | +0.039 |
Neg logit contributions | |
diary | -0.036 |
shield | -0.035 |
es | -0.033 |
oc | -0.032 |
journal | -0.031 |
Token | rainbow |
Token ID | 27223 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
aa | +0.039 |
Kids | +0.037 |
round | +0.033 |
oe | +0.032 |
oes | +0.031 |
Neg logit contributions | |
diary | -0.047 |
shield | -0.045 |
journal | -0.042 |
webs | -0.041 |
house | -0.041 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
aa | +0.076 |
Kids | +0.075 |
oe | +0.069 |
oes | +0.066 |
sur | +0.066 |
Neg logit contributions | |
diary | -0.053 |
es | -0.052 |
shield | -0.051 |
house | -0.048 |
journal | -0.046 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
aa | +0.055 |
oe | +0.053 |
Kids | +0.051 |
oes | +0.051 |
round | +0.049 |
Neg logit contributions | |
shield | -0.053 |
diary | -0.052 |
es | -0.050 |
oc | -0.050 |
shields | -0.046 |
Token | slide |
Token ID | 10649 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
aa | +0.028 |
Kids | +0.027 |
oe | +0.027 |
oes | +0.026 |
round | +0.024 |
Neg logit contributions | |
shield | -0.030 |
diary | -0.030 |
oc | -0.028 |
es | -0.028 |
journal | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
Kids | +0.086 |
aa | +0.083 |
Fre | +0.078 |
Abbey | +0.077 |
leaf | +0.077 |
Neg logit contributions | |
house | -0.040 |
es | -0.034 |
oc | -0.032 |
shield | -0.028 |
diary | -0.028 |
Token | Sara |
Token ID | 24799 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
aa | +0.066 |
oe | +0.062 |
oes | +0.060 |
Kids | +0.058 |
round | +0.056 |
Neg logit contributions | |
oc | -0.048 |
es | -0.048 |
diary | -0.048 |
house | -0.046 |
shield | -0.045 |
Token | wants |
Token ID | 3382 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
aa | +0.062 |
oe | +0.061 |
Kids | +0.060 |
oes | +0.059 |
round | +0.056 |
Neg logit contributions | |
es | -0.045 |
shield | -0.042 |
oc | -0.042 |
diary | -0.041 |
webs | -0.037 |
Token | to |
Token ID | 284 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
ora | +0.070 |
Kids | +0.068 |
oe | +0.066 |
aa | +0.066 |
sur | +0.065 |
Neg logit contributions | |
something | -0.068 |
nothing | -0.063 |
no | -0.063 |
bones | -0.062 |
anything | -0.060 |
Token | go |
Token ID | 467 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
Kids | +0.080 |
aa | +0.075 |
oe | +0.070 |
ho | +0.068 |
ora | +0.067 |
Neg logit contributions | |
shield | -0.048 |
house | -0.044 |
oc | -0.039 |
diary | -0.039 |
whatever | -0.038 |
Token | first |
Token ID | 717 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
Kids | +0.189 |
iya | +0.172 |
pastor | +0.166 |
Fre | +0.165 |
aa | +0.164 |
Neg logit contributions | |
house | -0.073 |
whatever | -0.058 |
shield | -0.056 |
es | -0.055 |
anywhere | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
aa | +0.085 |
Kids | +0.084 |
oes | +0.077 |
leaf | +0.077 |
oe | +0.075 |
Neg logit contributions | |
es | -0.038 |
diary | -0.033 |
shield | -0.032 |
house | -0.031 |
oc | -0.028 |
Token | She |
Token ID | 1375 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
oe | +0.054 |
aa | +0.053 |
round | +0.051 |
Kids | +0.050 |
oes | +0.050 |
Neg logit contributions | |
diary | -0.036 |
es | -0.035 |
oc | -0.034 |
shield | -0.033 |
house | -0.031 |
Token | runs |
Token ID | 4539 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
aa | +0.034 |
oe | +0.034 |
Kids | +0.033 |
oes | +0.033 |
round | +0.030 |
Neg logit contributions | |
shield | -0.037 |
diary | -0.036 |
es | -0.035 |
oc | -0.035 |
shields | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
Kids | +0.064 |
aa | +0.061 |
iki | +0.060 |
oes | +0.058 |
argo | +0.055 |
Neg logit contributions | |
es | -0.071 |
shield | -0.066 |
house | -0.066 |
diary | -0.066 |
something | -0.064 |
Token | big |
Token ID | 1263 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
aa | +0.008 |
oes | +0.008 |
Kids | +0.008 |
oe | +0.007 |
round | +0.007 |
Neg logit contributions | |
diary | -0.009 |
shield | -0.008 |
journal | -0.008 |
oc | -0.008 |
house | -0.007 |
Token | slide |
Token ID | 10649 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
aa | +0.023 |
Kids | +0.022 |
oes | +0.022 |
oe | +0.021 |
round | +0.019 |
Neg logit contributions | |
diary | -0.024 |
shield | -0.024 |
oc | -0.023 |
es | -0.022 |
journal | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
Kids | +0.053 |
aa | +0.052 |
leaf | +0.047 |
Fre | +0.047 |
Abbey | +0.047 |
Neg logit contributions | |
house | -0.030 |
es | -0.027 |
diary | -0.025 |
oc | -0.024 |
shield | -0.024 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
shield | +0.011 |
diary | +0.011 |
es | +0.011 |
oc | +0.010 |
shields | +0.010 |
Neg logit contributions | |
aa | -0.011 |
oe | -0.010 |
oes | -0.010 |
Kids | -0.010 |
round | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
aa | +0.057 |
Kids | +0.054 |
sur | +0.052 |
ora | +0.051 |
oe | +0.047 |
Neg logit contributions | |
diary | -0.067 |
es | -0.066 |
something | -0.065 |
nothing | -0.064 |
no | -0.064 |
Token | go |
Token ID | 467 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
Kids | +0.063 |
aa | +0.063 |
oe | +0.056 |
ho | +0.052 |
ora | +0.052 |
Neg logit contributions | |
shield | -0.038 |
house | -0.035 |
oc | -0.032 |
whatever | -0.032 |
diary | -0.032 |
Token | on |
Token ID | 319 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Kids | +0.191 |
iya | +0.172 |
pastor | +0.171 |
aa | +0.170 |
argo | +0.165 |
Neg logit contributions | |
house | -0.073 |
whatever | -0.062 |
es | -0.058 |
shield | -0.057 |
anywhere | -0.054 |
Token | it |
Token ID | 340 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
aa | +0.048 |
oes | +0.046 |
Kids | +0.045 |
oe | +0.043 |
round | +0.042 |
Neg logit contributions | |
diary | -0.032 |
shield | -0.031 |
es | -0.029 |
webs | -0.027 |
shields | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
aa | +0.038 |
Kids | +0.036 |
oe | +0.035 |
oes | +0.034 |
round | +0.033 |
Neg logit contributions | |
diary | -0.031 |
shield | -0.031 |
es | -0.030 |
oc | -0.029 |
house | -0.027 |
Token | She |
Token ID | 1375 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
aa | +0.001 |
oe | +0.001 |
Kids | +0.001 |
oes | +0.001 |
round | +0.001 |
Neg logit contributions | |
shield | -0.002 |
diary | -0.002 |
oc | -0.002 |
es | -0.002 |
shields | -0.002 |
Token | left |
Token ID | 1364 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
oes | +0.040 |
aa | +0.038 |
oe | +0.036 |
Kids | +0.035 |
round | +0.035 |
Neg logit contributions | |
shield | -0.038 |
es | -0.037 |
diary | -0.035 |
oc | -0.035 |
shields | -0.034 |
Token | big |
Token ID | 1263 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
oes | +0.018 |
aa | +0.018 |
Kids | +0.017 |
oe | +0.016 |
round | +0.016 |
Neg logit contributions | |
diary | -0.018 |
shield | -0.018 |
journal | -0.016 |
oc | -0.016 |
house | -0.015 |
Token | slide |
Token ID | 10649 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
aa | +0.028 |
Kids | +0.027 |
oes | +0.027 |
oe | +0.027 |
round | +0.024 |
Neg logit contributions | |
diary | -0.029 |
shield | -0.028 |
oc | -0.026 |
journal | -0.025 |
es | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Kids | +0.060 |
aa | +0.058 |
Fre | +0.053 |
Abbey | +0.053 |
leaf | +0.053 |
Neg logit contributions | |
house | -0.033 |
es | -0.028 |
diary | -0.028 |
oc | -0.026 |
shield | -0.025 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
aa | +0.003 |
oe | +0.003 |
oes | +0.003 |
Kids | +0.003 |
round | +0.002 |
Neg logit contributions | |
diary | -0.003 |
shield | -0.003 |
es | -0.003 |
oc | -0.003 |
shields | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
aa | +0.050 |
Kids | +0.046 |
sur | +0.044 |
ora | +0.043 |
oe | +0.041 |
Neg logit contributions | |
diary | -0.066 |
es | -0.065 |
shield | -0.061 |
something | -0.060 |
nothing | -0.060 |
Token | go |
Token ID | 467 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
Kids | +0.063 |
aa | +0.062 |
oe | +0.057 |
ora | +0.053 |
ho | +0.052 |
Neg logit contributions | |
shield | -0.041 |
house | -0.037 |
diary | -0.035 |
oc | -0.034 |
whatever | -0.032 |
Token | on |
Token ID | 319 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
Kids | +0.182 |
iya | +0.165 |
pastor | +0.164 |
aa | +0.162 |
Fre | +0.159 |
Neg logit contributions | |
house | -0.080 |
whatever | -0.067 |
es | -0.065 |
shield | -0.063 |
weapon | -0.061 |
Token | it |
Token ID | 340 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
aa | +0.052 |
oes | +0.049 |
Kids | +0.048 |
oe | +0.046 |
round | +0.045 |
Neg logit contributions | |
diary | -0.036 |
shield | -0.035 |
es | -0.033 |
webs | -0.030 |
journal | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
aa | +0.033 |
oe | +0.032 |
Kids | +0.031 |
oes | +0.030 |
round | +0.029 |
Neg logit contributions | |
diary | -0.031 |
shield | -0.030 |
es | -0.029 |
oc | -0.029 |
shields | -0.027 |
Token | She |
Token ID | 1375 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
aa | +0.017 |
oe | +0.016 |
oes | +0.016 |
Kids | +0.016 |
round | +0.015 |
Neg logit contributions | |
diary | -0.018 |
shield | -0.017 |
es | -0.017 |
oc | -0.016 |
journal | -0.016 |
Token | asked |
Token ID | 1965 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
oes | +0.035 |
aa | +0.034 |
oe | +0.033 |
Kids | +0.031 |
round | +0.030 |
Neg logit contributions | |
shield | -0.039 |
es | -0.038 |
diary | -0.037 |
oc | -0.036 |
shields | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
diary | +0.028 |
shield | +0.028 |
es | +0.027 |
oc | +0.027 |
shields | +0.025 |
Neg logit contributions | |
aa | -0.022 |
oe | -0.021 |
Kids | -0.021 |
oes | -0.020 |
round | -0.019 |
Token | then |
Token ID | 788 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
diary | +0.005 |
shield | +0.005 |
es | +0.005 |
oc | +0.004 |
shields | +0.004 |
Neg logit contributions | |
aa | -0.004 |
oe | -0.003 |
Kids | -0.003 |
oes | -0.003 |
round | -0.003 |
Token | took |
Token ID | 1718 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
aa | +0.001 |
oe | +0.001 |
Kids | +0.001 |
oes | +0.001 |
round | +0.001 |
Neg logit contributions | |
diary | -0.002 |
shield | -0.002 |
es | -0.002 |
oc | -0.002 |
shields | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
diary | +0.004 |
shield | +0.004 |
es | +0.004 |
oc | +0.004 |
shields | +0.003 |
Neg logit contributions | |
aa | -0.004 |
oe | -0.004 |
Kids | -0.004 |
oes | -0.004 |
round | -0.004 |
Token | other |
Token ID | 584 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
aa | +0.050 |
oe | +0.048 |
Kids | +0.047 |
oes | +0.046 |
round | +0.043 |
Neg logit contributions | |
diary | -0.054 |
shield | -0.054 |
es | -0.053 |
oc | -0.052 |
shields | -0.048 |
Token | end |
Token ID | 886 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
aa | +0.043 |
oe | +0.041 |
Kids | +0.040 |
oes | +0.039 |
round | +0.037 |
Neg logit contributions | |
diary | -0.047 |
shield | -0.047 |
es | -0.046 |
oc | -0.046 |
journal | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Kids | +0.140 |
aa | +0.133 |
sur | +0.124 |
round | +0.120 |
Abbey | +0.116 |
Neg logit contributions | |
es | -0.131 |
diary | -0.128 |
shield | -0.123 |
house | -0.119 |
journal | -0.112 |
Token | ran |
Token ID | 4966 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
diary | +0.005 |
shield | +0.005 |
es | +0.005 |
oc | +0.005 |
shields | +0.005 |
Neg logit contributions | |
aa | -0.004 |
oe | -0.004 |
Kids | -0.004 |
oes | -0.003 |
round | -0.003 |
Token | away |
Token ID | 1497 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
aa | +0.035 |
Kids | +0.035 |
oes | +0.035 |
iki | +0.030 |
oe | +0.029 |
Neg logit contributions | |
shield | -0.037 |
diary | -0.036 |
es | -0.035 |
webs | -0.033 |
shields | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
aa | +0.001 |
oe | +0.001 |
Kids | +0.001 |
oes | +0.001 |
round | +0.001 |
Neg logit contributions | |
diary | -0.001 |
shield | -0.001 |
es | -0.001 |
oc | -0.001 |
shields | -0.001 |
Token | gigg |
Token ID | 30442 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
aa | +0.009 |
Kids | +0.009 |
oe | +0.009 |
oes | +0.009 |
round | +0.008 |
Neg logit contributions | |
shield | -0.010 |
diary | -0.010 |
es | -0.010 |
oc | -0.009 |
journal | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
aa | +0.032 |
Kids | +0.031 |
oe | +0.031 |
oes | +0.029 |
round | +0.028 |
Neg logit contributions | |
diary | -0.029 |
shield | -0.029 |
es | -0.028 |
oc | -0.027 |
journal | -0.025 |
Token | Do |
Token ID | 2141 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
aa | +0.021 |
oe | +0.020 |
Kids | +0.020 |
oes | +0.019 |
round | +0.018 |
Neg logit contributions | |
diary | -0.016 |
shield | -0.016 |
es | -0.016 |
oc | -0.015 |
journal | -0.014 |
Token | you |
Token ID | 345 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
aa | +0.011 |
oe | +0.010 |
Kids | +0.010 |
oes | +0.010 |
round | +0.009 |
Neg logit contributions | |
shield | -0.011 |
diary | -0.010 |
oc | -0.010 |
es | -0.010 |
shields | -0.009 |
Token | want |
Token ID | 765 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
aa | +0.054 |
Kids | +0.053 |
oe | +0.052 |
oes | +0.049 |
round | +0.048 |
Neg logit contributions | |
diary | -0.048 |
shield | -0.047 |
oc | -0.045 |
es | -0.044 |
house | -0.042 |
Token | to |
Token ID | 284 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
aa | +0.049 |
Kids | +0.046 |
oe | +0.046 |
sur | +0.040 |
Abbey | +0.039 |
Neg logit contributions | |
diary | -0.100 |
shield | -0.097 |
es | -0.095 |
journal | -0.090 |
webs | -0.089 |
Token | go |
Token ID | 467 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
Kids | +0.096 |
aa | +0.092 |
oe | +0.083 |
round | +0.082 |
Abbey | +0.082 |
Neg logit contributions | |
diary | -0.065 |
shield | -0.064 |
house | -0.062 |
webs | -0.057 |
whatever | -0.057 |
Token | high |
Token ID | 1029 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
Kids | +0.170 |
Abbey | +0.155 |
aa | +0.155 |
pastor | +0.151 |
sur | +0.150 |
Neg logit contributions | |
house | -0.097 |
es | -0.085 |
diary | -0.081 |
whatever | -0.076 |
shield | -0.074 |
Token | ?" |
Token ID | 1701 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
Kids | +0.076 |
aa | +0.075 |
oes | +0.069 |
oe | +0.068 |
iki | +0.067 |
Neg logit contributions | |
shield | -0.039 |
es | -0.039 |
diary | -0.039 |
oc | -0.037 |
house | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
aa | +0.076 |
oe | +0.076 |
round | +0.074 |
oes | +0.071 |
Kids | +0.071 |
Neg logit contributions | |
es | -0.049 |
diary | -0.048 |
oc | -0.046 |
shield | -0.045 |
house | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | +7.96e-02 |
Pos logit contributions | |
aa | +0.028 |
oes | +0.027 |
oe | +0.027 |
round | +0.027 |
Kids | +0.026 |
Neg logit contributions | |
es | -0.023 |
oc | -0.023 |
diary | -0.022 |
shield | -0.022 |
house | -0.019 |
Token | L |
Token ID | 43 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
es | +0.002 |
oc | +0.002 |
diary | +0.002 |
shield | +0.002 |
house | +0.002 |
Neg logit contributions | |
aa | -0.003 |
oe | -0.002 |
oes | -0.002 |
Kids | -0.002 |
round | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
shield | +0.001 |
diary | +0.001 |
es | +0.001 |
oc | +0.001 |
shields | +0.001 |
Neg logit contributions | |
aa | -0.001 |
Kids | -0.001 |
oe | -0.001 |
oes | -0.001 |
round | -0.001 |
Token | Coco |
Token ID | 48222 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
diary | +0.020 |
shield | +0.019 |
oc | +0.019 |
es | +0.019 |
onel | +0.018 |
Neg logit contributions | |
aa | -0.016 |
oe | -0.015 |
Kids | -0.015 |
oes | -0.014 |
round | -0.014 |
Token | holds |
Token ID | 6622 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
diary | +0.017 |
shield | +0.016 |
oc | +0.016 |
es | +0.015 |
journal | +0.015 |
Neg logit contributions | |
aa | -0.013 |
oe | -0.013 |
Kids | -0.012 |
oes | -0.012 |
round | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
aa | +0.008 |
oe | +0.007 |
Kids | +0.007 |
oes | +0.007 |
round | +0.007 |
Neg logit contributions | |
diary | -0.009 |
shield | -0.009 |
oc | -0.008 |
es | -0.008 |
shields | -0.008 |
Token | other |
Token ID | 584 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
aa | +0.015 |
oe | +0.014 |
oes | +0.013 |
Kids | +0.013 |
round | +0.012 |
Neg logit contributions | |
es | -0.017 |
oc | -0.017 |
diary | -0.016 |
shield | -0.016 |
house | -0.015 |
Token | end |
Token ID | 886 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
aa | +0.036 |
oe | +0.035 |
oes | +0.033 |
Kids | +0.032 |
round | +0.031 |
Neg logit contributions | |
oc | -0.036 |
diary | -0.036 |
shield | -0.035 |
es | -0.034 |
Majesty | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Kids | +0.147 |
aa | +0.142 |
sur | +0.130 |
Abbey | +0.127 |
round | +0.126 |
Neg logit contributions | |
es | -0.122 |
diary | -0.119 |
shield | -0.116 |
house | -0.112 |
journal | -0.104 |
Token | Coco |
Token ID | 48222 |
Feature activation | +8.67e-02 |
Pos logit contributions | |
aa | +0.029 |
Kids | +0.027 |
oe | +0.027 |
oes | +0.026 |
round | +0.024 |
Neg logit contributions | |
diary | -0.040 |
shield | -0.039 |
oc | -0.038 |
es | -0.038 |
journal | -0.036 |
Token | is |
Token ID | 318 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
diary | +0.003 |
shield | +0.003 |
oc | +0.003 |
es | +0.003 |
journal | +0.003 |
Neg logit contributions | |
aa | -0.002 |
oe | -0.002 |
Kids | -0.002 |
oes | -0.002 |
round | -0.002 |
Token | smart |
Token ID | 4451 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
aa | +0.015 |
oe | +0.014 |
Kids | +0.014 |
oes | +0.013 |
round | +0.013 |
Neg logit contributions | |
diary | -0.016 |
shield | -0.016 |
oc | -0.016 |
es | -0.016 |
journal | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
diary | +0.011 |
shield | +0.011 |
oc | +0.011 |
es | +0.010 |
journal | +0.010 |
Neg logit contributions | |
aa | -0.006 |
oe | -0.005 |
Kids | -0.005 |
oes | -0.005 |
round | -0.005 |
Token | slide |
Token ID | 10649 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
aa | +0.025 |
Kids | +0.024 |
oe | +0.024 |
oes | +0.023 |
round | +0.021 |
Neg logit contributions | |
shield | -0.027 |
diary | -0.027 |
oc | -0.025 |
es | -0.024 |
journal | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Kids | +0.085 |
aa | +0.084 |
Fre | +0.077 |
Abbey | +0.077 |
iki | +0.076 |
Neg logit contributions | |
house | -0.039 |
es | -0.034 |
oc | -0.032 |
shield | -0.028 |
diary | -0.028 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
aa | +0.057 |
oe | +0.054 |
oes | +0.051 |
Kids | +0.051 |
round | +0.049 |
Neg logit contributions | |
diary | -0.049 |
es | -0.049 |
oc | -0.048 |
shield | -0.048 |
house | -0.046 |
Token | wants |
Token ID | 3382 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
aa | +0.043 |
oe | +0.042 |
Kids | +0.041 |
oes | +0.041 |
round | +0.038 |
Neg logit contributions | |
shield | -0.033 |
diary | -0.032 |
es | -0.032 |
oc | -0.031 |
shields | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
aa | +0.064 |
ora | +0.063 |
Kids | +0.062 |
oe | +0.060 |
sur | +0.057 |
Neg logit contributions | |
something | -0.069 |
bones | -0.069 |
traps | -0.067 |
es | -0.067 |
shield | -0.066 |
Token | go |
Token ID | 467 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
Kids | +0.081 |
aa | +0.076 |
oe | +0.070 |
ho | +0.068 |
ora | +0.067 |
Neg logit contributions | |
shield | -0.048 |
house | -0.044 |
oc | -0.039 |
whatever | -0.039 |
diary | -0.039 |
Token | on |
Token ID | 319 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Kids | +0.184 |
iya | +0.169 |
aa | +0.162 |
pastor | +0.160 |
Fre | +0.159 |
Neg logit contributions | |
house | -0.079 |
whatever | -0.061 |
shield | -0.060 |
es | -0.060 |
weapon | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
aa | +0.040 |
oes | +0.038 |
Kids | +0.038 |
oe | +0.036 |
round | +0.035 |
Neg logit contributions | |
shield | -0.028 |
diary | -0.027 |
es | -0.026 |
oc | -0.024 |
shields | -0.024 |
Token | slide |
Token ID | 10649 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
aa | +0.032 |
Kids | +0.031 |
oes | +0.028 |
oe | +0.028 |
ora | +0.027 |
Neg logit contributions | |
shield | -0.030 |
diary | -0.027 |
journal | -0.025 |
sword | -0.025 |
chest | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Kids | +0.111 |
aa | +0.105 |
leaf | +0.099 |
iki | +0.094 |
sur | +0.094 |
Neg logit contributions | |
es | -0.050 |
house | -0.049 |
oc | -0.047 |
shield | -0.042 |
diary | -0.040 |
Token | He |
Token ID | 679 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
aa | +0.055 |
oe | +0.052 |
Kids | +0.051 |
oes | +0.050 |
round | +0.050 |
Neg logit contributions | |
oc | -0.034 |
es | -0.033 |
shield | -0.032 |
diary | -0.031 |
house | -0.030 |
Token | 's |
Token ID | 338 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
diary | +0.003 |
shield | +0.002 |
es | +0.002 |
oc | +0.002 |
journal | +0.002 |
Neg logit contributions | |
aa | -0.007 |
oe | -0.007 |
Kids | -0.007 |
oes | -0.007 |
round | -0.007 |
Token | go |
Token ID | 467 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
aa | +0.009 |
oe | +0.009 |
Kids | +0.009 |
oes | +0.009 |
round | +0.008 |
Neg logit contributions | |
diary | -0.013 |
shield | -0.013 |
es | -0.013 |
oc | -0.013 |
shields | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
Kids | +0.129 |
aa | +0.114 |
pastor | +0.114 |
Ice | +0.111 |
Abbey | +0.110 |
Neg logit contributions | |
house | -0.088 |
es | -0.084 |
oc | -0.084 |
shield | -0.079 |
diary | -0.077 |
Token | find |
Token ID | 1064 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
aa | +0.004 |
oe | +0.004 |
Kids | +0.004 |
oes | +0.004 |
round | +0.003 |
Neg logit contributions | |
shield | -0.005 |
diary | -0.005 |
es | -0.005 |
oc | -0.005 |
journal | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
shield | +0.005 |
diary | +0.005 |
oc | +0.005 |
es | +0.005 |
istered | +0.005 |
Neg logit contributions | |
aa | -0.006 |
oe | -0.006 |
Kids | -0.005 |
oes | -0.005 |
round | -0.005 |
Token | end |
Token ID | 886 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
aa | +0.019 |
Kids | +0.017 |
oe | +0.017 |
oes | +0.016 |
round | +0.016 |
Neg logit contributions | |
diary | -0.023 |
shield | -0.023 |
es | -0.021 |
journal | -0.021 |
oc | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Kids | +0.154 |
aa | +0.153 |
sur | +0.146 |
Abbey | +0.133 |
pastor | +0.131 |
Neg logit contributions | |
es | -0.120 |
house | -0.108 |
diary | -0.105 |
webs | -0.097 |
journal | -0.092 |
Token | it |
Token ID | 340 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
aa | +0.037 |
Kids | +0.035 |
oe | +0.035 |
oes | +0.035 |
round | +0.033 |
Neg logit contributions | |
shield | -0.029 |
diary | -0.029 |
es | -0.027 |
oc | -0.026 |
shields | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
aa | +0.015 |
oe | +0.014 |
Kids | +0.014 |
oes | +0.014 |
round | +0.013 |
Neg logit contributions | |
diary | -0.013 |
shield | -0.013 |
es | -0.013 |
oc | -0.012 |
shields | -0.011 |
Token | Maybe |
Token ID | 6674 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
aa | +0.005 |
oe | +0.004 |
Kids | +0.004 |
oes | +0.004 |
round | +0.004 |
Neg logit contributions | |
diary | -0.003 |
shield | -0.003 |
es | -0.003 |
oc | -0.003 |
shields | -0.003 |
Token | there |
Token ID | 612 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
aa | +0.063 |
Kids | +0.060 |
oe | +0.059 |
round | +0.056 |
oes | +0.055 |
Neg logit contributions | |
diary | -0.045 |
shield | -0.045 |
es | -0.042 |
journal | -0.039 |
shields | -0.038 |
Token | big |
Token ID | 1263 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
oes | +0.011 |
aa | +0.011 |
Kids | +0.011 |
oe | +0.010 |
round | +0.010 |
Neg logit contributions | |
diary | -0.012 |
shield | -0.011 |
journal | -0.010 |
oc | -0.010 |
house | -0.010 |
Token | slide |
Token ID | 10649 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
aa | +0.018 |
Kids | +0.017 |
oe | +0.017 |
oes | +0.017 |
round | +0.015 |
Neg logit contributions | |
diary | -0.018 |
shield | -0.018 |
oc | -0.017 |
es | -0.016 |
journal | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
Kids | +0.058 |
aa | +0.056 |
Fre | +0.050 |
sur | +0.050 |
Abbey | +0.050 |
Neg logit contributions | |
house | -0.036 |
es | -0.032 |
oc | -0.031 |
diary | -0.030 |
shield | -0.029 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
aa | +0.010 |
oes | +0.009 |
oe | +0.009 |
Kids | +0.009 |
round | +0.008 |
Neg logit contributions | |
shield | -0.011 |
diary | -0.011 |
es | -0.010 |
oc | -0.010 |
shields | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
aa | +0.064 |
Kids | +0.064 |
sur | +0.063 |
ora | +0.062 |
oes | +0.056 |
Neg logit contributions | |
something | -0.073 |
no | -0.071 |
nothing | -0.071 |
es | -0.070 |
diary | -0.069 |
Token | go |
Token ID | 467 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
Kids | +0.062 |
aa | +0.061 |
oe | +0.055 |
ora | +0.052 |
ho | +0.051 |
Neg logit contributions | |
shield | -0.038 |
house | -0.035 |
oc | -0.033 |
diary | -0.032 |
whatever | -0.031 |
Token | on |
Token ID | 319 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Kids | +0.181 |
pastor | +0.162 |
iya | +0.159 |
aa | +0.157 |
Fre | +0.157 |
Neg logit contributions | |
house | -0.078 |
whatever | -0.064 |
es | -0.063 |
shield | -0.062 |
oc | -0.059 |
Token | it |
Token ID | 340 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
aa | +0.042 |
oes | +0.040 |
Kids | +0.040 |
oe | +0.038 |
round | +0.037 |
Neg logit contributions | |
diary | -0.031 |
shield | -0.031 |
es | -0.029 |
oc | -0.027 |
webs | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
aa | +0.036 |
Kids | +0.034 |
oe | +0.034 |
oes | +0.033 |
round | +0.031 |
Neg logit contributions | |
diary | -0.032 |
shield | -0.032 |
es | -0.031 |
oc | -0.030 |
shields | -0.028 |
Token | She |
Token ID | 1375 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
aa | +0.067 |
oe | +0.066 |
oes | +0.065 |
Kids | +0.064 |
round | +0.062 |
Neg logit contributions | |
diary | -0.061 |
es | -0.059 |
oc | -0.058 |
shield | -0.057 |
house | -0.054 |
Token | ran |
Token ID | 4966 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
oes | +0.042 |
aa | +0.039 |
oe | +0.039 |
Kids | +0.037 |
round | +0.036 |
Neg logit contributions | |
shield | -0.043 |
es | -0.042 |
oc | -0.041 |
diary | -0.040 |
house | -0.038 |
Token | starting |
Token ID | 3599 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
aa | +0.022 |
Kids | +0.021 |
oes | +0.021 |
oe | +0.020 |
round | +0.020 |
Neg logit contributions | |
shield | -0.018 |
diary | -0.018 |
es | -0.017 |
house | -0.016 |
vel | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
Kids | +0.035 |
aa | +0.035 |
round | +0.033 |
oes | +0.032 |
oe | +0.030 |
Neg logit contributions | |
diary | -0.086 |
shield | -0.083 |
es | -0.082 |
webs | -0.078 |
house | -0.076 |
Token | feel |
Token ID | 1254 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
aa | +0.013 |
oe | +0.013 |
Kids | +0.012 |
oes | +0.012 |
round | +0.011 |
Neg logit contributions | |
diary | -0.012 |
shield | -0.012 |
es | -0.012 |
oc | -0.012 |
shields | -0.011 |
Token | cold |
Token ID | 4692 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
aa | +0.004 |
oe | +0.004 |
Kids | +0.004 |
oes | +0.004 |
sur | +0.003 |
Neg logit contributions | |
oc | -0.006 |
es | -0.006 |
diary | -0.006 |
shield | -0.006 |
shields | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
aa | +0.018 |
Kids | +0.018 |
oe | +0.017 |
oes | +0.017 |
round | +0.016 |
Neg logit contributions | |
diary | -0.012 |
shield | -0.012 |
es | -0.011 |
oc | -0.010 |
house | -0.010 |
Token | Then |
Token ID | 3244 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
shield | +0.066 |
oc | +0.066 |
istered | +0.062 |
shields | +0.062 |
vel | +0.061 |
Neg logit contributions | |
Kids | -0.029 |
aa | -0.029 |
oes | -0.027 |
oe | -0.027 |
to | -0.026 |
Token | she |
Token ID | 673 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
oc | +0.115 |
onel | +0.113 |
istered | +0.112 |
cod | +0.109 |
osaurus | +0.107 |
Neg logit contributions | |
to | -0.040 |
aa | -0.033 |
oe | -0.032 |
Kids | -0.029 |
slowly | -0.029 |
Token | saw |
Token ID | 2497 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
aa | +0.011 |
oe | +0.011 |
oes | +0.011 |
Kids | +0.010 |
round | +0.010 |
Neg logit contributions | |
shield | -0.012 |
diary | -0.011 |
es | -0.011 |
oc | -0.010 |
shields | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
oc | +0.034 |
istered | +0.030 |
vel | +0.029 |
es | +0.029 |
shield | +0.028 |
Neg logit contributions | |
aa | -0.024 |
Kids | -0.023 |
Kay | -0.023 |
Su | -0.022 |
to | -0.022 |
Token | gentleman |
Token ID | 22427 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
diary | +0.006 |
shield | +0.006 |
oc | +0.005 |
journal | +0.005 |
es | +0.005 |
Neg logit contributions | |
aa | -0.006 |
oes | -0.005 |
Kids | -0.005 |
oe | -0.005 |
round | -0.005 |
Token | walking |
Token ID | 6155 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
diary | +0.032 |
shield | +0.032 |
es | +0.031 |
oc | +0.030 |
journal | +0.028 |
Neg logit contributions | |
aa | -0.034 |
oe | -0.032 |
Kids | -0.032 |
oes | -0.031 |
round | -0.029 |
Token | " |
Token ID | 366 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
aa | +0.007 |
oe | +0.007 |
Kids | +0.007 |
oes | +0.007 |
round | +0.006 |
Neg logit contributions | |
diary | -0.006 |
shield | -0.006 |
es | -0.006 |
oc | -0.006 |
journal | -0.005 |
Token | Oh |
Token ID | 5812 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
aa | +0.016 |
oe | +0.016 |
oes | +0.015 |
Kids | +0.015 |
round | +0.014 |
Neg logit contributions | |
diary | -0.017 |
shield | -0.017 |
oc | -0.017 |
es | -0.017 |
journal | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
diary | +0.092 |
shields | +0.091 |
oc | +0.091 |
webs | +0.089 |
bes | +0.089 |
Neg logit contributions | |
aa | -0.056 |
Su | -0.055 |
oe | -0.052 |
Jen | -0.051 |
Kay | -0.048 |
Token | Ben |
Token ID | 3932 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
oc | +0.022 |
es | +0.021 |
house | +0.020 |
opes | +0.019 |
webs | +0.019 |
Neg logit contributions | |
aa | -0.011 |
Sara | -0.010 |
Kids | -0.010 |
sur | -0.010 |
dads | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
shield | +0.085 |
diary | +0.085 |
shields | +0.082 |
onel | +0.082 |
webs | +0.079 |
Neg logit contributions | |
aa | -0.060 |
oe | -0.058 |
Kids | -0.050 |
oes | -0.048 |
to | -0.045 |
Token | you |
Token ID | 345 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
oc | +0.023 |
es | +0.022 |
diary | +0.021 |
shield | +0.021 |
shields | +0.021 |
Neg logit contributions | |
aa | -0.018 |
Kids | -0.017 |
to | -0.017 |
oes | -0.016 |
oe | -0.016 |
Token | have |
Token ID | 423 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
diary | +0.083 |
Majesty | +0.078 |
shield | +0.077 |
journal | +0.076 |
shields | +0.075 |
Neg logit contributions | |
aa | -0.056 |
oe | -0.045 |
packed | -0.044 |
se | -0.042 |
Kids | -0.041 |
Token | a |
Token ID | 257 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
oc | +0.048 |
shield | +0.047 |
diary | +0.047 |
es | +0.047 |
journal | +0.044 |
Neg logit contributions | |
aa | -0.017 |
oe | -0.015 |
Kids | -0.014 |
oes | -0.013 |
round | -0.011 |
Token | high |
Token ID | 1029 |
Feature activation | -8.91e-02 |
Pos logit contributions | |
es | +0.002 |
diary | +0.002 |
shield | +0.002 |
oc | +0.002 |
shields | +0.001 |
Neg logit contributions | |
aa | -0.002 |
oe | -0.002 |
Kids | -0.002 |
oes | -0.002 |
round | -0.002 |
Token | temperature |
Token ID | 5951 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
aa | +0.003 |
oe | +0.002 |
oes | +0.002 |
Kids | +0.002 |
round | +0.002 |
Neg logit contributions | |
es | -0.003 |
diary | -0.003 |
shield | -0.003 |
oc | -0.003 |
onel | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
aa | +0.015 |
Kids | +0.015 |
oe | +0.014 |
oes | +0.014 |
round | +0.013 |
Neg logit contributions | |
diary | -0.014 |
es | -0.014 |
shield | -0.014 |
oc | -0.014 |
house | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
shield | +0.042 |
diary | +0.041 |
es | +0.039 |
oc | +0.039 |
shields | +0.037 |
Neg logit contributions | |
aa | -0.030 |
oe | -0.029 |
Kids | -0.028 |
oes | -0.027 |
round | -0.025 |
Token | L |
Token ID | 43 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
shield | +0.069 |
diary | +0.068 |
es | +0.064 |
traps | +0.062 |
shields | +0.062 |
Neg logit contributions | |
Kids | -0.056 |
aa | -0.053 |
oe | -0.052 |
oes | -0.045 |
round | -0.045 |
Token | ily |
Token ID | 813 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
aa | +0.035 |
oe | +0.034 |
Kids | +0.034 |
oes | +0.032 |
round | +0.030 |
Neg logit contributions | |
shield | -0.035 |
diary | -0.034 |
es | -0.033 |
oc | -0.033 |
shields | -0.031 |
Token | hugged |
Token ID | 41130 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
diary | +0.000 |
shield | +0.000 |
es | +0.000 |
oc | +0.000 |
shields | +0.000 |
Neg logit contributions | |
aa | -0.000 |
oe | -0.000 |
Kids | -0.000 |
oes | -0.000 |
round | -0.000 |
Token | her |
Token ID | 607 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
aa | +0.009 |
oe | +0.008 |
Kids | +0.008 |
oes | +0.008 |
round | +0.008 |
Neg logit contributions | |
diary | -0.005 |
shield | -0.005 |
es | -0.005 |
oc | -0.005 |
shields | -0.004 |
Token | doll |
Token ID | 3654 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
oc | +0.021 |
es | +0.020 |
diary | +0.019 |
shield | +0.019 |
onel | +0.019 |
Neg logit contributions | |
aa | -0.020 |
oe | -0.019 |
Kids | -0.017 |
oes | -0.017 |
sur | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
diary | +0.100 |
shield | +0.099 |
es | +0.099 |
onel | +0.097 |
oc | +0.097 |
Neg logit contributions | |
aa | -0.052 |
oe | -0.051 |
oes | -0.045 |
round | -0.044 |
Kids | -0.039 |
Token | smiled |
Token ID | 13541 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
diary | +0.030 |
shield | +0.030 |
oc | +0.030 |
es | +0.029 |
vel | +0.028 |
Neg logit contributions | |
aa | -0.014 |
Kids | -0.013 |
oe | -0.013 |
oes | -0.011 |
sur | -0.010 |
Token | back |
Token ID | 736 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
diary | +0.015 |
oc | +0.014 |
shield | +0.014 |
es | +0.014 |
traps | +0.014 |
Neg logit contributions | |
aa | -0.012 |
oe | -0.011 |
Kids | -0.010 |
oes | -0.010 |
sur | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
diary | +0.014 |
shield | +0.014 |
es | +0.014 |
oc | +0.013 |
shields | +0.012 |
Neg logit contributions | |
aa | -0.015 |
oe | -0.014 |
Kids | -0.014 |
oes | -0.014 |
round | -0.013 |
Token | feeling |
Token ID | 4203 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
aa | +0.033 |
oe | +0.032 |
oes | +0.032 |
Kids | +0.032 |
round | +0.029 |
Neg logit contributions | |
shield | -0.030 |
diary | -0.030 |
es | -0.028 |
oc | -0.027 |
house | -0.026 |
Token | had |
Token ID | 550 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
aa | +0.004 |
oe | +0.003 |
oes | +0.003 |
Kids | +0.003 |
round | +0.003 |
Neg logit contributions | |
shield | -0.005 |
es | -0.005 |
diary | -0.005 |
oc | -0.005 |
house | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
diary | +0.016 |
shield | +0.016 |
es | +0.015 |
oc | +0.015 |
shields | +0.013 |
Neg logit contributions | |
aa | -0.025 |
oe | -0.024 |
Kids | -0.024 |
oes | -0.023 |
round | -0.022 |
Token | toy |
Token ID | 13373 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
es | +0.005 |
diary | +0.005 |
shield | +0.005 |
oc | +0.005 |
shields | +0.005 |
Neg logit contributions | |
aa | -0.004 |
oe | -0.004 |
Kids | -0.004 |
oes | -0.004 |
round | -0.004 |
Token | soldier |
Token ID | 10686 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
es | +0.050 |
oc | +0.050 |
vel | +0.049 |
diary | +0.048 |
Majesty | +0.046 |
Neg logit contributions | |
aa | -0.055 |
oe | -0.053 |
oes | -0.051 |
round | -0.050 |
Kids | -0.047 |
Token | in |
Token ID | 287 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
onel | +0.055 |
diary | +0.055 |
shield | +0.055 |
oc | +0.054 |
shields | +0.054 |
Neg logit contributions | |
aa | -0.045 |
oe | -0.042 |
round | -0.039 |
oes | -0.037 |
Kids | -0.037 |
Token | his |
Token ID | 465 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
diary | +0.010 |
shield | +0.010 |
es | +0.010 |
oc | +0.009 |
shields | +0.009 |
Neg logit contributions | |
aa | -0.011 |
oe | -0.011 |
Kids | -0.010 |
oes | -0.010 |
round | -0.010 |
Token | hand |
Token ID | 1021 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
es | +0.080 |
vel | +0.077 |
onel | +0.076 |
oc | +0.071 |
shield | +0.071 |
Neg logit contributions | |
aa | -0.062 |
oe | -0.061 |
oes | -0.058 |
to | -0.054 |
Kids | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
diary | +0.011 |
shield | +0.010 |
es | +0.010 |
oc | +0.010 |
shields | +0.009 |
Neg logit contributions | |
aa | -0.011 |
oe | -0.010 |
Kids | -0.010 |
oes | -0.010 |
round | -0.009 |
Token | Tim |
Token ID | 5045 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
aa | +0.029 |
oe | +0.028 |
Kids | +0.027 |
oes | +0.027 |
round | +0.026 |
Neg logit contributions | |
shield | -0.018 |
oc | -0.018 |
diary | -0.018 |
es | -0.017 |
house | -0.016 |
Token | my |
Token ID | 1820 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
aa | +0.008 |
oe | +0.007 |
Kids | +0.007 |
oes | +0.007 |
round | +0.007 |
Neg logit contributions | |
diary | -0.009 |
shield | -0.009 |
es | -0.009 |
oc | -0.008 |
house | -0.008 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
aa | +0.004 |
oe | +0.003 |
Kids | +0.003 |
oes | +0.003 |
round | +0.003 |
Neg logit contributions | |
diary | -0.005 |
shield | -0.005 |
es | -0.005 |
oc | -0.004 |
journal | -0.004 |
Token | bath |
Token ID | 7837 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
diary | +0.023 |
es | +0.023 |
shield | +0.023 |
oc | +0.023 |
house | +0.021 |
Neg logit contributions | |
aa | -0.023 |
oe | -0.022 |
Kids | -0.022 |
oes | -0.021 |
round | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
aa | +0.019 |
oe | +0.018 |
Kids | +0.018 |
oes | +0.017 |
round | +0.017 |
Neg logit contributions | |
shield | -0.015 |
diary | -0.015 |
es | -0.015 |
oc | -0.014 |
journal | -0.013 |
Token | He |
Token ID | 679 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
aa | +0.020 |
oe | +0.019 |
Kids | +0.019 |
oes | +0.018 |
round | +0.017 |
Neg logit contributions | |
diary | -0.020 |
shield | -0.020 |
es | -0.020 |
oc | -0.019 |
shields | -0.018 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
aa | +0.017 |
oe | +0.016 |
oes | +0.016 |
Kids | +0.016 |
round | +0.015 |
Neg logit contributions | |
shield | -0.017 |
diary | -0.016 |
es | -0.016 |
oc | -0.015 |
shields | -0.015 |
Token | his |
Token ID | 465 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
oe | +0.039 |
aa | +0.039 |
Kids | +0.036 |
oes | +0.034 |
ora | +0.033 |
Neg logit contributions | |
shield | -0.065 |
diary | -0.062 |
shields | -0.060 |
es | -0.059 |
webs | -0.059 |
Token | robot |
Token ID | 9379 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
es | +0.034 |
vel | +0.032 |
oc | +0.030 |
onel | +0.030 |
istered | +0.029 |
Neg logit contributions | |
aa | -0.038 |
oe | -0.036 |
oes | -0.035 |
Kids | -0.033 |
weekend | -0.033 |
Token | very |
Token ID | 845 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
istered | +0.106 |
onel | +0.105 |
oc | +0.103 |
vel | +0.102 |
alas | +0.102 |
Neg logit contributions | |
to | -0.045 |
aa | -0.042 |
oes | -0.042 |
oe | -0.041 |
round | -0.040 |
Token | much |
Token ID | 881 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
diary | +0.005 |
shield | +0.005 |
es | +0.005 |
oc | +0.005 |
shields | +0.005 |
Neg logit contributions | |
aa | -0.006 |
oe | -0.005 |
Kids | -0.005 |
oes | -0.005 |
round | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
aa | +0.028 |
Kids | +0.027 |
oe | +0.027 |
oes | +0.026 |
round | +0.024 |
Neg logit contributions | |
diary | -0.024 |
shield | -0.024 |
es | -0.024 |
oc | -0.023 |
journal | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
aa | +0.013 |
Kids | +0.012 |
oe | +0.012 |
oes | +0.012 |
round | +0.011 |
Neg logit contributions | |
diary | -0.018 |
shield | -0.017 |
es | -0.017 |
oc | -0.016 |
shields | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
aa | +0.025 |
oe | +0.023 |
Kids | +0.023 |
oes | +0.023 |
round | +0.022 |
Neg logit contributions | |
diary | -0.023 |
oc | -0.022 |
shield | -0.022 |
es | -0.022 |
journal | -0.020 |
Token | he |
Token ID | 339 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
aa | +0.030 |
oe | +0.029 |
Kids | +0.028 |
oes | +0.028 |
round | +0.026 |
Neg logit contributions | |
diary | -0.030 |
shield | -0.029 |
es | -0.028 |
oc | -0.028 |
journal | -0.026 |
Token | could |
Token ID | 714 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
aa | +0.021 |
oe | +0.020 |
Kids | +0.020 |
oes | +0.020 |
round | +0.019 |
Neg logit contributions | |
es | -0.016 |
shield | -0.016 |
diary | -0.016 |
oc | -0.015 |
webs | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
Kids | +0.029 |
aa | +0.029 |
oe | +0.027 |
oes | +0.027 |
round | +0.026 |
Neg logit contributions | |
shield | -0.021 |
es | -0.020 |
diary | -0.020 |
oc | -0.018 |
house | -0.017 |
Token | finally |
Token ID | 3443 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
diary | +0.032 |
shield | +0.031 |
es | +0.030 |
oc | +0.030 |
journal | +0.030 |
Neg logit contributions | |
aa | -0.024 |
oe | -0.023 |
Kids | -0.022 |
oes | -0.021 |
round | -0.020 |
Token | got |
Token ID | 1392 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
diary | +0.014 |
shield | +0.013 |
oc | +0.013 |
es | +0.012 |
journal | +0.012 |
Neg logit contributions | |
aa | -0.011 |
oe | -0.011 |
Kids | -0.010 |
oes | -0.010 |
round | -0.009 |
Token | away |
Token ID | 1497 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
aa | +0.016 |
Kids | +0.015 |
oe | +0.015 |
oes | +0.014 |
round | +0.014 |
Neg logit contributions | |
shield | -0.016 |
diary | -0.016 |
es | -0.015 |
oc | -0.015 |
shields | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
shield | +0.012 |
diary | +0.012 |
es | +0.012 |
oc | +0.012 |
shields | +0.011 |
Neg logit contributions | |
aa | -0.009 |
oe | -0.008 |
Kids | -0.008 |
oes | -0.008 |
round | -0.007 |
Token | He |
Token ID | 679 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
diary | +0.041 |
shield | +0.041 |
vel | +0.038 |
journal | +0.037 |
onel | +0.037 |
Neg logit contributions | |
aa | -0.025 |
oe | -0.024 |
Kids | -0.024 |
oes | -0.023 |
round | -0.021 |
Token | decided |
Token ID | 3066 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
shield | +0.002 |
diary | +0.002 |
es | +0.002 |
oc | +0.002 |
shields | +0.002 |
Neg logit contributions | |
aa | -0.002 |
oe | -0.002 |
Kids | -0.002 |
oes | -0.002 |
round | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
aa | +0.007 |
Kids | +0.006 |
oe | +0.006 |
oes | +0.006 |
ora | +0.005 |
Neg logit contributions | |
shield | -0.015 |
diary | -0.015 |
es | -0.015 |
traps | -0.014 |
oc | -0.014 |
Token | stick |
Token ID | 4859 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
aa | +0.023 |
oe | +0.022 |
Kids | +0.022 |
oes | +0.021 |
round | +0.020 |
Neg logit contributions | |
shield | -0.027 |
diary | -0.027 |
es | -0.026 |
oc | -0.025 |
shields | -0.024 |
Token | A |
Token ID | 317 |
Feature activation | +9.57e-02 |
Pos logit contributions | |
aa | +0.029 |
oe | +0.028 |
oes | +0.027 |
Kids | +0.027 |
round | +0.026 |
Neg logit contributions | |
diary | -0.025 |
shield | -0.024 |
es | -0.024 |
oc | -0.023 |
webs | -0.021 |
Token | puppy |
Token ID | 26188 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
shield | +0.003 |
diary | +0.003 |
oc | +0.003 |
es | +0.003 |
journal | +0.003 |
Neg logit contributions | |
aa | -0.003 |
oes | -0.003 |
Kids | -0.003 |
oe | -0.003 |
round | -0.003 |
Token | suddenly |
Token ID | 6451 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
diary | +0.057 |
Majesty | +0.057 |
shield | +0.056 |
istered | +0.056 |
shields | +0.056 |
Neg logit contributions | |
aa | -0.028 |
oe | -0.027 |
Kids | -0.026 |
ho | -0.021 |
round | -0.021 |
Token | appeared |
Token ID | 4120 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
diary | +0.041 |
shield | +0.040 |
oc | +0.039 |
es | +0.039 |
journal | +0.037 |
Neg logit contributions | |
aa | -0.027 |
oe | -0.025 |
Kids | -0.024 |
oes | -0.023 |
round | -0.021 |
Token | from |
Token ID | 422 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
diary | +0.028 |
shield | +0.028 |
es | +0.027 |
oc | +0.026 |
journal | +0.025 |
Neg logit contributions | |
aa | -0.022 |
Kids | -0.021 |
oe | -0.021 |
oes | -0.020 |
round | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
shield | +0.004 |
diary | +0.004 |
es | +0.004 |
oc | +0.004 |
shields | +0.004 |
Neg logit contributions | |
aa | -0.004 |
oe | -0.003 |
Kids | -0.003 |
oes | -0.003 |
round | -0.003 |
Token | ground |
Token ID | 2323 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
aa | +0.003 |
oe | +0.003 |
Kids | +0.003 |
oes | +0.003 |
round | +0.003 |
Neg logit contributions | |
diary | -0.003 |
shield | -0.003 |
es | -0.003 |
oc | -0.003 |
journal | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
diary | +0.022 |
shield | +0.022 |
es | +0.022 |
oc | +0.021 |
house | +0.020 |
Neg logit contributions | |
aa | -0.023 |
Kids | -0.022 |
oe | -0.022 |
oes | -0.021 |
round | -0.020 |
Token | Lori |
Token ID | 43741 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
oe | +0.073 |
aa | +0.073 |
oes | +0.072 |
Kids | +0.069 |
round | +0.068 |
Neg logit contributions | |
diary | -0.058 |
es | -0.057 |
shield | -0.057 |
oc | -0.054 |
webs | -0.050 |
Token | was |
Token ID | 373 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
diary | +0.007 |
shield | +0.006 |
es | +0.006 |
oc | +0.006 |
shields | +0.006 |
Neg logit contributions | |
aa | -0.005 |
oe | -0.005 |
Kids | -0.005 |
oes | -0.005 |
round | -0.004 |
Token | so |
Token ID | 523 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
diary | +0.016 |
shield | +0.016 |
es | +0.015 |
oc | +0.015 |
journal | +0.014 |
Neg logit contributions | |
aa | -0.016 |
Kids | -0.015 |
oe | -0.015 |
oes | -0.015 |
round | -0.014 |
Token | found |
Token ID | 1043 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
diary | +0.020 |
shield | +0.020 |
es | +0.019 |
oc | +0.018 |
shields | +0.017 |
Neg logit contributions | |
aa | -0.024 |
oe | -0.023 |
Kids | -0.022 |
oes | -0.022 |
round | -0.021 |
Token | it |
Token ID | 340 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
oc | +0.015 |
shield | +0.015 |
diary | +0.015 |
Majesty | +0.015 |
vel | +0.014 |
Neg logit contributions | |
aa | -0.014 |
oe | -0.013 |
oes | -0.013 |
Kids | -0.013 |
Su | -0.013 |
Token | while |
Token ID | 981 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
diary | +0.014 |
shield | +0.014 |
es | +0.014 |
oc | +0.014 |
shields | +0.013 |
Neg logit contributions | |
aa | -0.010 |
oe | -0.010 |
Kids | -0.010 |
oes | -0.009 |
round | -0.009 |
Token | they |
Token ID | 484 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
aa | +0.018 |
oe | +0.018 |
Kids | +0.017 |
oes | +0.017 |
round | +0.016 |
Neg logit contributions | |
diary | -0.015 |
shield | -0.015 |
es | -0.015 |
oc | -0.014 |
shields | -0.013 |
Token | were |
Token ID | 547 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
diary | +0.009 |
shield | +0.009 |
oc | +0.009 |
es | +0.008 |
Majesty | +0.008 |
Neg logit contributions | |
aa | -0.006 |
oe | -0.006 |
Kids | -0.006 |
oes | -0.005 |
ho | -0.005 |
Token | out |
Token ID | 503 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
diary | +0.006 |
shield | +0.006 |
es | +0.006 |
oc | +0.006 |
shields | +0.005 |
Neg logit contributions | |
aa | -0.006 |
oe | -0.006 |
Kids | -0.006 |
oes | -0.005 |
round | -0.005 |
Token | playing |
Token ID | 2712 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
diary | +0.025 |
shield | +0.025 |
es | +0.024 |
oc | +0.024 |
shields | +0.023 |
Neg logit contributions | |
aa | -0.020 |
oe | -0.019 |
Kids | -0.019 |
oes | -0.018 |
round | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
Majesty | +0.047 |
ience | +0.045 |
istered | +0.044 |
fears | +0.044 |
onel | +0.043 |
Neg logit contributions | |
to | -0.014 |
oe | -0.013 |
towards | -0.011 |
Kids | -0.009 |
weekend | -0.009 |
Token | The |
Token ID | 383 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
aa | +0.027 |
oe | +0.025 |
Kids | +0.024 |
oes | +0.024 |
round | +0.023 |
Neg logit contributions | |
diary | -0.023 |
es | -0.023 |
oc | -0.023 |
shield | -0.023 |
house | -0.022 |
Token | children |
Token ID | 1751 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
es | +0.019 |
oc | +0.018 |
vel | +0.017 |
istered | +0.017 |
onel | +0.017 |
Neg logit contributions | |
elderly | -0.012 |
vendor | -0.011 |
weekend | -0.011 |
aa | -0.010 |
Kids | -0.010 |
Token | had |
Token ID | 550 |
Feature activation | +8.81e-03 |
Pos logit contributions | |
aa | +0.013 |
oe | +0.013 |
Kids | +0.013 |
oes | +0.012 |
round | +0.012 |
Neg logit contributions | |
diary | -0.014 |
shield | -0.014 |
es | -0.014 |
oc | -0.013 |
shields | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
aa | +0.002 |
oe | +0.002 |
Kids | +0.002 |
oes | +0.002 |
round | +0.002 |
Neg logit contributions | |
diary | -0.002 |
shield | -0.002 |
oc | -0.002 |
es | -0.002 |
shields | -0.002 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
shield | +0.024 |
diary | +0.024 |
es | +0.023 |
oc | +0.022 |
shields | +0.021 |
Neg logit contributions | |
aa | -0.020 |
Kids | -0.019 |
oe | -0.019 |
oes | -0.019 |
round | -0.018 |
Token | Once |
Token ID | 7454 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
diary | +0.008 |
shield | +0.008 |
es | +0.008 |
oc | +0.008 |
shields | +0.007 |
Neg logit contributions | |
aa | -0.007 |
oe | -0.006 |
Kids | -0.006 |
oes | -0.006 |
round | -0.006 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
shield | +0.035 |
diary | +0.035 |
oc | +0.034 |
es | +0.034 |
shields | +0.032 |
Neg logit contributions | |
oe | -0.025 |
aa | -0.024 |
oes | -0.022 |
Kids | -0.021 |
weekend | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
oc | +0.036 |
es | +0.035 |
onel | +0.034 |
Majesty | +0.034 |
diary | +0.034 |
Neg logit contributions | |
aa | -0.022 |
oe | -0.022 |
Kids | -0.022 |
to | -0.021 |
weekend | -0.021 |
Token | time |
Token ID | 640 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
diary | +0.009 |
shield | +0.009 |
es | +0.009 |
oc | +0.009 |
shields | +0.009 |
Neg logit contributions | |
aa | -0.006 |
oe | -0.005 |
Kids | -0.005 |
oes | -0.005 |
round | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
shield | +0.028 |
diary | +0.028 |
oc | +0.026 |
shields | +0.026 |
es | +0.025 |
Neg logit contributions | |
oe | -0.025 |
aa | -0.024 |
oes | -0.022 |
Kids | -0.021 |
Kay | -0.019 |
Token | there |
Token ID | 612 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
oe | +0.016 |
aa | +0.016 |
Kids | +0.014 |
oes | +0.014 |
round | +0.013 |
Neg logit contributions | |
shield | -0.021 |
diary | -0.021 |
oc | -0.020 |
es | -0.020 |
shields | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
shield | +0.028 |
diary | +0.028 |
shields | +0.027 |
es | +0.026 |
oc | +0.026 |
Neg logit contributions | |
oe | -0.017 |
aa | -0.016 |
Kids | -0.016 |
oes | -0.015 |
weekend | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
aa | +0.018 |
oe | +0.018 |
Kids | +0.018 |
oes | +0.016 |
weekend | +0.016 |
Neg logit contributions | |
shield | -0.013 |
oc | -0.013 |
diary | -0.013 |
es | -0.013 |
shields | -0.012 |
Token | spoiled |
Token ID | 34781 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
shield | +0.000 |
diary | +0.000 |
oc | +0.000 |
es | +0.000 |
journal | +0.000 |
Neg logit contributions | |
aa | -0.000 |
oes | -0.000 |
oe | -0.000 |
Kids | -0.000 |
round | -0.000 |
Token | looking |
Token ID | 2045 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
diary | +0.022 |
shield | +0.021 |
oc | +0.021 |
es | +0.021 |
journal | +0.019 |
Neg logit contributions | |
aa | -0.021 |
oe | -0.021 |
Kids | -0.020 |
oes | -0.019 |
round | -0.018 |
Token | after |
Token ID | 706 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
diary | +0.009 |
shield | +0.009 |
es | +0.009 |
oc | +0.009 |
shields | +0.008 |
Neg logit contributions | |
aa | -0.007 |
oe | -0.007 |
Kids | -0.007 |
oes | -0.007 |
round | -0.006 |
Token | him |
Token ID | 683 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
aa | +0.000 |
oe | +0.000 |
Kids | +0.000 |
oes | +0.000 |
round | +0.000 |
Neg logit contributions | |
diary | -0.000 |
shield | -0.000 |
es | -0.000 |
oc | -0.000 |
shields | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
diary | +0.045 |
shield | +0.044 |
oc | +0.044 |
es | +0.043 |
webs | +0.042 |
Neg logit contributions | |
aa | -0.031 |
oe | -0.030 |
oes | -0.028 |
Kids | -0.025 |
weekend | -0.025 |
Token | They |
Token ID | 1119 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
diary | +0.014 |
shield | +0.014 |
es | +0.013 |
oc | +0.013 |
shields | +0.013 |
Neg logit contributions | |
aa | -0.013 |
Kids | -0.012 |
oe | -0.012 |
oes | -0.012 |
round | -0.011 |
Token | both |
Token ID | 1111 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
diary | +0.001 |
shield | +0.001 |
es | +0.001 |
oc | +0.001 |
journal | +0.001 |
Neg logit contributions | |
aa | -0.001 |
oe | -0.001 |
Kids | -0.001 |
oes | -0.001 |
round | -0.001 |
Token | gl |
Token ID | 1278 |
Feature activation | -5.67e-02 |
Pos logit contributions | |
diary | +0.001 |
shield | +0.001 |
es | +0.001 |
oc | +0.001 |
journal | +0.001 |
Neg logit contributions | |
aa | -0.001 |
oe | -0.000 |
Kids | -0.000 |
oes | -0.000 |
round | -0.000 |
Token | owed |
Token ID | 6972 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
aa | +0.002 |
Kids | +0.002 |
oe | +0.002 |
oes | +0.002 |
round | +0.002 |
Neg logit contributions | |
shield | -0.001 |
diary | -0.001 |
es | -0.001 |
oc | -0.001 |
shields | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
diary | +0.005 |
shield | +0.005 |
es | +0.005 |
oc | +0.005 |
shields | +0.005 |
Neg logit contributions | |
aa | -0.004 |
oe | -0.004 |
Kids | -0.004 |
oes | -0.004 |
round | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
aa | +0.012 |
oe | +0.012 |
Kids | +0.012 |
oes | +0.011 |
round | +0.011 |
Neg logit contributions | |
diary | -0.014 |
shield | -0.014 |
es | -0.014 |
oc | -0.013 |
journal | -0.013 |
Token | sun |
Token ID | 4252 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
diary | +0.013 |
shield | +0.013 |
es | +0.013 |
oc | +0.012 |
shields | +0.012 |
Neg logit contributions | |
aa | -0.010 |
oe | -0.009 |
Kids | -0.009 |
oes | -0.009 |
round | -0.008 |
Token | be |
Token ID | 307 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
aa | +0.034 |
Kids | +0.032 |
oe | +0.032 |
oes | +0.030 |
round | +0.030 |
Neg logit contributions | |
shield | -0.034 |
diary | -0.033 |
oc | -0.032 |
es | -0.032 |
house | -0.030 |
Token | two |
Token ID | 734 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
aa | +0.032 |
oe | +0.031 |
Kids | +0.030 |
oes | +0.029 |
round | +0.027 |
Neg logit contributions | |
diary | -0.035 |
shield | -0.035 |
es | -0.034 |
oc | -0.033 |
journal | -0.031 |
Token | coins |
Token ID | 10796 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
aa | +0.020 |
Kids | +0.020 |
oe | +0.020 |
oes | +0.019 |
round | +0.018 |
Neg logit contributions | |
shield | -0.018 |
diary | -0.018 |
es | -0.017 |
oc | -0.017 |
shields | -0.016 |
Token | ." |
Token ID | 526 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
diary | +0.001 |
shield | +0.001 |
es | +0.001 |
oc | +0.001 |
shields | +0.001 |
Neg logit contributions | |
aa | -0.001 |
oe | -0.001 |
Kids | -0.001 |
oes | -0.001 |
round | -0.001 |
Token | L |
Token ID | 406 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
aa | +0.028 |
oe | +0.027 |
Kids | +0.027 |
oes | +0.027 |
round | +0.025 |
Neg logit contributions | |
oc | -0.028 |
es | -0.028 |
shield | -0.027 |
diary | -0.026 |
shields | -0.024 |
Token | ila |
Token ID | 10102 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
weekend | +0.059 |
oe | +0.057 |
aa | +0.057 |
oes | +0.056 |
Kids | +0.052 |
Neg logit contributions | |
es | -0.102 |
oc | -0.087 |
onel | -0.084 |
diary | -0.084 |
vel | -0.083 |
Token | and |
Token ID | 290 |
Feature activation | -6.72e-02 |
Pos logit contributions | |
aa | +0.038 |
oe | +0.036 |
Kids | +0.036 |
oes | +0.035 |
round | +0.032 |
Neg logit contributions | |
shield | -0.056 |
diary | -0.055 |
es | -0.055 |
oc | -0.053 |
shields | -0.050 |
Token | Ben |
Token ID | 3932 |
Feature activation | -9.49e-02 |
Pos logit contributions | |
aa | +0.002 |
oe | +0.002 |
Kids | +0.002 |
oes | +0.002 |
round | +0.002 |
Neg logit contributions | |
diary | -0.002 |
shield | -0.002 |
oc | -0.002 |
es | -0.002 |
house | -0.002 |
Token | look |
Token ID | 804 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
aa | +0.002 |
oe | +0.002 |
Kids | +0.002 |
oes | +0.002 |
round | +0.002 |
Neg logit contributions | |
diary | -0.003 |
shield | -0.003 |
oc | -0.003 |
es | -0.003 |
shields | -0.003 |
Token | at |
Token ID | 379 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
diary | +0.049 |
shield | +0.049 |
es | +0.047 |
oc | +0.046 |
shields | +0.045 |
Neg logit contributions | |
aa | -0.035 |
oe | -0.033 |
Kids | -0.029 |
round | -0.029 |
oes | -0.028 |
Token | their |
Token ID | 511 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
aa | +0.006 |
oe | +0.005 |
Kids | +0.005 |
oes | +0.005 |
round | +0.005 |
Neg logit contributions | |
diary | -0.006 |
shield | -0.006 |
es | -0.006 |
oc | -0.006 |
shields | -0.006 |
Token | little |
Token ID | 1310 |
Feature activation | +9.59e-02 |
Pos logit contributions | |
oes | +0.009 |
aa | +0.009 |
oe | +0.009 |
Kids | +0.009 |
round | +0.008 |
Neg logit contributions | |
shield | -0.007 |
diary | -0.007 |
oc | -0.007 |
es | -0.006 |
journal | -0.006 |
Token | girl |
Token ID | 2576 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
shield | +0.003 |
diary | +0.003 |
oc | +0.003 |
journal | +0.003 |
es | +0.003 |
Neg logit contributions | |
Kids | -0.003 |
oes | -0.003 |
oe | -0.003 |
aa | -0.003 |
round | -0.002 |
Token | who |
Token ID | 508 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
diary | +0.013 |
shield | +0.012 |
oc | +0.012 |
es | +0.012 |
house | +0.011 |
Neg logit contributions | |
aa | -0.018 |
oe | -0.017 |
Kids | -0.017 |
oes | -0.017 |
round | -0.016 |
Token | wanted |
Token ID | 2227 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
aa | +0.016 |
oe | +0.016 |
Kids | +0.015 |
oes | +0.014 |
weekend | +0.013 |
Neg logit contributions | |
shield | -0.019 |
diary | -0.018 |
es | -0.018 |
shields | -0.018 |
oc | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
aa | +0.007 |
oe | +0.007 |
Kids | +0.006 |
round | +0.006 |
oes | +0.006 |
Neg logit contributions | |
diary | -0.014 |
shield | -0.014 |
journal | -0.013 |
es | -0.012 |
shields | -0.012 |
Token | go |
Token ID | 467 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
diary | +0.018 |
shield | +0.017 |
es | +0.017 |
oc | +0.016 |
journal | +0.016 |
Neg logit contributions | |
aa | -0.015 |
oe | -0.015 |
Kids | -0.015 |
oes | -0.014 |
round | -0.013 |
Token | sailing |
Token ID | 28499 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
Kids | +0.071 |
aa | +0.065 |
oe | +0.064 |
Abbey | +0.060 |
ho | +0.060 |
Neg logit contributions | |
shield | -0.068 |
diary | -0.067 |
es | -0.059 |
weapon | -0.058 |
journal | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
aa | +0.018 |
Kids | +0.017 |
oe | +0.017 |
oes | +0.016 |
round | +0.015 |
Neg logit contributions | |
shield | -0.018 |
diary | -0.018 |
es | -0.018 |
oc | -0.017 |
journal | -0.016 |
Token | She |
Token ID | 1375 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
diary | +0.027 |
shield | +0.025 |
es | +0.024 |
oc | +0.024 |
house | +0.023 |
Neg logit contributions | |
aa | -0.027 |
oe | -0.026 |
Kids | -0.025 |
oes | -0.024 |
round | -0.024 |
Token | asked |
Token ID | 1965 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
oes | +0.048 |
aa | +0.046 |
oe | +0.046 |
Kids | +0.044 |
round | +0.043 |
Neg logit contributions | |
shield | -0.047 |
oc | -0.046 |
es | -0.043 |
diary | -0.043 |
shields | -0.040 |
Token | her |
Token ID | 607 |
Feature activation | -8.33e-02 |
Pos logit contributions | |
diary | +0.023 |
shield | +0.022 |
es | +0.022 |
oc | +0.020 |
journal | +0.020 |
Neg logit contributions | |
aa | -0.024 |
oe | -0.023 |
Kids | -0.023 |
oes | -0.022 |
round | -0.022 |
Token | helps |
Token ID | 5419 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
shield | +0.032 |
diary | +0.032 |
es | +0.031 |
oc | +0.030 |
shields | +0.029 |
Neg logit contributions | |
aa | -0.026 |
Kids | -0.025 |
oe | -0.025 |
oes | -0.024 |
round | -0.022 |
Token | him |
Token ID | 683 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
aa | +0.038 |
oe | +0.038 |
Kids | +0.038 |
round | +0.035 |
oes | +0.035 |
Neg logit contributions | |
shield | -0.037 |
diary | -0.037 |
es | -0.036 |
oc | -0.033 |
shields | -0.033 |
Token | drink |
Token ID | 4144 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
aa | +0.015 |
oe | +0.014 |
oes | +0.014 |
Kids | +0.014 |
round | +0.013 |
Neg logit contributions | |
diary | -0.020 |
shield | -0.020 |
es | -0.019 |
oc | -0.019 |
shields | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
aa | +0.058 |
Kids | +0.058 |
oe | +0.054 |
oes | +0.053 |
round | +0.051 |
Neg logit contributions | |
shield | -0.059 |
es | -0.057 |
diary | -0.056 |
oc | -0.054 |
shields | -0.052 |
Token | water |
Token ID | 1660 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
aa | +0.016 |
oe | +0.015 |
Kids | +0.015 |
oes | +0.015 |
round | +0.014 |
Neg logit contributions | |
diary | -0.017 |
shield | -0.017 |
es | -0.016 |
oc | -0.016 |
shields | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Kids | +0.067 |
aa | +0.065 |
oe | +0.061 |
oes | +0.059 |
round | +0.057 |
Neg logit contributions | |
shield | -0.056 |
es | -0.054 |
diary | -0.053 |
oc | -0.050 |
shields | -0.048 |
Token | They |
Token ID | 1119 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
aa | +0.031 |
oe | +0.029 |
Kids | +0.029 |
oes | +0.028 |
round | +0.026 |
Neg logit contributions | |
diary | -0.036 |
shield | -0.035 |
es | -0.034 |
oc | -0.034 |
shields | -0.032 |
Token | are |
Token ID | 389 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
diary | +0.011 |
es | +0.010 |
shield | +0.010 |
oc | +0.010 |
journal | +0.009 |
Neg logit contributions | |
aa | -0.009 |
oe | -0.009 |
oes | -0.008 |
Kids | -0.008 |
round | -0.008 |
Token | proud |
Token ID | 6613 |
Feature activation | -8.30e-01 |
Pos logit contributions | |
aa | +0.004 |
oe | +0.004 |
Kids | +0.004 |
oes | +0.004 |
round | +0.004 |
Neg logit contributions | |
diary | -0.005 |
shield | -0.005 |
oc | -0.005 |
es | -0.005 |
journal | -0.005 |
Token | of |
Token ID | 286 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
aa | +0.020 |
oe | +0.019 |
Kids | +0.018 |
oes | +0.018 |
round | +0.017 |
Neg logit contributions | |
shield | -0.030 |
diary | -0.030 |
es | -0.029 |
oc | -0.029 |
shields | -0.027 |
Token | their |
Token ID | 511 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
aa | +0.010 |
Kids | +0.009 |
oe | +0.009 |
oes | +0.008 |
round | +0.007 |
Neg logit contributions | |
diary | -0.019 |
shield | -0.019 |
oc | -0.019 |
es | -0.018 |
journal | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
aa | +0.002 |
oe | +0.002 |
Kids | +0.002 |
oes | +0.002 |
round | +0.002 |
Neg logit contributions | |
diary | -0.002 |
shield | -0.002 |
es | -0.002 |
oc | -0.002 |
shields | -0.002 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
diary | +0.003 |
shield | +0.003 |
es | +0.003 |
oc | +0.003 |
shields | +0.003 |
Neg logit contributions | |
aa | -0.003 |
oe | -0.003 |
Kids | -0.003 |
oes | -0.003 |
round | -0.003 |
Token | ran |
Token ID | 4966 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
aa | +0.043 |
oe | +0.041 |
Kids | +0.041 |
oes | +0.040 |
round | +0.037 |
Neg logit contributions | |
shield | -0.050 |
diary | -0.050 |
es | -0.049 |
oc | -0.048 |
house | -0.045 |
Token | to |
Token ID | 284 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
Kids | +0.041 |
aa | +0.039 |
oes | +0.036 |
iki | +0.033 |
iza | +0.032 |
Neg logit contributions | |
shield | -0.048 |
diary | -0.045 |
es | -0.045 |
webs | -0.044 |
house | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
aa | +0.015 |
Kids | +0.014 |
oe | +0.014 |
oes | +0.014 |
round | +0.013 |
Neg logit contributions | |
shield | -0.011 |
diary | -0.010 |
oc | -0.009 |
es | -0.009 |
shields | -0.009 |
Token | slide |
Token ID | 10649 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
aa | +0.018 |
oe | +0.017 |
Kids | +0.017 |
oes | +0.016 |
round | +0.014 |
Neg logit contributions | |
shield | -0.028 |
diary | -0.028 |
es | -0.027 |
oc | -0.026 |
journal | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
Kids | +0.054 |
aa | +0.051 |
Fre | +0.045 |
Ab | +0.045 |
Abbey | +0.045 |
Neg logit contributions | |
es | -0.037 |
house | -0.037 |
oc | -0.036 |
shield | -0.036 |
diary | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
aa | +0.025 |
Kids | +0.025 |
oe | +0.024 |
oes | +0.023 |
ora | +0.022 |
Neg logit contributions | |
shield | -0.021 |
diary | -0.019 |
es | -0.018 |
oc | -0.018 |
house | -0.017 |
Token | Lily |
Token ID | 20037 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
aa | +0.015 |
Kids | +0.014 |
oes | +0.014 |
oe | +0.014 |
ora | +0.012 |
Neg logit contributions | |
shield | -0.014 |
diary | -0.014 |
es | -0.014 |
oc | -0.013 |
house | -0.012 |
Token | followed |
Token ID | 3940 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
aa | +0.010 |
Kids | +0.009 |
oe | +0.009 |
oes | +0.009 |
round | +0.008 |
Neg logit contributions | |
shield | -0.013 |
diary | -0.013 |
es | -0.013 |
oc | -0.012 |
house | -0.012 |
Token | him |
Token ID | 683 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
aa | +0.015 |
Kids | +0.015 |
oe | +0.014 |
oes | +0.014 |
round | +0.013 |
Neg logit contributions | |
diary | -0.011 |
shield | -0.011 |
es | -0.010 |
oc | -0.010 |
shields | -0.009 |
Token | mother |
Token ID | 2802 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
shield | +0.020 |
diary | +0.020 |
es | +0.020 |
oc | +0.019 |
shields | +0.018 |
Neg logit contributions | |
aa | -0.020 |
oe | -0.019 |
Kids | -0.018 |
oes | -0.018 |
round | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
aa | +0.012 |
oe | +0.011 |
Kids | +0.011 |
oes | +0.011 |
round | +0.010 |
Neg logit contributions | |
diary | -0.008 |
shield | -0.008 |
es | -0.007 |
oc | -0.007 |
shields | -0.007 |
Token | stayed |
Token ID | 9658 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
diary | +0.018 |
shield | +0.018 |
es | +0.018 |
oc | +0.017 |
shields | +0.016 |
Neg logit contributions | |
aa | -0.014 |
oe | -0.013 |
Kids | -0.013 |
oes | -0.013 |
round | -0.012 |
Token | put |
Token ID | 1234 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
aa | +0.018 |
oe | +0.018 |
Kids | +0.017 |
oes | +0.016 |
round | +0.015 |
Neg logit contributions | |
diary | -0.024 |
shield | -0.024 |
es | -0.023 |
oc | -0.023 |
shields | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
aa | +0.030 |
oe | +0.028 |
Kids | +0.028 |
oes | +0.027 |
round | +0.026 |
Neg logit contributions | |
diary | -0.034 |
shield | -0.034 |
es | -0.033 |
oc | -0.032 |
journal | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
aa | +0.033 |
oes | +0.032 |
oe | +0.032 |
Kids | +0.030 |
round | +0.029 |
Neg logit contributions | |
oc | -0.021 |
diary | -0.021 |
es | -0.020 |
shield | -0.019 |
house | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
aa | +0.031 |
oes | +0.030 |
oe | +0.029 |
round | +0.027 |
Kids | +0.027 |
Neg logit contributions | |
oc | -0.024 |
es | -0.024 |
diary | -0.023 |
shield | -0.022 |
house | -0.021 |
Token | The |
Token ID | 464 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
aa | +0.010 |
oes | +0.010 |
oe | +0.010 |
Kids | +0.009 |
round | +0.009 |
Neg logit contributions | |
oc | -0.008 |
es | -0.008 |
diary | -0.008 |
shield | -0.008 |
vel | -0.007 |
Token | mother |
Token ID | 2802 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
aa | +0.022 |
oe | +0.021 |
Kids | +0.021 |
oes | +0.020 |
round | +0.019 |
Neg logit contributions | |
diary | -0.024 |
shield | -0.024 |
es | -0.023 |
oc | -0.023 |
shields | -0.021 |
Token | made |
Token ID | 925 |
Feature activation | -5.09e-03 |
Pos logit contributions | |
aa | +0.052 |
oes | +0.052 |
oe | +0.050 |
Kids | +0.049 |
round | +0.046 |
Neg logit contributions | |
es | -0.062 |
shield | -0.061 |
oc | -0.060 |
diary | -0.059 |
house | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
oes | +0.000 |
aa | +0.000 |
oe | +0.000 |
Kids | +0.000 |
round | +0.000 |
Neg logit contributions | |
diary | -0.000 |
es | -0.000 |
shield | -0.000 |
oc | -0.000 |
webs | -0.000 |
Token | what |
Token ID | 644 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
aa | +0.048 |
oe | +0.047 |
Kids | +0.046 |
oes | +0.044 |
round | +0.043 |
Neg logit contributions | |
diary | -0.035 |
es | -0.035 |
shield | -0.035 |
oc | -0.032 |
journal | -0.030 |
Token | happened |
Token ID | 3022 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
oes | +0.051 |
aa | +0.051 |
round | +0.051 |
oe | +0.050 |
ora | +0.047 |
Neg logit contributions | |
diary | -0.034 |
es | -0.032 |
shield | -0.031 |
journal | -0.028 |
oc | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
diary | +0.002 |
shield | +0.002 |
es | +0.002 |
oc | +0.002 |
journal | +0.002 |
Neg logit contributions | |
aa | -0.003 |
oe | -0.002 |
Kids | -0.002 |
oes | -0.002 |
round | -0.002 |
Token | Their |
Token ID | 5334 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
aa | +0.046 |
oe | +0.045 |
round | +0.044 |
oes | +0.043 |
guard | +0.043 |
Neg logit contributions | |
diary | -0.033 |
es | -0.031 |
house | -0.031 |
oc | -0.030 |
shield | -0.030 |
Token | mom |
Token ID | 1995 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
aa | +0.007 |
oes | +0.007 |
oe | +0.007 |
Kids | +0.007 |
round | +0.007 |
Neg logit contributions | |
diary | -0.005 |
shield | -0.005 |
es | -0.004 |
journal | -0.004 |
oc | -0.004 |
Token | hugged |
Token ID | 41130 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
aa | +0.029 |
oes | +0.028 |
oe | +0.028 |
Kids | +0.027 |
round | +0.026 |
Neg logit contributions | |
es | -0.029 |
diary | -0.029 |
shield | -0.028 |
oc | -0.028 |
house | -0.026 |
Token | them |
Token ID | 606 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
round | +0.099 |
oe | +0.095 |
Ice | +0.092 |
onna | +0.092 |
sur | +0.091 |
Neg logit contributions | |
es | -0.067 |
shield | -0.063 |
diary | -0.059 |
what | -0.058 |
oc | -0.057 |
Token | and |
Token ID | 290 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
diary | +0.047 |
shield | +0.047 |
es | +0.046 |
oc | +0.045 |
shields | +0.043 |
Neg logit contributions | |
aa | -0.026 |
oe | -0.025 |
Kids | -0.024 |
oes | -0.023 |
round | -0.022 |
Token | said |
Token ID | 531 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
diary | +0.007 |
shield | +0.007 |
es | +0.007 |
oc | +0.007 |
shields | +0.007 |
Neg logit contributions | |
aa | -0.005 |
oe | -0.005 |
oes | -0.005 |
Kids | -0.005 |
round | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
aa | +0.003 |
oe | +0.003 |
oes | +0.003 |
Kids | +0.003 |
round | +0.003 |
Neg logit contributions | |
diary | -0.002 |
shield | -0.002 |
es | -0.002 |
oc | -0.002 |
journal | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
oe | +0.053 |
aa | +0.052 |
oes | +0.050 |
Kids | +0.049 |
ora | +0.048 |
Neg logit contributions | |
es | -0.033 |
diary | -0.031 |
shield | -0.031 |
oc | -0.030 |
house | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
aa | +0.035 |
Kids | +0.034 |
oe | +0.033 |
oes | +0.033 |
round | +0.031 |
Neg logit contributions | |
es | -0.028 |
diary | -0.028 |
shield | -0.027 |
oc | -0.025 |
journal | -0.024 |
Token | She |
Token ID | 1375 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
diary | +0.001 |
shield | +0.001 |
es | +0.001 |
oc | +0.001 |
shields | +0.001 |
Neg logit contributions | |
aa | -0.001 |
oe | -0.001 |
Kids | -0.001 |
oes | -0.001 |
round | -0.001 |
Token | said |
Token ID | 531 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
aa | +0.036 |
oes | +0.036 |
oe | +0.035 |
Kids | +0.034 |
round | +0.032 |
Neg logit contributions | |
shield | -0.048 |
diary | -0.046 |
es | -0.046 |
oc | -0.045 |
house | -0.042 |
Token | they |
Token ID | 484 |
Feature activation | +3.95e-02 |
Pos logit contributions | |
shield | +0.006 |
diary | +0.006 |
oc | +0.006 |
es | +0.006 |
shields | +0.005 |
Neg logit contributions | |
aa | -0.006 |
oe | -0.006 |
Kids | -0.006 |
oes | -0.005 |
round | -0.005 |
Token | could |
Token ID | 714 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
shield | +0.001 |
diary | +0.001 |
oc | +0.001 |
es | +0.001 |
shields | +0.001 |
Neg logit contributions | |
aa | -0.001 |
oe | -0.001 |
Kids | -0.001 |
oes | -0.001 |
round | -0.001 |
Token | go |
Token ID | 467 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
aa | +0.019 |
oe | +0.018 |
Kids | +0.018 |
oes | +0.017 |
round | +0.016 |
Neg logit contributions | |
diary | -0.022 |
shield | -0.022 |
es | -0.022 |
oc | -0.021 |
shields | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
Kids | +0.078 |
aa | +0.076 |
oes | +0.071 |
ho | +0.068 |
oe | +0.068 |
Neg logit contributions | |
shield | -0.074 |
diary | -0.071 |
es | -0.069 |
house | -0.068 |
oc | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
diary | +0.013 |
shield | +0.013 |
es | +0.012 |
oc | +0.012 |
shields | +0.011 |
Neg logit contributions | |
aa | -0.011 |
oe | -0.010 |
Kids | -0.010 |
oes | -0.010 |
round | -0.009 |
Token | park |
Token ID | 3952 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
diary | +0.005 |
shield | +0.005 |
es | +0.005 |
oc | +0.005 |
journal | +0.005 |
Neg logit contributions | |
aa | -0.005 |
oe | -0.005 |
Kids | -0.005 |
oes | -0.004 |
round | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
aa | +0.033 |
Kids | +0.031 |
oe | +0.030 |
oes | +0.030 |
round | +0.027 |
Neg logit contributions | |
diary | -0.039 |
shield | -0.039 |
es | -0.038 |
oc | -0.037 |
house | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
aa | +0.015 |
oe | +0.015 |
Kids | +0.014 |
oes | +0.014 |
round | +0.013 |
Neg logit contributions | |
shield | -0.018 |
diary | -0.017 |
es | -0.017 |
oc | -0.016 |
house | -0.016 |
Token | you |
Token ID | 345 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
aa | +0.025 |
Kids | +0.024 |
oe | +0.024 |
oes | +0.023 |
round | +0.022 |
Neg logit contributions | |
diary | -0.024 |
shield | -0.024 |
es | -0.023 |
oc | -0.022 |
house | -0.021 |
Token | want |
Token ID | 765 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
aa | +0.001 |
oe | +0.001 |
Kids | +0.001 |
oes | +0.001 |
round | +0.001 |
Neg logit contributions | |
diary | -0.001 |
shield | -0.001 |
es | -0.001 |
oc | -0.001 |
shields | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
aa | +0.030 |
oe | +0.029 |
Kids | +0.028 |
oes | +0.028 |
round | +0.026 |
Neg logit contributions | |
shield | -0.029 |
diary | -0.029 |
es | -0.028 |
oc | -0.028 |
shields | -0.026 |
Token | Let |
Token ID | 3914 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
diary | +0.005 |
shield | +0.005 |
es | +0.005 |
oc | +0.004 |
journal | +0.004 |
Neg logit contributions | |
aa | -0.007 |
oe | -0.007 |
Kids | -0.007 |
oes | -0.007 |
round | -0.007 |
Token | 's |
Token ID | 338 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
aa | +0.004 |
oe | +0.003 |
Kids | +0.003 |
oes | +0.003 |
round | +0.003 |
Neg logit contributions | |
diary | -0.001 |
shield | -0.001 |
es | -0.001 |
oc | -0.001 |
journal | -0.001 |
Token | go |
Token ID | 467 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
diary | +0.002 |
shield | +0.002 |
es | +0.002 |
oc | +0.002 |
shields | +0.001 |
Neg logit contributions | |
aa | -0.001 |
oe | -0.001 |
Kids | -0.001 |
oes | -0.001 |
round | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
Kids | +0.111 |
aa | +0.101 |
pastor | +0.097 |
sur | +0.097 |
ho | +0.096 |
Neg logit contributions | |
es | -0.085 |
house | -0.083 |
diary | -0.081 |
oc | -0.079 |
shield | -0.076 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
aa | +0.006 |
oe | +0.005 |
Kids | +0.005 |
oes | +0.005 |
round | +0.005 |
Neg logit contributions | |
diary | -0.006 |
shield | -0.006 |
es | -0.005 |
oc | -0.005 |
shields | -0.005 |
Token | couch |
Token ID | 18507 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
es | +0.040 |
shield | +0.038 |
oc | +0.037 |
diary | +0.036 |
shields | +0.035 |
Neg logit contributions | |
aa | -0.028 |
oe | -0.028 |
Kids | -0.027 |
oes | -0.026 |
round | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
aa | +0.029 |
Kids | +0.028 |
oe | +0.027 |
oes | +0.026 |
round | +0.024 |
Neg logit contributions | |
diary | -0.035 |
shield | -0.035 |
es | -0.035 |
oc | -0.034 |
house | -0.032 |
Token | sn |
Token ID | 3013 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
diary | +0.013 |
shield | +0.013 |
es | +0.013 |
oc | +0.013 |
shields | +0.012 |
Neg logit contributions | |
aa | -0.011 |
oe | -0.011 |
Kids | -0.011 |
oes | -0.010 |
round | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
aa | +0.002 |
oe | +0.002 |
oes | +0.002 |
Kids | +0.002 |
round | +0.002 |
Neg logit contributions | |
diary | -0.001 |
shield | -0.001 |
es | -0.001 |
oc | -0.001 |
journal | -0.001 |
Token | � |
Token ID | 6184 |
Feature activation | -5.69e-02 |
Pos logit contributions | |
oes | +0.065 |
aa | +0.064 |
Kids | +0.063 |
oe | +0.063 |
round | +0.059 |
Neg logit contributions | |
es | -0.032 |
shield | -0.032 |
diary | -0.031 |
oc | -0.031 |
vel | -0.029 |
Token | � |
Token ID | 95 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
aa | +0.002 |
oes | +0.002 |
oe | +0.002 |
Kids | +0.002 |
round | +0.002 |
Neg logit contributions | |
diary | -0.001 |
shield | -0.001 |
oc | -0.001 |
es | -0.001 |
house | -0.001 |
Token | € |
Token ID | 26391 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
aa | +0.011 |
oe | +0.011 |
Kids | +0.011 |
oes | +0.011 |
round | +0.010 |
Neg logit contributions | |
diary | -0.010 |
shield | -0.010 |
es | -0.009 |
oc | -0.009 |
house | -0.009 |
Token | � |
Token ID | 129 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
shield | +0.016 |
diary | +0.015 |
shields | +0.014 |
onel | +0.013 |
weapon | +0.013 |
Neg logit contributions | |
aa | -0.017 |
oe | -0.016 |
Kids | -0.015 |
oes | -0.014 |
round | -0.014 |
Token | � |
Token ID | 241 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
aa | +0.030 |
oes | +0.030 |
oe | +0.030 |
Kids | +0.030 |
guard | +0.027 |
Neg logit contributions | |
diary | -0.016 |
oc | -0.015 |
shield | -0.015 |
es | -0.015 |
vel | -0.014 |
Token | There |
Token ID | 1858 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
oes | +0.083 |
aa | +0.079 |
oe | +0.079 |
glers | +0.073 |
round | +0.069 |
Neg logit contributions | |
oc | -0.066 |
es | -0.063 |
diary | -0.060 |
vel | -0.059 |
alas | -0.057 |
Token | now |
Token ID | 783 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
shield | +0.051 |
diary | +0.050 |
oc | +0.049 |
shields | +0.049 |
es | +0.046 |
Neg logit contributions | |
oe | -0.045 |
aa | -0.045 |
Kids | -0.042 |
oes | -0.040 |
weekend | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
diary | +0.006 |
shield | +0.006 |
es | +0.006 |
oc | +0.006 |
shields | +0.006 |
Neg logit contributions | |
aa | -0.007 |
oe | -0.006 |
Kids | -0.006 |
oes | -0.006 |
round | -0.006 |
Token | All |
Token ID | 1439 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
diary | +0.006 |
shield | +0.005 |
es | +0.005 |
oc | +0.005 |
house | +0.005 |
Neg logit contributions | |
aa | -0.009 |
oe | -0.009 |
oes | -0.008 |
Kids | -0.008 |
round | -0.008 |
Token | better |
Token ID | 1365 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
aa | +0.041 |
oe | +0.040 |
Kids | +0.039 |
oes | +0.039 |
round | +0.038 |
Neg logit contributions | |
diary | -0.034 |
shield | -0.033 |
es | -0.033 |
oc | -0.031 |
journal | -0.029 |
Token | said |
Token ID | 531 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
aa | +0.009 |
oe | +0.008 |
Kids | +0.008 |
oes | +0.008 |
round | +0.007 |
Neg logit contributions | |
diary | -0.021 |
shield | -0.021 |
es | -0.020 |
oc | -0.020 |
shields | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
shield | +0.011 |
diary | +0.011 |
es | +0.011 |
oc | +0.010 |
journal | +0.009 |
Neg logit contributions | |
aa | -0.013 |
Kids | -0.012 |
oe | -0.012 |
oes | -0.012 |
round | -0.011 |
Token | " |
Token ID | 366 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
aa | +0.052 |
oe | +0.050 |
Kids | +0.048 |
oes | +0.048 |
round | +0.046 |
Neg logit contributions | |
es | -0.043 |
shield | -0.042 |
oc | -0.042 |
diary | -0.042 |
house | -0.038 |
Token | Let |
Token ID | 5756 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
aa | +0.025 |
oe | +0.024 |
oes | +0.023 |
Kids | +0.022 |
round | +0.021 |
Neg logit contributions | |
oc | -0.024 |
es | -0.024 |
diary | -0.024 |
shield | -0.024 |
house | -0.022 |
Token | 's |
Token ID | 338 |
Feature activation | -9.28e-02 |
Pos logit contributions | |
diary | +0.003 |
shield | +0.003 |
es | +0.003 |
oc | +0.003 |
journal | +0.003 |
Neg logit contributions | |
aa | -0.010 |
oe | -0.010 |
Kids | -0.010 |
oes | -0.010 |
round | -0.010 |
Token | go |
Token ID | 467 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
aa | +0.002 |
oe | +0.002 |
oes | +0.002 |
Kids | +0.002 |
round | +0.002 |
Neg logit contributions | |
diary | -0.003 |
es | -0.003 |
shield | -0.003 |
oc | -0.003 |
shields | -0.003 |
Token | closer |
Token ID | 5699 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
Kids | +0.110 |
aa | +0.103 |
pastor | +0.096 |
oes | +0.096 |
Ice | +0.095 |
Neg logit contributions | |
oc | -0.091 |
es | -0.088 |
house | -0.086 |
shield | -0.081 |
diary | -0.075 |
Token | and |
Token ID | 290 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
Kids | +0.065 |
aa | +0.063 |
oe | +0.059 |
oes | +0.055 |
sur | +0.052 |
Neg logit contributions | |
es | -0.081 |
shield | -0.076 |
oc | -0.074 |
diary | -0.073 |
house | -0.069 |
Token | touch |
Token ID | 3638 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
diary | +0.006 |
shield | +0.006 |
es | +0.006 |
oc | +0.006 |
shields | +0.005 |
Neg logit contributions | |
aa | -0.004 |
oe | -0.004 |
Kids | -0.004 |
oes | -0.004 |
round | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
aa | +0.053 |
oe | +0.051 |
Kids | +0.050 |
oes | +0.049 |
round | +0.046 |
Neg logit contributions | |
diary | -0.059 |
shield | -0.058 |
es | -0.056 |
oc | -0.055 |
shields | -0.052 |
Token | ." |
Token ID | 526 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
aa | +0.010 |
oe | +0.010 |
Kids | +0.009 |
oes | +0.009 |
round | +0.009 |
Neg logit contributions | |
diary | -0.010 |
shield | -0.010 |
es | -0.010 |
oc | -0.010 |
journal | -0.009 |