TOP ACTIVATIONS
MAX = 0.214

was , so he hopped closer to investigate . As the
As the young rabbit hopped closer , a loud bang filled
she wanted to take a closer look , so she wiped
he wanted to take a closer look . When
. So , he stepped closer and noticed the body was
s take a closer look . This one looks
chicken , so he went closer to the bull .
hopped over to take a closer look , and saw it
slide over to take a closer look .
. She wanted to get closer to it , so she
was too scared to come closer . The
, so he slowly moved closer . The pigeon started to
He was about to go closer to take a better look
bent down to take a closer look and discovered it was
strange sack . He got closer and realized that it was
he tried to take a closer look . He asked his
but the shadow kept coming closer . She looked around and
stepped forward to take a closer look . It was a
and the sw an came closer . Then , the boy
that he was one step closer to achieving his dream .

MIN ACTIVATIONS
MIN = -0.269

box of cereal . The cash ier said , " Of
ier . The cash ier said , " You
only give out on special occasions . â The kids
to help and fixed the cash register . The shop keeper
gave the money to the cash ier . The
they got up to the cash ier they looked very surprised
asked . The cash ier said , " It
s on display near the cash register . They looked so
ier . The cash ier said , " What
and took it to the cash ier . The
. Smith happily thanked the cash ier and walked back to
the dressing room and the cash ier , but she was
over her allowance to the cash ier . As
When they got to the cash ier , the lady weighed
, they went to the cash ier to pay . The
. He smiled at the cash ier , who said he
. She ran to the cash ier to buy the toy
it is only for special occasions . â She wink
The little boy thanked the cash ier and went home happy
ier to pay . The cash ier was very nice and

INTERVAL 0.093 - 0.214
CONTAINS 3.433%

Once upon a time , there were two friends , Anna
see a big fly buzzing around a flower . Sam wants
because his play house was broken . His mom told him
The little girl and the grey goose watched the paper shapes
street . As she was walking , she saw a big

INTERVAL -0.027 - 0.093
CONTAINS 75.355%

They are made of snow , and snow melts when it
away . Emma thought it was fun and could not wait
The lady smiles and says hello back . She asks Sara
years old . One day , he wanted to play outside
seen again ! <|endoftext|> Sam was a three year old boy

INTERVAL -0.148 - -0.027
CONTAINS 20.797%

they walked , Tommy noticed something strange in the road .
they knew they could trust each other no matter what .
they were always together , even when they were apart .
. He was excited to get home and start crafting .
tidy everything looked , she thanked the bunny and they played

INTERVAL -0.269 - -0.148
CONTAINS 0.415%

p ears . L ily got very scared and
toys . They are living things . You should be gentle
party , Lily saw a lot of y ummy food .
it 's important to take responsibility and help others when they
They promised to have more parties in the future . Then
Token was
Token ID373
Feature activation+2.13e-02

Pos logit contributions
Bang+0.128
 snowball+0.120
 shoot+0.113
 BO+0.111
 dam+0.110
Neg logit contributions
iest-0.120
 queens-0.115
 dancers-0.115
 Erin-0.115
ala-0.115
Token,
Token ID11
Feature activation-2.44e-02

Pos logit contributions
Bang+0.038
 hit+0.035
 poked+0.034
 snowball+0.034
 shoot+0.034
Neg logit contributions
 register-0.030
 singers-0.028
 queens-0.028
ities-0.028
reating-0.028
Token so
Token ID523
Feature activation-6.34e-03

Pos logit contributions
nam+0.035
 queens+0.034
 penn+0.032
 dancers+0.032
reating+0.032
Neg logit contributions
Bang-0.040
 hit-0.040
 poked-0.038
 searched-0.038
 accidentally-0.037
Token he
Token ID339
Feature activation+4.70e-02

Pos logit contributions
nam+0.008
 queens+0.008
 penn+0.007
 importantly+0.007
yle+0.006
Neg logit contributions
Bang-0.012
 hit-0.012
 quarrel-0.011
 fight-0.011
 shoot-0.011
Token hopped
Token ID45230
Feature activation+3.83e-02

Pos logit contributions
house+0.055
 fight+0.053
 snowball+0.052
 BO+0.051
 quarrel+0.051
Neg logit contributions
 queens-0.087
iza-0.081
la-0.079
 singers-0.077
nam-0.077
Token closer
Token ID5699
Feature activation+2.14e-01

Pos logit contributions
 accidentally+0.045
 poked+0.043
house+0.043
 quarrel+0.043
 hit+0.043
Neg logit contributions
 register-0.068
 queens-0.068
overs-0.068
reating-0.067
 Clare-0.066
Token to
Token ID284
Feature activation+4.95e-02

Pos logit contributions
Bang+0.291
 hit+0.290
 shoot+0.278
 accidentally+0.274
 poked+0.266
Neg logit contributions
 queens-0.375
 penn-0.374
 register-0.362
 Clare-0.361
iley-0.360
Token investigate
Token ID9161
Feature activation+3.71e-02

Pos logit contributions
house+0.066
 accidentally+0.064
Bang+0.064
 hit+0.062
 searched+0.062
Neg logit contributions
 queens-0.084
nam-0.082
 Clare-0.079
 dancers-0.079
 Erin-0.078
Token.
Token ID13
Feature activation-1.13e-03

Pos logit contributions
 hit+0.051
 shoot+0.048
 poked+0.048
 searched+0.047
Bang+0.047
Neg logit contributions
 queens-0.068
nam-0.067
 register-0.067
 penn-0.066
overs-0.065
Token As
Token ID1081
Feature activation-5.26e-02

Pos logit contributions
 Erin+0.002
 Clare+0.002
 Debbie+0.002
 N+0.002
nam+0.002
Neg logit contributions
 quarrel-0.002
 hit-0.002
 fight-0.002
 argument-0.002
Bang-0.002
Token the
Token ID262
Feature activation-5.35e-03

Pos logit contributions
 queens+0.080
 penn+0.078
nam+0.078
 register+0.077
overs+0.076
Neg logit contributions
 hit-0.088
Bang-0.084
 shoot-0.084
 poked-0.083
 searched-0.082
Token As
Token ID1081
Feature activation-5.26e-02

Pos logit contributions
 Erin+0.002
 Clare+0.002
 Debbie+0.002
 N+0.002
nam+0.002
Neg logit contributions
 quarrel-0.002
 hit-0.002
 fight-0.002
 argument-0.002
Bang-0.002
Token the
Token ID262
Feature activation-5.35e-03

Pos logit contributions
 queens+0.080
 penn+0.078
nam+0.078
 register+0.077
overs+0.076
Neg logit contributions
 hit-0.088
Bang-0.084
 shoot-0.084
 poked-0.083
 searched-0.082
Token young
Token ID1862
Feature activation+7.57e-02

Pos logit contributions
 queens+0.008
 importantly+0.007
 register+0.007
 dancers+0.007
 singers+0.007
Neg logit contributions
 accidentally-0.009
 poked-0.009
 searched-0.009
Bang-0.009
 hit-0.008
Token rabbit
Token ID22746
Feature activation+5.36e-02

Pos logit contributions
 hit+0.093
Bang+0.089
 shoot+0.087
 poked+0.086
 searched+0.086
Neg logit contributions
 queens-0.147
 penn-0.143
nam-0.143
 register-0.141
overs-0.140
Token hopped
Token ID45230
Feature activation+3.76e-02

Pos logit contributions
Bang+0.063
 snowball+0.059
 shoot+0.054
 fight+0.052
 BO+0.051
Neg logit contributions
 queens-0.093
 penn-0.090
iley-0.088
yle-0.086
 register-0.085
Token closer
Token ID5699
Feature activation+2.14e-01

Pos logit contributions
 accidentally+0.050
 quarrel+0.049
 hit+0.048
 poked+0.048
Bang+0.047
Neg logit contributions
 register-0.062
overs-0.060
 queens-0.060
 Clare-0.060
 Erin-0.059
Token,
Token ID11
Feature activation-2.53e-02

Pos logit contributions
Bang+0.275
 hit+0.269
 shoot+0.256
 accidentally+0.251
 poked+0.244
Neg logit contributions
 penn-0.395
 queens-0.391
 Clare-0.380
iley-0.378
 Erin-0.377
Token a
Token ID257
Feature activation+2.02e-02

Pos logit contributions
 queens+0.033
nam+0.033
 penn+0.032
 Erin+0.031
 register+0.031
Neg logit contributions
 hit-0.045
Bang-0.044
 shoot-0.043
 searched-0.043
 poked-0.043
Token loud
Token ID7812
Feature activation+1.23e-01

Pos logit contributions
 hit+0.027
 searched+0.027
Bang+0.027
 poked+0.026
 shoot+0.025
Neg logit contributions
 queens-0.035
nam-0.034
 penn-0.033
 register-0.033
iley-0.033
Token bang
Token ID20188
Feature activation+3.17e-02

Pos logit contributions
Bang+0.157
 searched+0.153
 accidentally+0.152
 poked+0.145
 hit+0.144
Neg logit contributions
 singers-0.193
 dancers-0.193
iley-0.192
 Clare-0.189
 Erin-0.189
Token filled
Token ID5901
Feature activation+3.33e-02

Pos logit contributions
Bang+0.030
 hit+0.029
 shoot+0.029
 searched+0.029
 accidentally+0.027
Neg logit contributions
 queens-0.066
 penn-0.066
 register-0.065
yle-0.064
 singers-0.064
Token she
Token ID673
Feature activation+1.16e-02

Pos logit contributions
 hit+0.010
Bang+0.009
 shoot+0.009
 searched+0.009
 poked+0.009
Neg logit contributions
 queens-0.023
nam-0.023
 penn-0.022
 register-0.022
yle-0.022
Token wanted
Token ID2227
Feature activation+6.04e-02

Pos logit contributions
Bang+0.013
 shoot+0.013
 hit+0.012
 snowball+0.012
 BO+0.012
Neg logit contributions
nam-0.023
 queens-0.023
illi-0.022
 penn-0.022
yle-0.022
Token to
Token ID284
Feature activation+4.82e-02

Pos logit contributions
 hit+0.054
 poked+0.049
 shoot+0.047
 accidentally+0.046
 searched+0.045
Neg logit contributions
 register-0.141
ities-0.140
nam-0.140
yle-0.140
iley-0.140
Token take
Token ID1011
Feature activation-4.98e-02

Pos logit contributions
Bang+0.062
 snowball+0.059
 searched+0.058
 accidentally+0.056
 BO+0.054
Neg logit contributions
 queens-0.084
nam-0.083
 dancers-0.083
 Clare-0.083
yle-0.080
Token a
Token ID257
Feature activation+2.13e-02

Pos logit contributions
 register+0.103
ities+0.103
nam+0.103
 queens+0.101
 importantly+0.101
Neg logit contributions
 hit-0.062
 shoot-0.056
 poked-0.055
Bang-0.054
 searched-0.052
Token closer
Token ID5699
Feature activation+2.13e-01

Pos logit contributions
Bang+0.026
 searched+0.025
 hit+0.024
 poked+0.023
 accidentally+0.022
Neg logit contributions
 penn-0.041
 queens-0.040
nam-0.040
yle-0.039
illi-0.039
Token look
Token ID804
Feature activation+3.44e-02

Pos logit contributions
Bang+0.266
 hit+0.259
 accidentally+0.251
 searched+0.243
 poked+0.241
Neg logit contributions
 penn-0.399
 queens-0.395
nam-0.387
 Clare-0.386
yle-0.384
Token,
Token ID11
Feature activation-2.20e-02

Pos logit contributions
 hit+0.031
 poked+0.028
 searched+0.027
 accidentally+0.025
 saw+0.025
Neg logit contributions
 queens-0.078
ities-0.077
iley-0.077
nam-0.077
 Erin-0.076
Token so
Token ID523
Feature activation-5.78e-03

Pos logit contributions
nam+0.034
 queens+0.034
 penn+0.033
 register+0.033
overs+0.032
Neg logit contributions
 hit-0.035
Bang-0.034
 shoot-0.033
 poked-0.033
 searched-0.033
Token she
Token ID673
Feature activation+1.23e-02

Pos logit contributions
 register+0.010
ities+0.010
overs+0.009
 queens+0.009
reating+0.009
Neg logit contributions
 hit-0.010
 accidentally-0.009
 poked-0.009
 shoot-0.009
 Suddenly-0.009
Token wiped
Token ID21122
Feature activation+3.94e-02

Pos logit contributions
Bang+0.012
 shoot+0.012
 hit+0.012
 fight+0.011
 quarrel+0.011
Neg logit contributions
 queens-0.026
 penn-0.025
nam-0.025
iza-0.025
yle-0.025
Token he
Token ID339
Feature activation+4.77e-02

Pos logit contributions
Bang+0.077
 hit+0.075
 shoot+0.071
 searched+0.070
 poked+0.070
Neg logit contributions
 queens-0.106
nam-0.105
 penn-0.104
 register-0.101
 Clare-0.100
Token wanted
Token ID2227
Feature activation+6.05e-02

Pos logit contributions
Bang+0.070
 BO+0.067
 shoot+0.062
 fight+0.062
 SPL+0.062
Neg logit contributions
la-0.073
 queens-0.070
 Erin-0.069
 dancers-0.068
 Clare-0.068
Token to
Token ID284
Feature activation+4.83e-02

Pos logit contributions
 hit+0.067
Bang+0.063
 shoot+0.062
 poked+0.061
 searched+0.060
Neg logit contributions
 queens-0.126
 penn-0.124
nam-0.124
 register-0.123
overs-0.122
Token take
Token ID1011
Feature activation-4.88e-02

Pos logit contributions
Bang+0.059
 accidentally+0.054
 searched+0.053
 hit+0.051
 snowball+0.050
Neg logit contributions
 dancers-0.089
 Clare-0.089
 queens-0.088
 penn-0.088
 passports-0.088
Token a
Token ID257
Feature activation+2.17e-02

Pos logit contributions
 register+0.098
 queens+0.098
nam+0.097
ities+0.096
overs+0.096
Neg logit contributions
 hit-0.063
 shoot-0.058
 poked-0.057
Bang-0.055
 searched-0.055
Token closer
Token ID5699
Feature activation+2.13e-01

Pos logit contributions
Bang+0.028
 searched+0.025
 hit+0.024
 accidentally+0.024
 poked+0.024
Neg logit contributions
 penn-0.041
 passports-0.040
yle-0.039
nam-0.039
illi-0.039
Token look
Token ID804
Feature activation+3.43e-02

Pos logit contributions
Bang+0.270
 hit+0.263
 accidentally+0.258
 searched+0.246
 poked+0.245
Neg logit contributions
 penn-0.391
 queens-0.386
 Clare-0.378
yle-0.378
nam-0.376
Token.
Token ID13
Feature activation+9.68e-04

Pos logit contributions
 hit+0.041
 poked+0.037
 searched+0.037
 shoot+0.037
 accidentally+0.036
Neg logit contributions
 queens-0.069
nam-0.069
 Erin-0.066
ities-0.066
 register-0.066
Token
Token ID198
Feature activation+2.52e-02

Pos logit contributions
 hit+0.001
 quarrel+0.001
 fight+0.001
Bang+0.001
 accidentally+0.001
Neg logit contributions
 Erin-0.002
 Clare-0.002
 Debbie-0.002
 Clara-0.002
nam-0.001
Token
Token ID198
Feature activation+2.40e-02

Pos logit contributions
 hit+0.035
 shoot+0.034
 poked+0.033
 quarrel+0.033
Bang+0.033
Neg logit contributions
illi-0.044
 Debbie-0.041
yle-0.041
iley-0.041
 Clare-0.041
TokenWhen
Token ID2215
Feature activation-9.81e-02

Pos logit contributions
 hit+0.033
 accidentally+0.032
 searched+0.032
 poked+0.032
 shoot+0.031
Neg logit contributions
 queens-0.041
illi-0.039
nam-0.038
iley-0.038
reating-0.038
Token.
Token ID13
Feature activation+1.53e-03

Pos logit contributions
 hit+0.099
Bang+0.096
 shoot+0.095
 poked+0.094
 searched+0.092
Neg logit contributions
 queens-0.101
overs-0.099
 penn-0.099
 register-0.099
nam-0.099
Token So
Token ID1406
Feature activation-4.91e-02

Pos logit contributions
 hit+0.002
 shoot+0.002
Bang+0.002
 quarrel+0.002
 fight+0.002
Neg logit contributions
ums-0.002
 Erin-0.002
 penn-0.002
ities-0.002
 register-0.002
Token,
Token ID11
Feature activation-2.19e-02

Pos logit contributions
 queens+0.103
nam+0.101
 register+0.100
 penn+0.100
overs+0.100
Neg logit contributions
 hit-0.057
 shoot-0.053
Bang-0.052
 searched-0.052
 poked-0.052
Token he
Token ID339
Feature activation+4.76e-02

Pos logit contributions
 queens+0.038
 register+0.037
 penn+0.037
illi+0.036
overs+0.036
Neg logit contributions
 hit-0.035
 shoot-0.032
 poked-0.031
 accidentally-0.031
Bang-0.031
Token stepped
Token ID10764
Feature activation+3.85e-02

Pos logit contributions
 BO+0.057
Bang+0.056
 SPL+0.054
 shoot+0.052
house+0.052
Neg logit contributions
 queens-0.081
la-0.081
 penn-0.080
iza-0.080
 passports-0.077
Token closer
Token ID5699
Feature activation+2.13e-01

Pos logit contributions
Bang+0.061
 shoot+0.061
 quarrel+0.060
 fight+0.059
 hit+0.059
Neg logit contributions
 register-0.060
 penn-0.057
overs-0.056
 queens-0.055
oll-0.054
Token and
Token ID290
Feature activation+7.89e-03

Pos logit contributions
Bang+0.259
 hit+0.257
 shoot+0.247
 accidentally+0.236
 poked+0.236
Neg logit contributions
 penn-0.408
 queens-0.405
 register-0.397
nam-0.394
iley-0.391
Token noticed
Token ID6810
Feature activation+7.11e-02

Pos logit contributions
 quarrel+0.007
house+0.007
Bang+0.007
 fight+0.007
 snowball+0.007
Neg logit contributions
iza-0.017
nam-0.017
 Erin-0.016
 Clare-0.016
 register-0.016
Token the
Token ID262
Feature activation-2.43e-03

Pos logit contributions
 hit+0.112
Bang+0.107
 shoot+0.107
 poked+0.105
 searched+0.104
Neg logit contributions
 queens-0.114
 penn-0.112
nam-0.112
 register-0.111
overs-0.109
Token body
Token ID1767
Feature activation-4.70e-02

Pos logit contributions
 queens+0.004
 penn+0.004
nam+0.004
 register+0.004
ities+0.004
Neg logit contributions
 hit-0.004
 searched-0.003
Bang-0.003
 shoot-0.003
 poked-0.003
Token was
Token ID373
Feature activation+2.35e-02

Pos logit contributions
 queens+0.087
nam+0.085
 penn+0.085
 register+0.085
overs+0.084
Neg logit contributions
 hit-0.063
 shoot-0.059
Bang-0.058
 poked-0.058
 searched-0.057
Token
Token ID26391
Feature activation+1.26e-01

Pos logit contributions
 hit+0.046
Bang+0.043
 shoot+0.043
 poked+0.042
 searched+0.042
Neg logit contributions
 queens-0.062
nam-0.061
 penn-0.061
 register-0.060
overs-0.059
Token
Token ID8151
Feature activation+2.22e-03

Pos logit contributions
 hit+0.159
 shoot+0.149
 accidentally+0.148
 poked+0.142
Bang+0.142
Neg logit contributions
 penn-0.245
 queens-0.244
nam-0.244
 register-0.241
reating-0.240
Tokens
Token ID82
Feature activation+7.06e-04

Pos logit contributions
 hit+0.003
 shoot+0.002
 accidentally+0.002
 poked+0.002
Bang+0.002
Neg logit contributions
 queens-0.004
nam-0.004
ities-0.004
 penn-0.004
 singers-0.004
Token take
Token ID1011
Feature activation-5.17e-02

Pos logit contributions
 hit+0.001
Bang+0.001
 shoot+0.001
 poked+0.001
 searched+0.001
Neg logit contributions
 queens-0.002
 penn-0.002
nam-0.002
 register-0.002
overs-0.001
Token a
Token ID257
Feature activation+1.99e-02

Pos logit contributions
ities+0.114
nam+0.113
 queens+0.111
lessness+0.111
 importantly+0.111
Neg logit contributions
 hit-0.064
 shoot-0.057
 poked-0.055
Bang-0.053
 play-0.052
Token closer
Token ID5699
Feature activation+2.13e-01

Pos logit contributions
Bang+0.026
 hit+0.026
 poked+0.025
 searched+0.025
house+0.024
Neg logit contributions
 penn-0.035
nam-0.035
yle-0.034
 queens-0.034
illi-0.034
Token look
Token ID804
Feature activation+3.49e-02

Pos logit contributions
 hit+0.247
Bang+0.239
 accidentally+0.230
 poked+0.229
 shoot+0.227
Neg logit contributions
 penn-0.416
 queens-0.416
nam-0.405
yle-0.404
 register-0.404
Token.
Token ID13
Feature activation-1.71e-03

Pos logit contributions
 hit+0.044
 poked+0.041
 shoot+0.041
 searched+0.040
Bang+0.039
Neg logit contributions
nam-0.067
 queens-0.067
 register-0.065
 penn-0.065
yle-0.064
Token This
Token ID770
Feature activation-2.48e-02

Pos logit contributions
 queens+0.003
 penn+0.003
nam+0.003
 register+0.003
ities+0.003
Neg logit contributions
 hit-0.002
 shoot-0.002
Bang-0.002
 Suddenly-0.002
 accidentally-0.002
Token one
Token ID530
Feature activation-4.03e-02

Pos logit contributions
 queens+0.049
 penn+0.049
nam+0.048
 register+0.048
overs+0.047
Neg logit contributions
 hit-0.029
Bang-0.028
 shoot-0.027
 poked-0.027
 searched-0.027
Token looks
Token ID3073
Feature activation+5.41e-02

Pos logit contributions
 queens+0.085
nam+0.084
 penn+0.084
 register+0.083
overs+0.082
Neg logit contributions
 hit-0.043
 shoot-0.040
Bang-0.040
 poked-0.039
 searched-0.039
Token chicken
Token ID9015
Feature activation-1.52e-02

Pos logit contributions
 searched+0.037
Bang+0.034
 hit+0.033
 poked+0.033
 shoot+0.032
Neg logit contributions
 queens-0.028
 penn-0.027
 singers-0.026
 register-0.026
 dancers-0.026
Token,
Token ID11
Feature activation-2.25e-02

Pos logit contributions
nam+0.029
 queens+0.028
 penn+0.028
 Erin+0.028
 Clare+0.027
Neg logit contributions
 hit-0.021
 shoot-0.020
 poked-0.019
 accidentally-0.018
 searched-0.018
Token so
Token ID523
Feature activation-5.46e-03

Pos logit contributions
 queens+0.039
 register+0.038
 penn+0.038
nam+0.038
overs+0.038
Neg logit contributions
 hit-0.033
 shoot-0.031
 poked-0.031
Bang-0.031
 searched-0.030
Token he
Token ID339
Feature activation+4.81e-02

Pos logit contributions
 queens+0.009
 register+0.009
 penn+0.009
overs+0.009
iley+0.009
Neg logit contributions
 hit-0.009
 shoot-0.008
 poked-0.008
Bang-0.008
 accidentally-0.008
Token went
Token ID1816
Feature activation+2.31e-02

Pos logit contributions
Bang+0.050
 shoot+0.049
 BO+0.049
 fight+0.047
house+0.047
Neg logit contributions
 queens-0.093
 penn-0.093
iza-0.090
nam-0.089
 Clare-0.088
Token closer
Token ID5699
Feature activation+2.13e-01

Pos logit contributions
Bang+0.027
 hit+0.026
 shoot+0.026
 poked+0.026
 accidentally+0.025
Neg logit contributions
 queens-0.044
 register-0.044
nam-0.043
overs-0.043
 penn-0.043
Token to
Token ID284
Feature activation+4.76e-02

Pos logit contributions
Bang+0.292
 hit+0.288
 shoot+0.278
 accidentally+0.269
 searched+0.266
Neg logit contributions
 penn-0.376
 queens-0.375
nam-0.362
 register-0.362
 Clare-0.360
Token the
Token ID262
Feature activation-5.25e-03

Pos logit contributions
house+0.074
Bang+0.074
 searched+0.072
 accidentally+0.069
 hit+0.068
Neg logit contributions
nam-0.070
 Clare-0.066
 queens-0.066
overs-0.065
yle-0.064
Token bull
Token ID6473
Feature activation+7.44e-02

Pos logit contributions
 register+0.007
 ponies+0.007
 dancers+0.007
 queens+0.006
 Debbie+0.006
Neg logit contributions
 searched-0.009
 accidentally-0.009
house-0.009
 shoot-0.009
 poked-0.009
Token.
Token ID13
Feature activation-3.07e-03

Pos logit contributions
Bang+0.157
 hit+0.136
 accidentally+0.136
 poked+0.129
AAAA+0.129
Neg logit contributions
 register-0.083
overs-0.077
yle-0.075
 penn-0.075
nam-0.074
Token
Token ID198
Feature activation+2.42e-02

Pos logit contributions
 N+0.003
 Erin+0.003
 Clara+0.003
 Mara+0.003
 Debbie+0.003
Neg logit contributions
 argument-0.005
 quarrel-0.005
Bang-0.005
 fight-0.005
 poked-0.005
Token hopped
Token ID45230
Feature activation+3.78e-02

Pos logit contributions
 fight+0.053
 BO+0.049
 shoot+0.049
Bang+0.047
 quarrel+0.047
Neg logit contributions
 queens-0.067
iley-0.065
nam-0.063
 penn-0.061
la-0.060
Token over
Token ID625
Feature activation+9.46e-02

Pos logit contributions
 accidentally+0.042
 hit+0.042
 poked+0.041
 shoot+0.041
house+0.041
Neg logit contributions
 queens-0.070
 register-0.068
nam-0.067
overs-0.067
 Clare-0.066
Token to
Token ID284
Feature activation+4.80e-02

Pos logit contributions
 hit+0.116
Bang+0.111
 shoot+0.110
 accidentally+0.107
 poked+0.106
Neg logit contributions
 queens-0.182
 penn-0.179
nam-0.176
overs-0.174
iley-0.173
Token take
Token ID1011
Feature activation-4.90e-02

Pos logit contributions
Bang+0.067
 hit+0.066
 accidentally+0.066
house+0.065
 poked+0.063
Neg logit contributions
nam-0.077
 Clare-0.076
 Erin-0.076
yle-0.075
 penn-0.074
Token a
Token ID257
Feature activation+2.09e-02

Pos logit contributions
 queens+0.089
 penn+0.088
nam+0.088
 register+0.087
overs+0.086
Neg logit contributions
 hit-0.066
Bang-0.063
 shoot-0.062
 poked-0.062
 searched-0.061
Token closer
Token ID5699
Feature activation+2.13e-01

Pos logit contributions
Bang+0.025
house+0.023
 searched+0.023
gy+0.022
 hit+0.022
Neg logit contributions
 penn-0.039
nam-0.038
yle-0.037
 queens-0.036
illi-0.036
Token look
Token ID804
Feature activation+3.43e-02

Pos logit contributions
Bang+0.313
 accidentally+0.305
 hit+0.290
 searched+0.277
 poked+0.272
Neg logit contributions
 penn-0.336
 queens-0.329
 Clare-0.328
reating-0.320
ala-0.319
Token,
Token ID11
Feature activation-2.21e-02

Pos logit contributions
 hit+0.046
 shoot+0.043
 poked+0.043
 searched+0.042
Bang+0.042
Neg logit contributions
 queens-0.063
nam-0.063
 penn-0.062
 register-0.062
overs-0.061
Token and
Token ID290
Feature activation+9.95e-03

Pos logit contributions
nam+0.032
 queens+0.031
 Clare+0.030
 penn+0.030
 dancers+0.030
Neg logit contributions
Bang-0.035
house-0.034
 quarrel-0.032
 fight-0.032
 hit-0.032
Token saw
Token ID2497
Feature activation+5.57e-02

Pos logit contributions
Bang+0.009
 quarrel+0.009
 fight+0.009
 shoot+0.009
 snowball+0.009
Neg logit contributions
nam-0.021
 queens-0.021
iza-0.020
 Clare-0.020
 Erin-0.020
Token it
Token ID340
Feature activation+8.61e-02

Pos logit contributions
 hit+0.078
 shoot+0.073
 poked+0.073
Bang+0.071
 searched+0.071
Neg logit contributions
 queens-0.101
 register-0.101
overs-0.100
nam-0.099
 penn-0.098
Token slide
Token ID10649
Feature activation+2.49e-02

Pos logit contributions
Bang+0.056
 hit+0.054
 accidentally+0.053
 poked+0.051
 snowball+0.050
Neg logit contributions
 queens-0.092
 Erin-0.090
 Clare-0.090
 penn-0.090
nam-0.089
Token over
Token ID625
Feature activation+9.53e-02

Pos logit contributions
 hit+0.027
 shoot+0.024
Bang+0.024
 poked+0.024
 searched+0.024
Neg logit contributions
 queens-0.054
nam-0.053
 penn-0.053
 register-0.052
ities-0.052
Token to
Token ID284
Feature activation+4.92e-02

Pos logit contributions
 hit+0.104
 poked+0.095
 searched+0.094
 shoot+0.090
 accidentally+0.088
Neg logit contributions
ities-0.208
nam-0.206
 register-0.205
 queens-0.202
ums-0.201
Token take
Token ID1011
Feature activation-4.80e-02

Pos logit contributions
Bang+0.060
 hit+0.060
 accidentally+0.057
 poked+0.056
 shoot+0.055
Neg logit contributions
 Clare-0.091
overs-0.090
 queens-0.090
nam-0.089
 Erin-0.089
Token a
Token ID257
Feature activation+2.08e-02

Pos logit contributions
 register+0.107
nam+0.107
reating+0.107
ities+0.107
 importantly+0.105
Neg logit contributions
 hit-0.052
 shoot-0.048
 poked-0.048
 searched-0.047
Bang-0.046
Token closer
Token ID5699
Feature activation+2.13e-01

Pos logit contributions
 searched+0.025
Bang+0.024
house+0.024
 Suddenly+0.022
gy+0.022
Neg logit contributions
 penn-0.038
 queens-0.037
nam-0.037
illi-0.037
yle-0.037
Token look
Token ID804
Feature activation+3.61e-02

Pos logit contributions
Bang+0.289
 accidentally+0.287
 hit+0.276
 searched+0.265
 poked+0.260
Neg logit contributions
 penn-0.363
 queens-0.356
 Clare-0.348
reating-0.347
yle-0.343
Token.
Token ID13
Feature activation+3.93e-03

Pos logit contributions
 hit+0.048
 poked+0.044
 shoot+0.044
 searched+0.044
 accidentally+0.043
Neg logit contributions
 queens-0.067
nam-0.067
 register-0.065
 penn-0.065
yle-0.065
Token
Token ID220
Feature activation-3.15e-03

Pos logit contributions
 hit+0.004
Bang+0.004
 shoot+0.004
 poked+0.004
 searched+0.004
Neg logit contributions
 queens-0.008
 penn-0.008
nam-0.008
 register-0.008
overs-0.008
Token
Token ID198
Feature activation+2.52e-02

Pos logit contributions
 queens+0.006
illi+0.006
overs+0.006
 penn+0.006
nam+0.006
Neg logit contributions
 hit-0.003
 shoot-0.003
Bang-0.003
 poked-0.003
 searched-0.003
Token
Token ID198
Feature activation+2.38e-02

Pos logit contributions
 hit+0.030
 shoot+0.028
Bang+0.028
 poked+0.028
 accidentally+0.027
Neg logit contributions
illi-0.049
 queens-0.048
 Clare-0.048
 Erin-0.047
iley-0.047
Token.
Token ID13
Feature activation+3.81e-03

Pos logit contributions
Bang+0.076
 hit+0.075
 shoot+0.073
 poked+0.071
 accidentally+0.070
Neg logit contributions
 penn-0.079
 queens-0.079
nam-0.079
 register-0.078
overs-0.078
Token She
Token ID1375
Feature activation-2.57e-03

Pos logit contributions
 hit+0.007
Bang+0.006
 shoot+0.006
 fight+0.006
 snowball+0.006
Neg logit contributions
 Mara-0.006
 Clare-0.006
overs-0.005
 Clara-0.005
 N-0.005
Token wanted
Token ID2227
Feature activation+6.03e-02

Pos logit contributions
nam+0.005
yle+0.005
iley+0.005
 Clare+0.005
la+0.004
Neg logit contributions
 fight-0.003
Bang-0.003
 shoot-0.003
 dam-0.003
house-0.003
Token to
Token ID284
Feature activation+4.83e-02

Pos logit contributions
 hit+0.077
Bang+0.077
 searched+0.073
 shoot+0.073
 accidentally+0.072
Neg logit contributions
 queens-0.113
 penn-0.110
nam-0.109
reating-0.105
 register-0.105
Token get
Token ID651
Feature activation-5.05e-02

Pos logit contributions
Bang+0.065
 accidentally+0.064
 searched+0.063
 snowball+0.061
house+0.059
Neg logit contributions
nam-0.075
 queens-0.074
 Clare-0.074
yle-0.074
 dancers-0.073
Token closer
Token ID5699
Feature activation+2.13e-01

Pos logit contributions
 queens+0.120
nam+0.119
 penn+0.119
 register+0.118
overs+0.117
Neg logit contributions
 hit-0.040
Bang-0.037
 shoot-0.036
 poked-0.035
 searched-0.035
Token to
Token ID284
Feature activation+4.85e-02

Pos logit contributions
 hit+0.194
 poked+0.176
 searched+0.175
 shoot+0.167
 accidentally+0.163
Neg logit contributions
 queens-0.486
 register-0.484
nam-0.482
overs-0.481
ities-0.471
Token it
Token ID340
Feature activation+8.58e-02

Pos logit contributions
Bang+0.092
house+0.092
 snowball+0.089
 accidentally+0.089
 searched+0.088
Neg logit contributions
 Clare-0.050
nam-0.050
 queens-0.049
 dancers-0.046
reating-0.045
Token,
Token ID11
Feature activation-2.19e-02

Pos logit contributions
Bang+0.167
 accidentally+0.147
 hit+0.146
 poked+0.141
 shoot+0.141
Neg logit contributions
 penn-0.104
 Erin-0.099
nam-0.099
 Clare-0.099
 queens-0.099
Token so
Token ID523
Feature activation-5.21e-03

Pos logit contributions
nam+0.033
 queens+0.032
 penn+0.031
 Clare+0.031
 register+0.031
Neg logit contributions
Bang-0.036
 hit-0.036
 shoot-0.034
 poked-0.034
 searched-0.034
Token she
Token ID673
Feature activation+1.16e-02

Pos logit contributions
 queens+0.006
 register+0.006
reating+0.006
 penn+0.006
nam+0.006
Neg logit contributions
 hit-0.011
 accidentally-0.011
 poked-0.010
 shoot-0.010
 searched-0.010
Token was
Token ID373
Feature activation+2.37e-02

Pos logit contributions
 penn+0.049
yle+0.048
 register+0.048
iza+0.047
illi+0.047
Neg logit contributions
Bang-0.030
 shoot-0.027
 hit-0.025
 BO-0.025
 SPL-0.025
Token too
Token ID1165
Feature activation+6.92e-03

Pos logit contributions
 hit+0.031
 shoot+0.029
 poked+0.029
Bang+0.028
 searched+0.028
Neg logit contributions
 queens-0.045
 penn-0.045
nam-0.044
 register-0.044
overs-0.044
Token scared
Token ID12008
Feature activation+1.23e-01

Pos logit contributions
 hit+0.008
Bang+0.008
 searched+0.008
 shoot+0.008
 poked+0.008
Neg logit contributions
 queens-0.013
 penn-0.013
nam-0.013
 register-0.013
overs-0.013
Token to
Token ID284
Feature activation+4.94e-02

Pos logit contributions
 hit+0.129
 searched+0.116
 poked+0.113
 shoot+0.112
 accidentally+0.111
Neg logit contributions
nam-0.282
 queens-0.278
illi-0.272
 penn-0.271
yle-0.265
Token come
Token ID1282
Feature activation-5.29e-03

Pos logit contributions
Bang+0.063
 searched+0.058
 accidentally+0.057
 hit+0.056
 poked+0.055
Neg logit contributions
 Clare-0.088
 Erin-0.088
 register-0.088
iza-0.087
 penn-0.087
Token closer
Token ID5699
Feature activation+2.13e-01

Pos logit contributions
 queens+0.009
overs+0.009
 register+0.009
 Erin+0.009
 penn+0.009
Neg logit contributions
Bang-0.007
 hit-0.007
 poked-0.007
 accidentally-0.007
 searched-0.007
Token.
Token ID13
Feature activation-4.40e-03

Pos logit contributions
 hit+0.249
 shoot+0.230
 searched+0.229
 poked+0.226
 accidentally+0.220
Neg logit contributions
 queens-0.431
nam-0.430
 penn-0.422
 register-0.422
yle-0.418
Token
Token ID220
Feature activation-3.76e-03

Pos logit contributions
 queens+0.009
nam+0.009
 penn+0.009
 register+0.009
overs+0.009
Neg logit contributions
 hit-0.005
Bang-0.004
 shoot-0.004
 poked-0.004
 searched-0.004
Token
Token ID198
Feature activation+2.17e-02

Pos logit contributions
illi+0.007
 register+0.007
ums+0.007
 Erin+0.007
overs+0.007
Neg logit contributions
 hit-0.004
 shoot-0.004
Bang-0.004
 searched-0.004
 poked-0.004
Token
Token ID198
Feature activation+2.10e-02

Pos logit contributions
 hit+0.028
 shoot+0.026
 poked+0.026
 searched+0.026
 quarrel+0.025
Neg logit contributions
illi-0.041
 queens-0.039
 Erin-0.039
 Clare-0.039
iza-0.038
TokenThe
Token ID464
Feature activation-8.56e-03

Pos logit contributions
 hit+0.031
 poked+0.030
 searched+0.030
 shoot+0.030
Bang+0.029
Neg logit contributions
 queens-0.035
nam-0.034
illi-0.034
 register-0.033
iley-0.033
Token,
Token ID11
Feature activation-2.22e-02

Pos logit contributions
Bang+0.043
 hit+0.043
 shoot+0.040
 poked+0.040
 accidentally+0.039
Neg logit contributions
 queens-0.050
nam-0.050
 penn-0.050
 register-0.049
overs-0.048
Token so
Token ID523
Feature activation-4.72e-03

Pos logit contributions
nam+0.033
 queens+0.033
 penn+0.032
 register+0.031
reating+0.030
Neg logit contributions
Bang-0.037
 hit-0.036
 shoot-0.035
 poked-0.034
 searched-0.034
Token he
Token ID339
Feature activation+4.79e-02

Pos logit contributions
 queens+0.007
 penn+0.007
nam+0.007
 register+0.007
overs+0.007
Neg logit contributions
 hit-0.008
 shoot-0.007
Bang-0.007
 poked-0.007
 searched-0.007
Token slowly
Token ID6364
Feature activation+1.01e-01

Pos logit contributions
Bang+0.051
 BO+0.050
 fight+0.049
 quarrel+0.048
 shoot+0.048
Neg logit contributions
 queens-0.095
 penn-0.093
iza-0.091
nam-0.089
yle-0.088
Token moved
Token ID3888
Feature activation+5.48e-02

Pos logit contributions
Bang+0.128
 snowball+0.113
house+0.110
 quarrel+0.105
 fight+0.100
Neg logit contributions
 penn-0.189
iza-0.180
 register-0.180
 cents-0.171
 queens-0.170
Token closer
Token ID5699
Feature activation+2.13e-01

Pos logit contributions
 hit+0.054
 accidentally+0.052
 shoot+0.051
Bang+0.051
 searched+0.050
Neg logit contributions
 queens-0.115
nam-0.114
 penn-0.113
overs-0.112
yle-0.111
Token.
Token ID13
Feature activation-2.36e-03

Pos logit contributions
 hit+0.273
Bang+0.266
 shoot+0.257
 poked+0.251
 accidentally+0.250
Neg logit contributions
 queens-0.397
 penn-0.395
nam-0.388
 register-0.386
overs-0.383
Token The
Token ID383
Feature activation+9.83e-04

Pos logit contributions
 Erin+0.004
 Clare+0.004
 N+0.004
overs+0.004
nam+0.004
Neg logit contributions
 hit-0.003
Bang-0.003
 quarrel-0.003
 snowball-0.003
 poked-0.003
Token pigeon
Token ID46387
Feature activation+7.44e-02

Pos logit contributions
 searched+0.002
Bang+0.002
 poked+0.002
 accidentally+0.002
 shoot+0.002
Neg logit contributions
 penn-0.001
 queens-0.001
nam-0.001
 register-0.001
essa-0.001
Token started
Token ID2067
Feature activation+2.65e-02

Pos logit contributions
Bang+0.103
 snowball+0.094
ulum+0.093
 BO+0.092
 Today+0.090
Neg logit contributions
 queens-0.110
 penn-0.110
la-0.100
 among-0.100
yle-0.096
Token to
Token ID284
Feature activation+4.75e-02

Pos logit contributions
Bang+0.040
house+0.036
 searched+0.036
 hit+0.036
 shoot+0.035
Neg logit contributions
 penn-0.044
 queens-0.041
nam-0.040
 dancers-0.039
 Erin-0.038
Token He
Token ID679
Feature activation+3.72e-02

Pos logit contributions
 hit+0.002
 poked+0.002
Bang+0.002
 shoot+0.002
 searched+0.002
Neg logit contributions
 Erin-0.003
nam-0.003
 Clare-0.003
overs-0.003
 register-0.003
Token was
Token ID373
Feature activation+2.17e-02

Pos logit contributions
Bang+0.041
house+0.039
 BO+0.038
 fight+0.038
 shoot+0.038
Neg logit contributions
iley-0.067
 penn-0.067
la-0.066
yle-0.066
 queens-0.065
Token about
Token ID546
Feature activation-1.79e-02

Pos logit contributions
 hit+0.032
 shoot+0.030
Bang+0.030
 poked+0.030
 searched+0.029
Neg logit contributions
 queens-0.037
 penn-0.037
nam-0.037
 register-0.036
overs-0.036
Token to
Token ID284
Feature activation+4.81e-02

Pos logit contributions
 register+0.039
 queens+0.039
overs+0.039
 penn+0.039
nam+0.039
Neg logit contributions
 hit-0.018
 shoot-0.016
 poked-0.016
Bang-0.016
 accidentally-0.016
Token go
Token ID467
Feature activation+2.56e-02

Pos logit contributions
 hit+0.051
Bang+0.047
 shoot+0.047
 poked+0.046
 searched+0.046
Neg logit contributions
 queens-0.102
nam-0.100
 penn-0.100
 register-0.100
overs-0.099
Token closer
Token ID5699
Feature activation+2.13e-01

Pos logit contributions
 hit+0.035
 shoot+0.032
Bang+0.032
 poked+0.031
 searched+0.031
Neg logit contributions
 queens-0.048
nam-0.047
 penn-0.047
 register-0.046
ities-0.046
Token to
Token ID284
Feature activation+4.85e-02

Pos logit contributions
 hit+0.205
 shoot+0.185
 searched+0.183
 poked+0.183
Bang+0.177
Neg logit contributions
nam-0.475
 queens-0.475
 register-0.469
 penn-0.467
yle-0.462
Token take
Token ID1011
Feature activation-4.99e-02

Pos logit contributions
 hit+0.066
 shoot+0.063
Bang+0.061
 poked+0.060
 searched+0.060
Neg logit contributions
 queens-0.090
 penn-0.089
nam-0.089
 register-0.088
overs-0.087
Token a
Token ID257
Feature activation+2.27e-02

Pos logit contributions
nam+0.108
 queens+0.107
 register+0.106
ities+0.106
lessness+0.104
Neg logit contributions
 hit-0.058
 shoot-0.056
Bang-0.052
 poked-0.051
 searched-0.049
Token better
Token ID1365
Feature activation+4.06e-03

Pos logit contributions
Bang+0.026
 searched+0.026
 accidentally+0.024
house+0.024
 poked+0.024
Neg logit contributions
 queens-0.042
 penn-0.041
nam-0.041
yle-0.040
 passports-0.040
Token look
Token ID804
Feature activation+3.58e-02

Pos logit contributions
 hit+0.004
 shoot+0.004
Bang+0.004
 poked+0.004
 searched+0.004
Neg logit contributions
 queens-0.009
nam-0.009
 register-0.009
 penn-0.008
yle-0.008
Token bent
Token ID17157
Feature activation+1.53e-01

Pos logit contributions
 fight+0.045
 shoot+0.043
Bang+0.043
 dam+0.043
house+0.043
Neg logit contributions
iley-0.071
yle-0.069
nam-0.068
 queens-0.068
iza-0.068
Token down
Token ID866
Feature activation+1.03e-01

Pos logit contributions
 shoot+0.196
Bang+0.195
 quarrel+0.189
 hit+0.187
 fight+0.187
Neg logit contributions
nam-0.265
 queens-0.257
 penn-0.257
yle-0.256
 Erin-0.254
Token to
Token ID284
Feature activation+4.87e-02

Pos logit contributions
 shoot+0.124
 hit+0.124
Bang+0.123
 accidentally+0.118
 searched+0.118
Neg logit contributions
 queens-0.190
 penn-0.189
 register-0.185
overs-0.185
iley-0.181
Token take
Token ID1011
Feature activation-5.05e-02

Pos logit contributions
house+0.061
Bang+0.056
 accidentally+0.055
 dam+0.054
 searched+0.053
Neg logit contributions
nam-0.088
yle-0.088
iza-0.087
 Erin-0.087
 Clare-0.085
Token a
Token ID257
Feature activation+2.20e-02

Pos logit contributions
 queens+0.091
 penn+0.090
nam+0.089
 register+0.089
overs+0.088
Neg logit contributions
 hit-0.068
Bang-0.065
 shoot-0.064
 poked-0.064
 searched-0.063
Token closer
Token ID5699
Feature activation+2.13e-01

Pos logit contributions
Bang+0.026
house+0.025
 searched+0.025
 Suddenly+0.024
gy+0.023
Neg logit contributions
 penn-0.040
nam-0.039
yle-0.039
illi-0.038
 register-0.038
Token look
Token ID804
Feature activation+3.47e-02

Pos logit contributions
Bang+0.314
 accidentally+0.305
 hit+0.289
 searched+0.281
house+0.277
Neg logit contributions
 penn-0.332
 Clare-0.325
 Erin-0.321
 Debbie-0.318
reating-0.318
Token and
Token ID290
Feature activation+1.11e-02

Pos logit contributions
 hit+0.047
 shoot+0.044
 poked+0.044
Bang+0.044
 searched+0.043
Neg logit contributions
 queens-0.064
nam-0.063
 penn-0.062
 register-0.062
overs-0.061
Token discovered
Token ID5071
Feature activation+1.36e-03

Pos logit contributions
Bang+0.008
house+0.008
 snowball+0.008
 hit+0.008
 shoot+0.007
Neg logit contributions
nam-0.027
 queens-0.026
 Erin-0.025
 Clare-0.025
iza-0.025
Token it
Token ID340
Feature activation+8.57e-02

Pos logit contributions
 hit+0.002
 shoot+0.002
 poked+0.002
 searched+0.002
 accidentally+0.001
Neg logit contributions
 queens-0.003
overs-0.003
iley-0.003
ities-0.003
 register-0.003
Token was
Token ID373
Feature activation+2.28e-02

Pos logit contributions
Bang+0.088
 hit+0.080
 shoot+0.080
 poked+0.074
 searched+0.072
Neg logit contributions
 register-0.175
 queens-0.172
yle-0.172
 penn-0.172
illi-0.170
Token strange
Token ID6283
Feature activation+9.66e-02

Pos logit contributions
Bang+0.033
 hit+0.032
 searched+0.032
 poked+0.032
 shoot+0.030
Neg logit contributions
 queens-0.043
 penn-0.041
nam-0.041
 register-0.041
iley-0.040
Token sack
Token ID23704
Feature activation-2.80e-02

Pos logit contributions
Bang+0.138
 hit+0.137
 searched+0.130
 poked+0.130
 shoot+0.129
Neg logit contributions
 penn-0.163
 queens-0.158
iley-0.157
 register-0.156
nam-0.156
Token.
Token ID13
Feature activation+8.06e-03

Pos logit contributions
 register+0.045
 queens+0.043
overs+0.043
 penn+0.043
nam+0.042
Neg logit contributions
Bang-0.043
 hit-0.041
 shoot-0.040
 poked-0.040
 accidentally-0.039
Token He
Token ID679
Feature activation+4.11e-02

Pos logit contributions
 hit+0.010
 shoot+0.010
Bang+0.010
 poked+0.010
 accidentally+0.009
Neg logit contributions
nam-0.015
overs-0.014
 Clare-0.014
 Erin-0.014
 register-0.014
Token got
Token ID1392
Feature activation-3.33e-02

Pos logit contributions
Bang+0.037
 shoot+0.035
 BO+0.034
 snowball+0.033
 hit+0.032
Neg logit contributions
yle-0.086
nam-0.086
iley-0.085
iza-0.085
 penn-0.084
Token closer
Token ID5699
Feature activation+2.13e-01

Pos logit contributions
 queens+0.069
iley+0.067
 register+0.067
overs+0.067
 penn+0.067
Neg logit contributions
 hit-0.039
 poked-0.035
 shoot-0.035
Bang-0.035
 searched-0.035
Token and
Token ID290
Feature activation+9.69e-03

Pos logit contributions
 hit+0.226
Bang+0.217
 shoot+0.212
 poked+0.205
 searched+0.201
Neg logit contributions
 queens-0.443
 penn-0.441
nam-0.437
 register-0.435
overs-0.429
Token realized
Token ID6939
Feature activation-2.65e-02

Pos logit contributions
Bang+0.007
 shoot+0.007
 snowball+0.006
 hit+0.006
 quarrel+0.006
Neg logit contributions
nam-0.023
 queens-0.022
 register-0.022
iza-0.022
 Erin-0.022
Token that
Token ID326
Feature activation+7.67e-03

Pos logit contributions
overs+0.056
 queens+0.055
ums+0.055
 register+0.055
ities+0.055
Neg logit contributions
 hit-0.031
 accidentally-0.029
 shoot-0.028
 searched-0.028
 poked-0.027
Token it
Token ID340
Feature activation+8.62e-02

Pos logit contributions
 hit+0.010
 shoot+0.009
 accidentally+0.009
 searched+0.009
 poked+0.008
Neg logit contributions
illi-0.016
 register-0.016
ums-0.016
iley-0.016
ala-0.015
Token was
Token ID373
Feature activation+2.30e-02

Pos logit contributions
Bang+0.080
 hit+0.079
 shoot+0.075
 poked+0.072
 searched+0.068
Neg logit contributions
 queens-0.184
 penn-0.182
 register-0.182
yle-0.181
nam-0.180
Token he
Token ID339
Feature activation+4.81e-02

Pos logit contributions
 register+0.009
 queens+0.008
 penn+0.008
overs+0.008
ities+0.008
Neg logit contributions
 hit-0.008
 shoot-0.007
 poked-0.007
Bang-0.007
 accidentally-0.007
Token tried
Token ID3088
Feature activation+6.10e-02

Pos logit contributions
 snowball+0.062
house+0.061
 BO+0.061
 fight+0.060
Bang+0.058
Neg logit contributions
nam-0.083
 queens-0.082
 dancers-0.074
 singers-0.074
 penn-0.074
Token to
Token ID284
Feature activation+4.92e-02

Pos logit contributions
Bang+0.087
 hit+0.083
 searched+0.081
 shoot+0.081
house+0.081
Neg logit contributions
 queens-0.103
nam-0.101
 penn-0.100
reating-0.098
 dancers-0.094
Token take
Token ID1011
Feature activation-4.89e-02

Pos logit contributions
 accidentally+0.065
house+0.063
Bang+0.062
 searched+0.062
 BO+0.062
Neg logit contributions
nam-0.082
 queens-0.082
 dancers-0.077
reating-0.074
 Clare-0.073
Token a
Token ID257
Feature activation+2.18e-02

Pos logit contributions
 queens+0.088
nam+0.087
 register+0.087
 penn+0.086
overs+0.085
Neg logit contributions
 hit-0.069
 shoot-0.065
Bang-0.065
 poked-0.064
 searched-0.063
Token closer
Token ID5699
Feature activation+2.13e-01

Pos logit contributions
Bang+0.026
 searched+0.024
house+0.023
 Suddenly+0.023
 accidentally+0.023
Neg logit contributions
 penn-0.041
nam-0.040
 queens-0.040
 passports-0.039
yle-0.039
Token look
Token ID804
Feature activation+3.53e-02

Pos logit contributions
Bang+0.276
 hit+0.267
 accidentally+0.266
 searched+0.250
 poked+0.247
Neg logit contributions
 penn-0.382
 queens-0.377
reating-0.366
nam-0.365
yle-0.364
Token.
Token ID13
Feature activation+1.55e-03

Pos logit contributions
 hit+0.042
 poked+0.039
 shoot+0.038
 searched+0.038
 accidentally+0.037
Neg logit contributions
 queens-0.072
nam-0.071
iley-0.069
 register-0.069
yle-0.069
Token He
Token ID679
Feature activation+3.73e-02

Pos logit contributions
Bang+0.002
 shoot+0.002
 searched+0.002
 poked+0.002
 accidentally+0.002
Neg logit contributions
 Clara-0.002
 Debbie-0.002
 Clare-0.002
 Mara-0.002
 Lib-0.002
Token asked
Token ID1965
Feature activation+3.29e-02

Pos logit contributions
 BO+0.041
Bang+0.041
 fight+0.039
 shoot+0.039
 SPL+0.038
Neg logit contributions
nam-0.067
 queens-0.066
la-0.066
 penn-0.065
yle-0.064
Token his
Token ID465
Feature activation-3.20e-02

Pos logit contributions
 hit+0.048
 shoot+0.045
Bang+0.044
 poked+0.044
 searched+0.044
Neg logit contributions
 queens-0.059
 penn-0.058
nam-0.057
 register-0.057
yle-0.057
Token but
Token ID475
Feature activation-3.48e-02

Pos logit contributions
 hit+0.020
 shoot+0.017
 poked+0.016
 accidentally+0.015
 closer+0.015
Neg logit contributions
asers-0.064
 queens-0.064
ities-0.064
 register-0.063
overs-0.063
Token the
Token ID262
Feature activation-4.30e-03

Pos logit contributions
 queens+0.064
reating+0.060
asers+0.059
 singers+0.059
ities+0.058
Neg logit contributions
 hit-0.056
 accidentally-0.054
 searched-0.054
 poked-0.052
 saw-0.050
Token shadow
Token ID9082
Feature activation+6.72e-02

Pos logit contributions
 queens+0.008
nam+0.008
 register+0.008
 penn+0.008
 dancers+0.008
Neg logit contributions
 hit-0.005
 shoot-0.005
Bang-0.005
 searched-0.005
 poked-0.005
Token kept
Token ID4030
Feature activation-2.62e-02

Pos logit contributions
Bang+0.066
 hit+0.062
 shoot+0.061
 searched+0.056
 poked+0.056
Neg logit contributions
 penn-0.141
 queens-0.140
nam-0.139
 register-0.138
yle-0.138
Token coming
Token ID2406
Feature activation-2.56e-05

Pos logit contributions
 queens+0.045
 register+0.043
 penn+0.043
nam+0.043
overs+0.043
Neg logit contributions
 hit-0.041
 shoot-0.038
 poked-0.038
 searched-0.038
Bang-0.037
Token closer
Token ID5699
Feature activation+2.13e-01

Pos logit contributions
 queens+0.000
nam+0.000
 register+0.000
 penn+0.000
overs+0.000
Neg logit contributions
 hit-0.000
Bang-0.000
 shoot-0.000
 poked-0.000
 accidentally-0.000
Token.
Token ID13
Feature activation+8.93e-04

Pos logit contributions
 hit+0.224
 searched+0.209
 shoot+0.200
 poked+0.199
 accidentally+0.188
Neg logit contributions
 queens-0.461
nam-0.455
illi-0.453
yle-0.451
iza-0.450
Token She
Token ID1375
Feature activation-7.10e-03

Pos logit contributions
 hit+0.001
 searched+0.001
 accidentally+0.001
 Suddenly+0.001
 poked+0.001
Neg logit contributions
 queens-0.002
reating-0.002
nam-0.002
 singers-0.002
ities-0.002
Token looked
Token ID3114
Feature activation+9.46e-02

Pos logit contributions
iley+0.014
 penn+0.014
iza+0.014
yle+0.014
 queens+0.014
Neg logit contributions
Bang-0.007
 shoot-0.007
 hit-0.006
 fight-0.006
 quarrel-0.006
Token around
Token ID1088
Feature activation+1.25e-01

Pos logit contributions
Bang+0.144
 shoot+0.134
 hit+0.132
 fight+0.126
 quarrel+0.125
Neg logit contributions
 penn-0.151
nam-0.151
 Clare-0.145
 register-0.145
 queens-0.143
Token and
Token ID290
Feature activation+8.35e-03

Pos logit contributions
 hit+0.141
Bang+0.133
 shoot+0.131
 poked+0.128
 searched+0.126
Neg logit contributions
 queens-0.254
 penn-0.251
nam-0.251
 register-0.249
overs-0.247
Token stepped
Token ID10764
Feature activation+3.73e-02

Pos logit contributions
 fight+0.044
 shoot+0.040
Bang+0.040
house+0.039
 quarrel+0.039
Neg logit contributions
nam-0.080
yle-0.079
 queens-0.077
iley-0.076
iza-0.076
Token forward
Token ID2651
Feature activation-4.40e-03

Pos logit contributions
 hit+0.037
 shoot+0.036
Bang+0.036
 accidentally+0.035
 fight+0.034
Neg logit contributions
 register-0.079
 queens-0.077
nam-0.077
yle-0.076
illi-0.076
Token to
Token ID284
Feature activation+4.79e-02

Pos logit contributions
 queens+0.010
nam+0.009
 penn+0.009
 register+0.009
overs+0.009
Neg logit contributions
 hit-0.004
 shoot-0.004
Bang-0.004
 poked-0.004
 searched-0.004
Token take
Token ID1011
Feature activation-5.05e-02

Pos logit contributions
Bang+0.069
house+0.067
 hit+0.065
 accidentally+0.064
 snowball+0.063
Neg logit contributions
yle-0.078
nam-0.077
 queens-0.076
 Clare-0.075
 penn-0.075
Token a
Token ID257
Feature activation+2.16e-02

Pos logit contributions
 queens+0.098
nam+0.096
 register+0.096
 penn+0.095
overs+0.094
Neg logit contributions
 hit-0.065
 shoot-0.062
Bang-0.061
 poked-0.060
 searched-0.060
Token closer
Token ID5699
Feature activation+2.12e-01

Pos logit contributions
Bang+0.021
 searched+0.021
house+0.020
 hit+0.020
 poked+0.019
Neg logit contributions
 penn-0.045
yle-0.044
nam-0.044
 queens-0.044
illi-0.043
Token look
Token ID804
Feature activation+3.37e-02

Pos logit contributions
Bang+0.279
 accidentally+0.269
 hit+0.268
 searched+0.254
 poked+0.252
Neg logit contributions
 penn-0.373
 queens-0.370
 Clare-0.364
reating-0.363
yle-0.363
Token.
Token ID13
Feature activation+7.71e-04

Pos logit contributions
 hit+0.044
 poked+0.040
 shoot+0.040
 searched+0.039
 accidentally+0.039
Neg logit contributions
 queens-0.065
nam-0.064
 register-0.062
 penn-0.062
overs-0.062
Token It
Token ID632
Feature activation+9.79e-02

Pos logit contributions
Bang+0.001
 hit+0.001
 shoot+0.001
 fight+0.001
 accidentally+0.001
Neg logit contributions
 Erin-0.001
nam-0.001
 penn-0.001
 Clare-0.001
overs-0.001
Token was
Token ID373
Feature activation+2.08e-02

Pos logit contributions
 fight+0.127
Bang+0.127
 quarrel+0.122
 shoot+0.120
 snowball+0.112
Neg logit contributions
yle-0.152
illi-0.151
 Erin-0.149
 queens-0.148
la-0.145
Token a
Token ID257
Feature activation+2.11e-02

Pos logit contributions
 hit+0.024
 shoot+0.022
 poked+0.022
 searched+0.021
Bang+0.021
Neg logit contributions
 queens-0.044
 register-0.044
overs-0.043
 penn-0.043
yle-0.043
Token and
Token ID290
Feature activation+7.14e-03

Pos logit contributions
nam+0.141
 penn+0.140
 register+0.137
 queens+0.133
overs+0.133
Neg logit contributions
Bang-0.132
 hit-0.127
 shoot-0.125
 accidentally-0.122
 poked-0.121
Token the
Token ID262
Feature activation-5.70e-03

Pos logit contributions
 hit+0.008
Bang+0.008
 shoot+0.008
 poked+0.008
 searched+0.008
Neg logit contributions
 queens-0.014
nam-0.014
 penn-0.014
 register-0.013
 Clare-0.013
Token sw
Token ID1509
Feature activation+7.77e-02

Pos logit contributions
 penn+0.011
 queens+0.010
nam+0.010
 dancers+0.010
 passports+0.010
Neg logit contributions
 searched-0.007
 accidentally-0.007
house-0.007
 hit-0.007
Bang-0.007
Tokenan
Token ID272
Feature activation+5.67e-02

Pos logit contributions
Bang+0.109
 accidentally+0.109
 hit+0.109
 shoot+0.106
 searched+0.101
Neg logit contributions
ums-0.135
 penn-0.131
overs-0.128
yle-0.127
ities-0.123
Token came
Token ID1625
Feature activation+3.93e-02

Pos logit contributions
Bang+0.065
 hit+0.057
 shoot+0.056
 accidentally+0.055
 bury+0.055
Neg logit contributions
 penn-0.109
 singers-0.105
 dancers-0.105
 queens-0.105
nam-0.105
Token closer
Token ID5699
Feature activation+2.12e-01

Pos logit contributions
house+0.052
Bang+0.052
 hit+0.052
 accidentally+0.052
 fight+0.050
Neg logit contributions
 queens-0.064
 dancers-0.063
ala-0.062
overs-0.059
ums-0.059
Token.
Token ID13
Feature activation-9.55e-04

Pos logit contributions
 hit+0.307
Bang+0.299
 shoot+0.290
 poked+0.286
 searched+0.283
Neg logit contributions
 queens-0.363
 penn-0.358
nam-0.354
 register-0.352
overs-0.348
Token Then
Token ID3244
Feature activation-2.04e-02

Pos logit contributions
 Erin+0.001
 N+0.001
 Clare+0.001
 Clara+0.001
 Debbie+0.001
Neg logit contributions
 quarrel-0.001
 hit-0.001
 fight-0.001
 argument-0.001
 poked-0.001
Token,
Token ID11
Feature activation-2.40e-02

Pos logit contributions
 queens+0.041
 penn+0.041
nam+0.040
 register+0.040
overs+0.040
Neg logit contributions
 hit-0.023
Bang-0.022
 shoot-0.022
 poked-0.021
 searched-0.021
Token the
Token ID262
Feature activation-5.91e-03

Pos logit contributions
nam+0.035
 queens+0.035
 penn+0.034
 register+0.033
overs+0.033
Neg logit contributions
 hit-0.041
Bang-0.040
 shoot-0.039
 searched-0.039
 poked-0.039
Token boy
Token ID2933
Feature activation+2.04e-02

Pos logit contributions
 penn+0.009
iza+0.008
 dancers+0.008
 queens+0.008
 singers+0.008
Neg logit contributions
 searched-0.009
 accidentally-0.009
house-0.009
Bang-0.009
 shoot-0.009
Token that
Token ID326
Feature activation+5.99e-03

Pos logit contributions
illi+0.194
 register+0.190
ums+0.185
overs+0.185
ities+0.185
Neg logit contributions
 hit-0.101
 accidentally-0.096
 shoot-0.093
 poked-0.088
 searched-0.087
Token he
Token ID339
Feature activation+4.70e-02

Pos logit contributions
 hit+0.008
 shoot+0.008
 accidentally+0.008
 poked+0.007
 searched+0.007
Neg logit contributions
illi-0.012
iza-0.011
iley-0.011
overs-0.011
 register-0.011
Token was
Token ID373
Feature activation+2.27e-02

Pos logit contributions
 hit+0.048
 searched+0.043
 poked+0.043
 accidentally+0.042
 shoot+0.042
Neg logit contributions
nam-0.104
 penn-0.104
 queens-0.104
overs-0.102
 register-0.102
Token one
Token ID530
Feature activation-4.18e-02

Pos logit contributions
 hit+0.032
 poked+0.029
 accidentally+0.029
 shoot+0.029
 searched+0.029
Neg logit contributions
 penn-0.041
 queens-0.041
yle-0.041
ities-0.041
reating-0.040
Token step
Token ID2239
Feature activation-3.17e-02

Pos logit contributions
nam+0.076
 Erin+0.074
ities+0.074
 Clare+0.072
 queens+0.072
Neg logit contributions
 hit-0.061
 poked-0.057
 shoot-0.056
 accidentally-0.055
 searched-0.053
Token closer
Token ID5699
Feature activation+2.12e-01

Pos logit contributions
 queens+0.056
nam+0.055
 penn+0.055
illi+0.054
ities+0.054
Neg logit contributions
 hit-0.046
 shoot-0.043
 searched-0.043
 poked-0.042
 accidentally-0.041
Token to
Token ID284
Feature activation+4.77e-02

Pos logit contributions
 hit+0.211
 searched+0.192
 shoot+0.192
 poked+0.189
Bang+0.185
Neg logit contributions
 queens-0.467
nam-0.466
 penn-0.460
 register-0.459
yle-0.455
Token achieving
Token ID16937
Feature activation-4.09e-02

Pos logit contributions
 hit+0.067
 shoot+0.066
 fight+0.060
 accidentally+0.059
 poked+0.059
Neg logit contributions
 penn-0.089
 register-0.088
illi-0.088
 queens-0.087
oll-0.087
Token his
Token ID465
Feature activation-3.37e-02

Pos logit contributions
 queens+0.087
ala+0.082
 register+0.082
illi+0.081
iza+0.080
Neg logit contributions
 shoot-0.048
 hit-0.048
 searched-0.044
 accidentally-0.043
Bang-0.042
Token dream
Token ID4320
Feature activation-1.54e-02

Pos logit contributions
 penn+0.061
nam+0.060
 register+0.059
 queens+0.059
iley+0.058
Neg logit contributions
 hit-0.045
 poked-0.044
Bang-0.044
 accidentally-0.043
 shoot-0.043
Token.
Token ID13
Feature activation-4.31e-03

Pos logit contributions
nam+0.026
 queens+0.026
 penn+0.026
 register+0.025
iley+0.025
Neg logit contributions
 hit-0.023
 shoot-0.022
 searched-0.021
 poked-0.021
Bang-0.021
Token box
Token ID3091
Feature activation-6.23e-02

Pos logit contributions
 hit+0.018
Bang+0.017
 searched+0.017
 poked+0.017
 shoot+0.016
Neg logit contributions
 queens-0.021
 penn-0.021
 register-0.020
nam-0.020
overs-0.020
Token of
Token ID286
Feature activation-9.17e-02

Pos logit contributions
nam+0.124
 penn+0.120
 queens+0.120
yle+0.119
iley+0.118
Neg logit contributions
 hit-0.080
 searched-0.072
 shoot-0.072
 accidentally-0.070
 poked-0.070
Token cereal
Token ID33158
Feature activation-4.32e-02

Pos logit contributions
 queens+0.147
 register+0.146
yle+0.146
nam+0.145
illi+0.143
Neg logit contributions
 hit-0.146
 shoot-0.137
 poked-0.135
Bang-0.134
 searched-0.133
Token.
Token ID13
Feature activation+3.46e-03

Pos logit contributions
nam+0.086
 queens+0.085
iley+0.084
yle+0.084
 penn+0.082
Neg logit contributions
 hit-0.054
 searched-0.048
 accidentally-0.048
 shoot-0.047
 poked-0.047
Token The
Token ID383
Feature activation+1.10e-03

Pos logit contributions
 hit+0.004
 shoot+0.004
Bang+0.004
 poked+0.004
 searched+0.004
Neg logit contributions
 queens-0.007
nam-0.007
overs-0.007
 penn-0.007
 register-0.007
Token cash
Token ID5003
Feature activation-2.69e-01

Pos logit contributions
 hit+0.002
 shoot+0.001
Bang+0.001
 poked+0.001
 searched+0.001
Neg logit contributions
 queens-0.002
nam-0.002
 penn-0.002
yle-0.002
 register-0.002
Tokenier
Token ID959
Feature activation-1.69e-02

Pos logit contributions
nam+0.330
 Clare+0.259
 queens+0.241
 Erin+0.238
 Debbie+0.236
Neg logit contributions
 hit-0.596
 poked-0.568
 searched-0.557
 replied-0.551
 saw-0.547
Token said
Token ID531
Feature activation+1.13e-02

Pos logit contributions
 queens+0.035
nam+0.035
 penn+0.034
 register+0.034
overs+0.034
Neg logit contributions
 hit-0.019
 shoot-0.017
Bang-0.017
 poked-0.017
 searched-0.017
Token,
Token ID11
Feature activation-2.48e-02

Pos logit contributions
 hit+0.014
 accidentally+0.013
 shoot+0.013
 poked+0.012
 searched+0.012
Neg logit contributions
nam-0.023
 queens-0.023
reating-0.022
yle-0.022
 register-0.022
Token "
Token ID366
Feature activation-2.11e-02

Pos logit contributions
 queens+0.051
nam+0.050
 penn+0.050
 register+0.050
yle+0.050
Neg logit contributions
 hit-0.028
 shoot-0.026
 accidentally-0.026
 searched-0.026
 poked-0.026
TokenOf
Token ID5189
Feature activation-1.06e-01

Pos logit contributions
 penn+0.034
nam+0.034
 register+0.034
 queens+0.034
ities+0.033
Neg logit contributions
Bang-0.033
 hit-0.033
 poked-0.031
 shoot-0.030
 accidentally-0.030
Tokenier
Token ID959
Feature activation-1.56e-02

Pos logit contributions
nam+0.366
 Clare+0.311
 queens+0.303
iley+0.296
 dancers+0.294
Neg logit contributions
 hit-0.488
 replied-0.484
 searched-0.476
house-0.464
 poked-0.464
Token.
Token ID13
Feature activation+7.93e-05

Pos logit contributions
 queens+0.035
nam+0.034
yle+0.033
iley+0.033
illi+0.033
Neg logit contributions
 hit-0.017
 searched-0.015
 shoot-0.015
 poked-0.015
 accidentally-0.014
Token
Token ID198
Feature activation+2.07e-02

Pos logit contributions
 hit+0.000
Bang+0.000
 shoot+0.000
 searched+0.000
 poked+0.000
Neg logit contributions
 queens-0.000
 penn-0.000
nam-0.000
 register-0.000
ities-0.000
Token
Token ID198
Feature activation+1.86e-02

Pos logit contributions
 hit+0.022
 shoot+0.021
 searched+0.020
 poked+0.020
Bang+0.020
Neg logit contributions
illi-0.043
 queens-0.043
overs-0.042
yle-0.042
iley-0.042
TokenThe
Token ID464
Feature activation-1.59e-02

Pos logit contributions
 hit+0.024
Bang+0.023
 shoot+0.023
 poked+0.023
 accidentally+0.022
Neg logit contributions
 queens-0.035
 penn-0.035
nam-0.035
 register-0.034
overs-0.034
Token cash
Token ID5003
Feature activation-2.65e-01

Pos logit contributions
ions+0.024
iley+0.023
overs+0.023
ities+0.023
reating+0.023
Neg logit contributions
 hit-0.029
 shoot-0.026
 fight-0.025
 quarrel-0.025
 accidentally-0.025
Tokenier
Token ID959
Feature activation-1.47e-02

Pos logit contributions
nam+0.358
 Clare+0.300
 queens+0.284
 Debbie+0.283
reating+0.277
Neg logit contributions
 hit-0.546
 poked-0.531
 replied-0.522
 searched-0.517
 saw-0.505
Token said
Token ID531
Feature activation+1.02e-02

Pos logit contributions
nam+0.033
 queens+0.033
 penn+0.032
 register+0.031
overs+0.031
Neg logit contributions
 hit-0.015
 poked-0.014
 searched-0.014
 shoot-0.013
 accidentally-0.013
Token,
Token ID11
Feature activation-2.49e-02

Pos logit contributions
 hit+0.010
 shoot+0.010
 accidentally+0.010
 searched+0.009
 poked+0.009
Neg logit contributions
 queens-0.023
nam-0.022
ities-0.022
iley-0.022
yle-0.022
Token "
Token ID366
Feature activation-2.26e-02

Pos logit contributions
 queens+0.054
nam+0.053
yle+0.053
reating+0.052
 register+0.052
Neg logit contributions
 hit-0.026
 shoot-0.024
 accidentally-0.024
 searched-0.024
 poked-0.023
TokenYou
Token ID1639
Feature activation-4.38e-02

Pos logit contributions
nam+0.039
 penn+0.039
ities+0.039
 register+0.039
ums+0.038
Neg logit contributions
Bang-0.034
 hit-0.032
 poked-0.031
 shoot-0.030
 accidentally-0.029
Token only
Token ID691
Feature activation-6.65e-03

Pos logit contributions
 hit+0.004
 shoot+0.004
 searched+0.004
 poked+0.004
 accidentally+0.003
Neg logit contributions
 register-0.006
 queens-0.006
yle-0.006
iley-0.005
illi-0.005
Token give
Token ID1577
Feature activation-1.19e-01

Pos logit contributions
 queens+0.013
yle+0.013
 register+0.013
ums+0.013
illi+0.013
Neg logit contributions
 hit-0.009
 shoot-0.008
 poked-0.008
 searched-0.008
 accidentally-0.008
Token out
Token ID503
Feature activation-8.49e-03

Pos logit contributions
 queens+0.228
ities+0.224
 importantly+0.222
 register+0.221
 singers+0.219
Neg logit contributions
 hit-0.152
 poked-0.139
 shoot-0.138
 searched-0.138
 accidentally-0.137
Token on
Token ID319
Feature activation-1.12e-03

Pos logit contributions
yle+0.016
 register+0.016
ums+0.015
ities+0.015
 penn+0.015
Neg logit contributions
 hit-0.011
 shoot-0.010
 poked-0.010
 searched-0.010
 accidentally-0.010
Token special
Token ID2041
Feature activation+1.22e-02

Pos logit contributions
 queens+0.002
 register+0.002
yle+0.002
oll+0.002
ums+0.002
Neg logit contributions
 hit-0.002
 accidentally-0.001
 shoot-0.001
 searched-0.001
 poked-0.001
Token occasions
Token ID12432
Feature activation-2.65e-01

Pos logit contributions
 hit+0.025
 searched+0.024
 shoot+0.024
 poked+0.023
 play+0.023
Neg logit contributions
yle-0.014
 queens-0.014
nam-0.014
illi-0.014
 register-0.014
Token.
Token ID13
Feature activation+2.89e-03

Pos logit contributions
 queens+0.575
nam+0.570
 penn+0.558
yle+0.549
iley+0.543
Neg logit contributions
 searched-0.226
 hit-0.223
 play-0.210
 accidentally-0.209
house-0.203
Tokenâ
Token ID22940
Feature activation+2.56e-02

Pos logit contributions
 hit+0.003
Bang+0.003
 shoot+0.002
 searched+0.002
 accidentally+0.002
Neg logit contributions
 penn-0.006
 queens-0.006
 register-0.006
nam-0.006
yle-0.006
Token
Token ID26391
Feature activation+1.17e-01

Pos logit contributions
 hit+0.036
 shoot+0.035
 poked+0.034
 accidentally+0.034
Bang+0.034
Neg logit contributions
 register-0.044
iley-0.044
iza-0.044
overs-0.043
illi-0.043
Token The
Token ID383
Feature activation-1.86e-03

Pos logit contributions
 hit+0.141
Bang+0.132
 shoot+0.131
 poked+0.129
 searched+0.128
Neg logit contributions
 queens-0.230
 penn-0.227
nam-0.227
 register-0.225
overs-0.222
Token kids
Token ID3988
Feature activation-8.42e-02

Pos logit contributions
yle+0.003
 queens+0.003
overs+0.003
ums+0.003
iley+0.003
Neg logit contributions
 hit-0.003
 searched-0.002
Bang-0.002
 shoot-0.002
 quarrel-0.002
Token to
Token ID284
Feature activation+4.94e-02

Pos logit contributions
 queens+0.009
nam+0.009
yle+0.009
 importantly+0.009
ities+0.009
Neg logit contributions
 hit-0.005
 poked-0.005
 searched-0.005
 accidentally-0.005
 shoot-0.004
Token help
Token ID1037
Feature activation-7.39e-02

Pos logit contributions
 hit+0.061
 shoot+0.057
 poked+0.054
 searched+0.053
 accidentally+0.052
Neg logit contributions
 queens-0.101
 register-0.099
 penn-0.099
nam-0.098
ities-0.098
Token and
Token ID290
Feature activation+4.41e-03

Pos logit contributions
 queens+0.128
nam+0.123
 importantly+0.121
 register+0.117
 singers+0.117
Neg logit contributions
 hit-0.119
 accidentally-0.110
 shoot-0.109
 poked-0.108
 play-0.105
Token fixed
Token ID5969
Feature activation+1.24e-02

Pos logit contributions
 hit+0.006
 shoot+0.006
Bang+0.006
 poked+0.006
 searched+0.006
Neg logit contributions
 queens-0.008
 penn-0.008
nam-0.008
 register-0.008
overs-0.008
Token the
Token ID262
Feature activation-6.15e-03

Pos logit contributions
 hit+0.014
 snowball+0.012
 accidentally+0.012
 poked+0.011
 shoot+0.011
Neg logit contributions
 queens-0.027
 importantly-0.026
 register-0.026
 singers-0.025
lessness-0.025
Token cash
Token ID5003
Feature activation-2.65e-01

Pos logit contributions
 queens+0.011
nam+0.010
 penn+0.010
 register+0.010
overs+0.010
Neg logit contributions
 hit-0.009
 shoot-0.008
Bang-0.008
 poked-0.008
 searched-0.008
Token register
Token ID7881
Feature activation-1.48e-01

Pos logit contributions
nam+0.387
 Clare+0.333
 Debbie+0.327
 hotels+0.313
 queens+0.313
Neg logit contributions
 hit-0.476
 replied-0.456
 poked-0.455
 searched-0.442
 accidentally-0.441
Token.
Token ID13
Feature activation+1.45e-05

Pos logit contributions
 queens+0.320
iley+0.313
reating+0.310
nam+0.303
 dancers+0.302
Neg logit contributions
 hit-0.168
 searched-0.158
 poked-0.151
 accidentally-0.149
 shoot-0.146
Token The
Token ID383
Feature activation+4.11e-03

Pos logit contributions
 hit+0.000
Bang+0.000
 shoot+0.000
 poked+0.000
 fight+0.000
Neg logit contributions
nam-0.000
overs-0.000
 Erin-0.000
 queens-0.000
 register-0.000
Token shop
Token ID6128
Feature activation-8.27e-02

Pos logit contributions
 hit+0.007
 shoot+0.007
 fight+0.007
 accidentally+0.007
 quarrel+0.007
Neg logit contributions
iley-0.006
ions-0.006
yle-0.006
overs-0.006
 queens-0.006
Tokenkeeper
Token ID13884
Feature activation-1.36e-02

Pos logit contributions
 queens+0.141
nam+0.139
iley+0.137
 penn+0.136
ities+0.135
Neg logit contributions
 hit-0.126
 searched-0.117
 shoot-0.116
 poked-0.116
 accidentally-0.115
Token gave
Token ID2921
Feature activation-1.02e-01

Pos logit contributions
Bang+0.031
 shoot+0.028
 hit+0.027
 snowball+0.024
 poked+0.024
Neg logit contributions
 penn-0.094
nam-0.094
 register-0.094
iza-0.094
 queens-0.093
Token the
Token ID262
Feature activation-1.01e-02

Pos logit contributions
ities+0.219
 queens+0.217
 importantly+0.213
 singers+0.211
 cents+0.210
Neg logit contributions
 hit-0.123
 searched-0.110
 poked-0.107
 shoot-0.106
Bang-0.100
Token money
Token ID1637
Feature activation-1.49e-01

Pos logit contributions
 queens+0.018
iley+0.018
ities+0.018
yle+0.017
overs+0.017
Neg logit contributions
 hit-0.015
 shoot-0.014
 poked-0.013
Bang-0.013
 accidentally-0.013
Token to
Token ID284
Feature activation+4.71e-02

Pos logit contributions
iley+0.384
 queens+0.372
 importantly+0.372
ities+0.372
illi+0.367
Neg logit contributions
 hit-0.118
 searched-0.096
 shoot-0.096
 play-0.085
 poked-0.084
Token the
Token ID262
Feature activation-7.18e-03

Pos logit contributions
 hit+0.061
 shoot+0.059
 play+0.054
 fight+0.052
 accidentally+0.051
Neg logit contributions
 queens-0.097
 penn-0.096
ities-0.095
 register-0.094
asers-0.094
Token cash
Token ID5003
Feature activation-2.65e-01

Pos logit contributions
 queens+0.012
iley+0.012
yle+0.012
 penn+0.012
nam+0.012
Neg logit contributions
 hit-0.011
 shoot-0.010
Bang-0.010
 accidentally-0.010
 poked-0.009
Tokenier
Token ID959
Feature activation-1.56e-02

Pos logit contributions
nam+0.366
 Clare+0.311
 queens+0.303
iley+0.296
 dancers+0.294
Neg logit contributions
 hit-0.488
 replied-0.484
 searched-0.476
house-0.464
 poked-0.464
Token.
Token ID13
Feature activation+7.93e-05

Pos logit contributions
 queens+0.035
nam+0.034
yle+0.033
iley+0.033
illi+0.033
Neg logit contributions
 hit-0.017
 searched-0.015
 shoot-0.015
 poked-0.015
 accidentally-0.014
Token
Token ID198
Feature activation+2.07e-02

Pos logit contributions
 hit+0.000
Bang+0.000
 shoot+0.000
 searched+0.000
 poked+0.000
Neg logit contributions
 queens-0.000
 penn-0.000
nam-0.000
 register-0.000
ities-0.000
Token
Token ID198
Feature activation+1.86e-02

Pos logit contributions
 hit+0.022
 shoot+0.021
 searched+0.020
 poked+0.020
Bang+0.020
Neg logit contributions
illi-0.043
 queens-0.043
overs-0.042
yle-0.042
iley-0.042
TokenThe
Token ID464
Feature activation-1.59e-02

Pos logit contributions
 hit+0.024
Bang+0.023
 shoot+0.023
 poked+0.023
 accidentally+0.022
Neg logit contributions
 queens-0.035
 penn-0.035
nam-0.035
 register-0.034
overs-0.034
Token they
Token ID484
Feature activation-1.41e-02

Pos logit contributions
oll+0.158
ities+0.157
asers+0.156
ums+0.155
yle+0.153
Neg logit contributions
 accidentally-0.113
 hit-0.112
 shoot-0.102
 fight-0.102
 searched-0.100
Token got
Token ID1392
Feature activation-3.51e-02

Pos logit contributions
 queens+0.032
 penn+0.031
nam+0.031
 register+0.031
overs+0.031
Neg logit contributions
 hit-0.013
Bang-0.012
 shoot-0.012
 poked-0.012
 searched-0.012
Token up
Token ID510
Feature activation+1.24e-01

Pos logit contributions
 queens+0.065
 penn+0.064
nam+0.064
 register+0.064
overs+0.063
Neg logit contributions
 hit-0.047
Bang-0.045
 shoot-0.045
 poked-0.044
 searched-0.043
Token to
Token ID284
Feature activation+4.60e-02

Pos logit contributions
 hit+0.120
 accidentally+0.107
 searched+0.105
 shoot+0.099
 fight+0.097
Neg logit contributions
 queens-0.288
ities-0.282
iley-0.280
yle-0.278
reating-0.277
Token the
Token ID262
Feature activation-6.38e-03

Pos logit contributions
 hit+0.067
 shoot+0.063
 searched+0.062
 accidentally+0.061
 poked+0.061
Neg logit contributions
 queens-0.083
 register-0.079
 penn-0.079
oll-0.079
nam-0.078
Token cash
Token ID5003
Feature activation-2.64e-01

Pos logit contributions
iley+0.012
 queens+0.012
yle+0.012
nam+0.012
ities+0.012
Neg logit contributions
 hit-0.008
 shoot-0.007
 accidentally-0.007
 fight-0.007
 quarrel-0.007
Tokenier
Token ID959
Feature activation-1.59e-02

Pos logit contributions
nam+0.355
 queens+0.277
 Clare+0.276
 diamonds+0.266
 importantly+0.260
Neg logit contributions
 hit-0.520
 replied-0.501
 accidentally-0.488
house-0.485
's-0.479
Token they
Token ID484
Feature activation-1.26e-02

Pos logit contributions
 queens+0.039
nam+0.038
illi+0.037
iley+0.037
yle+0.037
Neg logit contributions
 hit-0.014
 searched-0.012
 accidentally-0.012
 shoot-0.011
 fight-0.011
Token looked
Token ID3114
Feature activation+9.27e-02

Pos logit contributions
 queens+0.029
 penn+0.029
nam+0.028
overs+0.028
iley+0.028
Neg logit contributions
 hit-0.012
 searched-0.010
 poked-0.010
 shoot-0.010
 accidentally-0.010
Token very
Token ID845
Feature activation+3.18e-03

Pos logit contributions
 hit+0.133
 shoot+0.125
Bang+0.125
 poked+0.124
 searched+0.124
Neg logit contributions
 queens-0.162
nam-0.158
 penn-0.158
 register-0.157
yle-0.155
Token surprised
Token ID6655
Feature activation+1.28e-01

Pos logit contributions
 hit+0.004
Bang+0.004
 shoot+0.004
 poked+0.004
 searched+0.004
Neg logit contributions
 queens-0.006
 penn-0.006
nam-0.006
 register-0.006
overs-0.006
Token asked
Token ID1965
Feature activation+3.19e-02

Pos logit contributions
 queens+0.141
 register+0.139
nam+0.138
 penn+0.138
iley+0.137
Neg logit contributions
Bang-0.067
 hit-0.066
 shoot-0.063
 searched-0.059
 poked-0.059
Token.
Token ID13
Feature activation-3.39e-03

Pos logit contributions
 hit+0.039
 poked+0.037
 accidentally+0.037
 searched+0.036
 shoot+0.035
Neg logit contributions
 queens-0.066
 penn-0.063
reating-0.062
nam-0.061
 cents-0.060
Token
Token ID198
Feature activation+1.76e-02

Pos logit contributions
 Erin+0.006
 Clare+0.006
nam+0.006
 queens+0.006
overs+0.006
Neg logit contributions
 hit-0.004
 shoot-0.004
Bang-0.004
 searched-0.004
 poked-0.004
Token
Token ID198
Feature activation+1.66e-02

Pos logit contributions
 hit+0.024
 shoot+0.023
 searched+0.023
 poked+0.022
 fight+0.022
Neg logit contributions
illi-0.032
 Erin-0.031
 Clare-0.031
iza-0.031
iley-0.031
TokenThe
Token ID464
Feature activation-1.49e-02

Pos logit contributions
 hit+0.028
 searched+0.027
 shoot+0.027
Bang+0.026
 poked+0.026
Neg logit contributions
 queens-0.024
iley-0.024
illi-0.024
iza-0.024
 Clare-0.023
Token cash
Token ID5003
Feature activation-2.61e-01

Pos logit contributions
ions+0.022
overs+0.021
yle+0.021
iley+0.021
 queens+0.021
Neg logit contributions
 hit-0.027
 quarrel-0.025
 fight-0.024
 shoot-0.024
 accidentally-0.024
Tokenier
Token ID959
Feature activation-1.39e-02

Pos logit contributions
nam+0.326
 Clare+0.278
 queens+0.268
reating+0.265
 passports+0.257
Neg logit contributions
 hit-0.557
 poked-0.555
 replied-0.542
 searched-0.525
 accidentally-0.523
Token said
Token ID531
Feature activation+8.24e-03

Pos logit contributions
 queens+0.033
nam+0.032
 penn+0.032
 register+0.032
overs+0.032
Neg logit contributions
 hit-0.012
 poked-0.011
 shoot-0.011
 searched-0.011
 accidentally-0.010
Token,
Token ID11
Feature activation-2.66e-02

Pos logit contributions
 hit+0.008
 accidentally+0.007
 shoot+0.007
 poked+0.007
 searched+0.007
Neg logit contributions
 queens-0.019
nam-0.018
reating-0.018
iley-0.018
ities-0.018
Token "
Token ID366
Feature activation-2.36e-02

Pos logit contributions
 queens+0.054
 penn+0.053
nam+0.053
 register+0.052
yle+0.052
Neg logit contributions
 hit-0.031
 shoot-0.029
 poked-0.028
 accidentally-0.028
 searched-0.028
TokenIt
Token ID1026
Feature activation+8.63e-02

Pos logit contributions
 penn+0.041
 register+0.041
 queens+0.040
nam+0.040
ities+0.039
Neg logit contributions
Bang-0.034
 hit-0.034
 poked-0.032
 accidentally-0.032
 shoot-0.032
Tokens
Token ID82
Feature activation-2.17e-03

Pos logit contributions
iley+0.049
 Debbie+0.048
 singers+0.047
overs+0.047
 Clare+0.047
Neg logit contributions
 hit-0.034
 accidentally-0.030
 poked-0.029
 searched-0.029
house-0.028
Token on
Token ID319
Feature activation+2.58e-04

Pos logit contributions
 queens+0.004
iley+0.004
nam+0.004
yle+0.004
 register+0.004
Neg logit contributions
 hit-0.003
 searched-0.002
 poked-0.002
 accidentally-0.002
 shoot-0.002
Token display
Token ID3359
Feature activation-9.89e-02

Pos logit contributions
 hit+0.000
 accidentally+0.000
 shoot+0.000
Bang+0.000
 One+0.000
Neg logit contributions
asers-0.001
oll-0.001
 queens-0.001
 importantly-0.001
iley-0.001
Token near
Token ID1474
Feature activation+6.53e-02

Pos logit contributions
iley+0.217
yle+0.212
 queens+0.208
nam+0.207
uka+0.207
Neg logit contributions
 hit-0.098
 searched-0.096
house-0.092
 poked-0.088
 accidentally-0.086
Token the
Token ID262
Feature activation-7.00e-03

Pos logit contributions
 hit+0.082
 accidentally+0.075
 shoot+0.074
 poked+0.072
 searched+0.072
Neg logit contributions
iley-0.131
oll-0.130
 queens-0.130
 importantly-0.127
lessness-0.127
Token cash
Token ID5003
Feature activation-2.61e-01

Pos logit contributions
iley+0.014
ities+0.014
yle+0.014
 importantly+0.014
ums+0.014
Neg logit contributions
 hit-0.009
 shoot-0.008
 accidentally-0.008
 fight-0.008
Bang-0.007
Token register
Token ID7881
Feature activation-1.43e-01

Pos logit contributions
nam+0.362
 Clare+0.295
 importantly+0.285
 queens+0.279
 Debbie+0.274
Neg logit contributions
's-0.480
 hit-0.471
house-0.466
 poked-0.455
 searched-0.453
Token.
Token ID13
Feature activation+5.42e-03

Pos logit contributions
 queens+0.320
iley+0.317
nam+0.314
reating+0.311
illi+0.306
Neg logit contributions
 hit-0.140
 searched-0.135
 accidentally-0.128
 poked-0.126
 saw-0.123
Token They
Token ID1119
Feature activation-1.76e-02

Pos logit contributions
 hit+0.009
 shoot+0.009
Bang+0.009
 poked+0.009
 snowball+0.008
Neg logit contributions
nam-0.008
overs-0.008
 Erin-0.008
 register-0.008
 penn-0.008
Token looked
Token ID3114
Feature activation+9.32e-02

Pos logit contributions
nam+0.035
 penn+0.035
 queens+0.034
 register+0.034
 Erin+0.033
Neg logit contributions
Bang-0.020
 hit-0.020
 shoot-0.020
 poked-0.018
 accidentally-0.018
Token so
Token ID523
Feature activation-3.34e-03

Pos logit contributions
Bang+0.152
 hit+0.149
 shoot+0.146
 poked+0.141
 accidentally+0.135
Neg logit contributions
nam-0.147
 penn-0.145
 queens-0.141
 register-0.136
overs-0.135
Tokenier
Token ID959
Feature activation-1.33e-02

Pos logit contributions
nam+0.371
 Clare+0.303
 queens+0.300
 dancers+0.284
 importantly+0.283
Neg logit contributions
 hit-0.491
 poked-0.475
 searched-0.469
 replied-0.458
 accidentally-0.454
Token.
Token ID13
Feature activation+2.19e-03

Pos logit contributions
 queens+0.027
nam+0.027
illi+0.026
 penn+0.026
iza+0.026
Neg logit contributions
 hit-0.017
 shoot-0.016
 searched-0.015
 poked-0.015
 fight-0.014
Token
Token ID198
Feature activation+2.15e-02

Pos logit contributions
 hit+0.002
Bang+0.002
 shoot+0.002
 poked+0.002
 searched+0.002
Neg logit contributions
 queens-0.005
 penn-0.005
nam-0.005
 register-0.005
overs-0.005
Token
Token ID198
Feature activation+2.01e-02

Pos logit contributions
 hit+0.024
 shoot+0.022
 searched+0.022
 poked+0.022
Bang+0.021
Neg logit contributions
 queens-0.044
illi-0.044
yle-0.043
overs-0.043
 register-0.043
TokenThe
Token ID464
Feature activation-1.29e-02

Pos logit contributions
 hit+0.026
Bang+0.024
 shoot+0.024
 poked+0.024
 searched+0.023
Neg logit contributions
 queens-0.038
 penn-0.038
nam-0.038
 register-0.038
overs-0.037
Token cash
Token ID5003
Feature activation-2.61e-01

Pos logit contributions
overs+0.022
nam+0.021
 queens+0.021
reating+0.021
ities+0.021
Neg logit contributions
 hit-0.021
 shoot-0.019
 fight-0.018
 accidentally-0.018
Bang-0.018
Tokenier
Token ID959
Feature activation-1.25e-02

Pos logit contributions
nam+0.364
 Clare+0.310
 Debbie+0.290
reating+0.289
 hotels+0.284
Neg logit contributions
 hit-0.530
 poked-0.525
 searched-0.506
 accidentally-0.499
 replied-0.498
Token said
Token ID531
Feature activation+1.13e-02

Pos logit contributions
 queens+0.027
nam+0.027
 penn+0.027
 register+0.027
overs+0.027
Neg logit contributions
 hit-0.013
 poked-0.012
 shoot-0.012
 searched-0.011
 accidentally-0.011
Token,
Token ID11
Feature activation-2.34e-02

Pos logit contributions
 hit+0.011
 shoot+0.011
 accidentally+0.010
 searched+0.010
 poked+0.010
Neg logit contributions
 queens-0.025
nam-0.025
reating-0.025
ities-0.025
iley-0.025
Token "
Token ID366
Feature activation-2.13e-02

Pos logit contributions
 queens+0.049
nam+0.048
 penn+0.048
 register+0.048
yle+0.048
Neg logit contributions
 hit-0.026
 shoot-0.024
 poked-0.024
 searched-0.024
 accidentally-0.023
TokenWhat
Token ID2061
Feature activation-6.85e-02

Pos logit contributions
 penn+0.038
nam+0.038
ities+0.037
ums+0.037
 passports+0.037
Neg logit contributions
Bang-0.031
 hit-0.029
 poked-0.028
 shoot-0.027
 accidentally-0.027
Token and
Token ID290
Feature activation+5.06e-03

Pos logit contributions
 hit+0.102
Bang+0.096
 shoot+0.096
 poked+0.094
 searched+0.093
Neg logit contributions
 queens-0.155
 penn-0.153
nam-0.153
 register-0.152
overs-0.150
Token took
Token ID1718
Feature activation-4.86e-02

Pos logit contributions
 hit+0.005
Bang+0.005
 shoot+0.004
 poked+0.004
 searched+0.004
Neg logit contributions
 queens-0.011
nam-0.011
 penn-0.011
 register-0.011
yle-0.011
Token it
Token ID340
Feature activation+8.13e-02

Pos logit contributions
nam+0.104
 queens+0.101
ities+0.101
 register+0.099
reating+0.097
Neg logit contributions
 hit-0.062
 shoot-0.057
Bang-0.055
 poked-0.055
 searched-0.053
Token to
Token ID284
Feature activation+4.84e-02

Pos logit contributions
 hit+0.107
 shoot+0.101
Bang+0.098
 searched+0.098
 poked+0.097
Neg logit contributions
 queens-0.153
nam-0.152
 penn-0.152
 register-0.150
iley-0.149
Token the
Token ID262
Feature activation-5.59e-03

Pos logit contributions
 hit+0.068
 shoot+0.065
Bang+0.061
 poked+0.060
 searched+0.059
Neg logit contributions
 penn-0.092
nam-0.091
 queens-0.091
 register-0.091
ities-0.089
Token cash
Token ID5003
Feature activation-2.61e-01

Pos logit contributions
 queens+0.010
 penn+0.010
nam+0.010
overs+0.010
yle+0.010
Neg logit contributions
 hit-0.008
 shoot-0.007
Bang-0.007
 poked-0.007
 accidentally-0.007
Tokenier
Token ID959
Feature activation-1.33e-02

Pos logit contributions
nam+0.371
 Clare+0.303
 queens+0.300
 dancers+0.284
 importantly+0.283
Neg logit contributions
 hit-0.491
 poked-0.475
 searched-0.469
 replied-0.458
 accidentally-0.454
Token.
Token ID13
Feature activation+2.19e-03

Pos logit contributions
 queens+0.027
nam+0.027
illi+0.026
 penn+0.026
iza+0.026
Neg logit contributions
 hit-0.017
 shoot-0.016
 searched-0.015
 poked-0.015
 fight-0.014
Token
Token ID198
Feature activation+2.15e-02

Pos logit contributions
 hit+0.002
Bang+0.002
 shoot+0.002
 poked+0.002
 searched+0.002
Neg logit contributions
 queens-0.005
 penn-0.005
nam-0.005
 register-0.005
overs-0.005
Token
Token ID198
Feature activation+2.01e-02

Pos logit contributions
 hit+0.024
 shoot+0.022
 searched+0.022
 poked+0.022
Bang+0.021
Neg logit contributions
 queens-0.044
illi-0.044
yle-0.043
overs-0.043
 register-0.043
TokenThe
Token ID464
Feature activation-1.29e-02

Pos logit contributions
 hit+0.026
Bang+0.024
 shoot+0.024
 poked+0.024
 searched+0.023
Neg logit contributions
 queens-0.038
 penn-0.038
nam-0.038
 register-0.038
overs-0.037
Token.
Token ID13
Feature activation-3.10e-03

Pos logit contributions
nam+0.185
reating+0.182
 queens+0.182
 dancers+0.176
yle+0.175
Neg logit contributions
 hit-0.118
 poked-0.108
 shoot-0.108
 searched-0.107
Bang-0.105
Token Smith
Token ID4176
Feature activation-1.55e-02

Pos logit contributions
 penn+0.004
 queens+0.004
iza+0.004
 singers+0.004
asers+0.004
Neg logit contributions
 hit-0.005
 shoot-0.005
Bang-0.005
 accidentally-0.005
 searched-0.005
Token happily
Token ID18177
Feature activation+2.17e-02

Pos logit contributions
 penn+0.030
 register+0.029
illi+0.029
iley+0.028
 queens+0.028
Neg logit contributions
Bang-0.019
 shoot-0.017
 hit-0.017
 BO-0.016
 SPL-0.015
Token thanked
Token ID26280
Feature activation-5.27e-02

Pos logit contributions
 hit+0.023
Bang+0.023
 shoot+0.022
 accidentally+0.021
 poked+0.021
Neg logit contributions
 queens-0.045
 penn-0.044
 register-0.044
nam-0.043
iley-0.043
Token the
Token ID262
Feature activation-7.69e-03

Pos logit contributions
iest+0.103
lessness+0.102
asers+0.099
ities+0.099
 cents+0.099
Neg logit contributions
 hit-0.065
 shoot-0.065
 play-0.060
 fight-0.060
 accidentally-0.059
Token cash
Token ID5003
Feature activation-2.61e-01

Pos logit contributions
ities+0.013
ions+0.013
iley+0.013
ala+0.013
overs+0.013
Neg logit contributions
 hit-0.012
 shoot-0.011
 fight-0.011
 quarrel-0.011
Bang-0.010
Tokenier
Token ID959
Feature activation-1.22e-02

Pos logit contributions
nam+0.365
 Clare+0.303
 passports+0.289
 Debbie+0.288
 dancers+0.285
Neg logit contributions
 hit-0.485
 replied-0.464
 searched-0.461
 poked-0.454
house-0.450
Token and
Token ID290
Feature activation+1.60e-03

Pos logit contributions
nam+0.031
 queens+0.030
yle+0.030
illi+0.030
iza+0.029
Neg logit contributions
 hit-0.009
 shoot-0.008
 searched-0.008
 fight-0.007
 replied-0.007
Token walked
Token ID6807
Feature activation+5.18e-02

Pos logit contributions
 hit+0.002
 searched+0.002
 shoot+0.002
 poked+0.002
 accidentally+0.001
Neg logit contributions
ities-0.004
yle-0.004
ala-0.004
iley-0.004
overs-0.004
Token back
Token ID736
Feature activation+6.69e-02

Pos logit contributions
 hit+0.050
 searched+0.045
 shoot+0.044
Bang+0.043
 poked+0.042
Neg logit contributions
ities-0.120
nam-0.119
 queens-0.118
yle-0.116
 penn-0.116
Token to
Token ID284
Feature activation+4.51e-02

Pos logit contributions
 hit+0.087
 shoot+0.082
Bang+0.082
 poked+0.081
 searched+0.080
Neg logit contributions
 queens-0.126
nam-0.124
 penn-0.124
 register-0.123
overs-0.121
Token the
Token ID262
Feature activation-4.43e-03

Pos logit contributions
 hit+0.069
 shoot+0.063
 poked+0.061
 fight+0.060
 searched+0.058
Neg logit contributions
 queens-0.088
 penn-0.086
 cents-0.086
 importantly-0.085
 dollars-0.085
Token dressing
Token ID18544
Feature activation-6.81e-02

Pos logit contributions
 queens+0.008
nam+0.008
 penn+0.008
 register+0.008
overs+0.008
Neg logit contributions
 hit-0.006
 shoot-0.006
Bang-0.006
 poked-0.006
 searched-0.005
Token room
Token ID2119
Feature activation-6.37e-02

Pos logit contributions
 importantly+0.158
 queens+0.158
iley+0.154
nam+0.153
 cents+0.149
Neg logit contributions
 hit-0.065
 searched-0.058
 accidentally-0.052
 poked-0.052
 shoot-0.050
Token and
Token ID290
Feature activation+7.71e-03

Pos logit contributions
 queens+0.132
iley+0.129
yle+0.127
 penn+0.126
nam+0.126
Neg logit contributions
 hit-0.074
 searched-0.071
 poked-0.065
 shoot-0.065
 accidentally-0.065
Token the
Token ID262
Feature activation-1.54e-03

Pos logit contributions
 hit+0.009
 searched+0.008
 accidentally+0.008
 poked+0.008
 shoot+0.007
Neg logit contributions
 queens-0.017
iley-0.017
ums-0.017
 penn-0.017
 cents-0.017
Token cash
Token ID5003
Feature activation-2.60e-01

Pos logit contributions
 queens+0.003
iley+0.003
yle+0.003
ums+0.003
overs+0.003
Neg logit contributions
 hit-0.002
 shoot-0.002
Bang-0.002
 fight-0.002
 poked-0.002
Tokenier
Token ID959
Feature activation-9.17e-03

Pos logit contributions
nam+0.392
 Clare+0.333
 queens+0.323
iley+0.315
 Debbie+0.313
Neg logit contributions
 hit-0.464
 poked-0.456
 searched-0.445
 replied-0.443
 broke-0.422
Token,
Token ID11
Feature activation-2.17e-02

Pos logit contributions
 queens+0.019
nam+0.019
iley+0.018
yle+0.018
 penn+0.018
Neg logit contributions
 hit-0.012
 searched-0.011
 poked-0.011
 accidentally-0.010
 shoot-0.010
Token but
Token ID475
Feature activation-3.15e-02

Pos logit contributions
iest+0.050
 queens+0.050
ums+0.049
reating+0.049
ala+0.048
Neg logit contributions
 hit-0.021
 accidentally-0.020
 searched-0.020
 saw-0.019
 poked-0.018
Token she
Token ID673
Feature activation+9.46e-03

Pos logit contributions
iley+0.060
ums+0.059
asers+0.058
 queens+0.058
unn+0.056
Neg logit contributions
 hit-0.047
 accidentally-0.045
 saw-0.042
 searched-0.040
 poked-0.039
Token was
Token ID373
Feature activation+2.16e-02

Pos logit contributions
 hit+0.009
 poked+0.008
 searched+0.008
 accidentally+0.008
 shoot+0.007
Neg logit contributions
 queens-0.022
nam-0.022
 penn-0.022
overs-0.022
 register-0.022
Token over
Token ID625
Feature activation+9.04e-02

Pos logit contributions
 queens+0.119
ities+0.114
iley+0.111
 singers+0.111
 importantly+0.111
Neg logit contributions
 hit-0.125
 searched-0.115
 poked-0.114
 shoot-0.113
 accidentally-0.113
Token her
Token ID607
Feature activation-5.56e-02

Pos logit contributions
 hit+0.109
 accidentally+0.105
 play+0.103
 poked+0.099
 searched+0.098
Neg logit contributions
ities-0.180
 queens-0.177
 singers-0.175
 register-0.175
ums-0.172
Token allowance
Token ID24930
Feature activation-1.53e-01

Pos logit contributions
 queens+0.091
iley+0.088
 register+0.087
overs+0.087
reating+0.087
Neg logit contributions
 hit-0.089
 shoot-0.084
 poked-0.082
 accidentally-0.081
 searched-0.081
Token to
Token ID284
Feature activation+4.74e-02

Pos logit contributions
iley+0.361
 queens+0.348
ubb+0.337
acy+0.335
 importantly+0.332
Neg logit contributions
 hit-0.182
 searched-0.141
 shoot-0.137
 poked-0.133
 fixed-0.130
Token the
Token ID262
Feature activation-3.95e-03

Pos logit contributions
 hit+0.051
 shoot+0.046
 play+0.043
 fight+0.042
 searched+0.040
Neg logit contributions
 queens-0.114
 importantly-0.106
 singers-0.106
iley-0.106
asers-0.106
Token cash
Token ID5003
Feature activation-2.60e-01

Pos logit contributions
 queens+0.007
iley+0.007
yle+0.007
nam+0.007
overs+0.007
Neg logit contributions
 hit-0.006
 shoot-0.005
Bang-0.005
 accidentally-0.005
 fight-0.005
Tokenier
Token ID959
Feature activation-1.39e-02

Pos logit contributions
nam+0.351
 Clare+0.309
 queens+0.299
 dancers+0.286
 Debbie+0.280
Neg logit contributions
 hit-0.488
house-0.474
 searched-0.466
 poked-0.462
 replied-0.457
Token.
Token ID13
Feature activation-6.03e-04

Pos logit contributions
 queens+0.034
nam+0.032
iley+0.031
 importantly+0.031
 singers+0.031
Neg logit contributions
 hit-0.014
 searched-0.012
 fight-0.011
 poked-0.011
 shoot-0.011
Token
Token ID198
Feature activation+2.36e-02

Pos logit contributions
overs+0.001
nam+0.001
 Erin+0.001
 penn+0.001
 register+0.001
Neg logit contributions
 hit-0.001
 shoot-0.001
Bang-0.001
 poked-0.001
 searched-0.001
Token
Token ID198
Feature activation+2.14e-02

Pos logit contributions
 hit+0.028
 shoot+0.026
 poked+0.026
 searched+0.026
Bang+0.025
Neg logit contributions
illi-0.046
yle-0.045
 Erin-0.045
 Clare-0.045
overs-0.045
TokenAs
Token ID1722
Feature activation-6.95e-02

Pos logit contributions
 hit+0.029
 searched+0.028
 poked+0.028
 shoot+0.028
Bang+0.027
Neg logit contributions
 queens-0.038
nam-0.037
 penn-0.037
 register-0.037
reating-0.037
TokenWhen
Token ID2215
Feature activation-1.01e-01

Pos logit contributions
 hit+0.030
 shoot+0.029
 searched+0.029
 poked+0.029
Bang+0.028
Neg logit contributions
 queens-0.027
nam-0.026
 penn-0.026
illi-0.026
 register-0.026
Token they
Token ID484
Feature activation-1.23e-02

Pos logit contributions
ities+0.200
asers+0.195
ums+0.193
oll+0.192
yle+0.190
Neg logit contributions
 hit-0.147
 accidentally-0.145
 play-0.126
 shoot-0.126
 fight-0.125
Token got
Token ID1392
Feature activation-3.47e-02

Pos logit contributions
 queens+0.027
 register+0.027
 penn+0.027
iza+0.027
yle+0.026
Neg logit contributions
Bang-0.011
 hit-0.011
 shoot-0.011
 poked-0.010
 accidentally-0.010
Token to
Token ID284
Feature activation+4.73e-02

Pos logit contributions
 queens+0.059
nam+0.059
 penn+0.058
 register+0.056
overs+0.056
Neg logit contributions
Bang-0.051
 shoot-0.049
 hit-0.048
 poked-0.046
 accidentally-0.046
Token the
Token ID262
Feature activation-7.81e-03

Pos logit contributions
 hit+0.078
Bang+0.076
 poked+0.074
 searched+0.074
 shoot+0.074
Neg logit contributions
 queens-0.070
nam-0.070
 penn-0.069
 register-0.068
overs-0.067
Token cash
Token ID5003
Feature activation-2.59e-01

Pos logit contributions
 register+0.015
 queens+0.014
 penn+0.014
overs+0.014
 passports+0.014
Neg logit contributions
 poked-0.010
 searched-0.010
Bang-0.009
 hit-0.009
 accidentally-0.009
Tokenier
Token ID959
Feature activation-1.14e-02

Pos logit contributions
nam+0.356
 Clare+0.293
 queens+0.273
 diamonds+0.266
 Debbie+0.263
Neg logit contributions
 hit-0.533
 poked-0.501
 replied-0.498
house-0.479
 accidentally-0.476
Token,
Token ID11
Feature activation-2.47e-02

Pos logit contributions
 queens+0.027
nam+0.026
reating+0.026
illi+0.025
 penn+0.025
Neg logit contributions
 hit-0.011
 accidentally-0.009
 searched-0.009
 poked-0.009
 shoot-0.009
Token the
Token ID262
Feature activation-5.19e-03

Pos logit contributions
iley+0.054
ities+0.053
reating+0.053
 pounds+0.053
oll+0.052
Neg logit contributions
 accidentally-0.030
 hit-0.028
 shoot-0.025
 saw-0.025
 poked-0.024
Token lady
Token ID10846
Feature activation-5.45e-02

Pos logit contributions
 queens+0.010
yle+0.010
nam+0.010
reating+0.010
 Erin+0.010
Neg logit contributions
 hit-0.007
 shoot-0.006
Bang-0.006
 fight-0.006
 poked-0.006
Token weighed
Token ID20261
Feature activation+4.54e-03

Pos logit contributions
 register+0.104
iza+0.102
 queens+0.102
 penn+0.101
illi+0.101
Neg logit contributions
Bang-0.069
 shoot-0.060
 hit-0.058
 snowball-0.055
 BO-0.055
Token,
Token ID11
Feature activation-2.10e-02

Pos logit contributions
 hit+0.032
 shoot+0.029
 accidentally+0.029
 searched+0.028
 poked+0.028
Neg logit contributions
 queens-0.070
nam-0.070
 register-0.068
ities-0.067
 penn-0.067
Token they
Token ID484
Feature activation-1.18e-02

Pos logit contributions
oll+0.042
 register+0.041
ities+0.041
 cents+0.040
reating+0.040
Neg logit contributions
 hit-0.027
 accidentally-0.027
 shoot-0.026
 poked-0.024
 searched-0.023
Token went
Token ID1816
Feature activation+2.43e-02

Pos logit contributions
 queens+0.024
nam+0.023
 penn+0.023
 register+0.023
overs+0.023
Neg logit contributions
 hit-0.013
Bang-0.013
 shoot-0.013
 poked-0.012
 searched-0.012
Token to
Token ID284
Feature activation+4.71e-02

Pos logit contributions
 hit+0.027
 searched+0.025
 shoot+0.024
 poked+0.023
 accidentally+0.023
Neg logit contributions
nam-0.052
 queens-0.051
ities-0.051
 penn-0.051
yle-0.051
Token the
Token ID262
Feature activation-7.43e-03

Pos logit contributions
 hit+0.075
Bang+0.075
 poked+0.072
 searched+0.072
 shoot+0.070
Neg logit contributions
nam-0.072
 Clare-0.070
 Erin-0.069
 penn-0.069
 queens-0.069
Token cash
Token ID5003
Feature activation-2.59e-01

Pos logit contributions
 queens+0.013
 penn+0.013
nam+0.013
 register+0.013
overs+0.013
Neg logit contributions
 hit-0.010
Bang-0.010
 shoot-0.010
 poked-0.009
 searched-0.009
Tokenier
Token ID959
Feature activation-1.13e-02

Pos logit contributions
nam+0.345
 queens+0.267
 Clare+0.267
 importantly+0.264
iley+0.251
Neg logit contributions
 hit-0.501
 searched-0.487
 replied-0.484
 poked-0.480
 accidentally-0.472
Token to
Token ID284
Feature activation+4.83e-02

Pos logit contributions
 queens+0.026
nam+0.026
illi+0.025
yle+0.025
 penn+0.025
Neg logit contributions
 hit-0.011
 searched-0.010
 poked-0.010
 shoot-0.010
 accidentally-0.009
Token pay
Token ID1414
Feature activation-1.37e-01

Pos logit contributions
 hit+0.053
 shoot+0.050
 searched+0.046
 poked+0.046
 accidentally+0.045
Neg logit contributions
 queens-0.105
 penn-0.103
iley-0.102
yle-0.101
ities-0.101
Token.
Token ID13
Feature activation+2.19e-03

Pos logit contributions
 queens+0.284
yle+0.271
ala+0.271
iley+0.269
 importantly+0.266
Neg logit contributions
 hit-0.170
 shoot-0.146
 poked-0.145
 searched-0.144
 saw-0.141
Token The
Token ID383
Feature activation+6.94e-04

Pos logit contributions
 hit+0.002
Bang+0.002
 shoot+0.002
 searched+0.002
 poked+0.002
Neg logit contributions
 queens-0.005
 penn-0.005
nam-0.005
 register-0.005
yle-0.005
Token.
Token ID13
Feature activation+2.66e-04

Pos logit contributions
nam+0.134
iley+0.128
yle+0.128
 queens+0.128
illi+0.125
Neg logit contributions
 hit-0.074
 shoot-0.067
 poked-0.067
 searched-0.066
 accidentally-0.063
Token He
Token ID679
Feature activation+3.35e-02

Pos logit contributions
 hit+0.000
Bang+0.000
 shoot+0.000
 poked+0.000
 searched+0.000
Neg logit contributions
 queens-0.001
 penn-0.001
nam-0.001
 register-0.001
yle-0.001
Token smiled
Token ID13541
Feature activation+5.54e-02

Pos logit contributions
 hit+0.034
Bang+0.032
 shoot+0.032
 poked+0.030
 searched+0.030
Neg logit contributions
 queens-0.071
 penn-0.071
nam-0.070
 register-0.069
overs-0.068
Token at
Token ID379
Feature activation+1.02e-02

Pos logit contributions
 hit+0.056
 shoot+0.052
 poked+0.051
 searched+0.050
 accidentally+0.049
Neg logit contributions
 penn-0.120
nam-0.120
 queens-0.119
 register-0.119
illi-0.119
Token the
Token ID262
Feature activation-8.09e-03

Pos logit contributions
 hit+0.013
 searched+0.012
 poked+0.011
 shoot+0.011
 accidentally+0.011
Neg logit contributions
 register-0.021
 cents-0.020
 queens-0.020
 dollars-0.020
 penn-0.020
Token cash
Token ID5003
Feature activation-2.58e-01

Pos logit contributions
 queens+0.013
yle+0.013
nam+0.013
 penn+0.013
 register+0.013
Neg logit contributions
 hit-0.012
 shoot-0.012
Bang-0.012
 poked-0.011
 accidentally-0.011
Tokenier
Token ID959
Feature activation-7.76e-03

Pos logit contributions
nam+0.430
 Clare+0.329
 queens+0.314
 Erin+0.310
 importantly+0.308
Neg logit contributions
 hit-0.443
 replied-0.423
 poked-0.418
's-0.416
house-0.401
Token,
Token ID11
Feature activation-2.38e-02

Pos logit contributions
 queens+0.017
nam+0.017
illi+0.017
yle+0.017
 register+0.016
Neg logit contributions
 hit-0.008
 shoot-0.007
 poked-0.007
 searched-0.007
 fight-0.007
Token who
Token ID508
Feature activation-4.17e-02

Pos logit contributions
 queens+0.051
 register+0.050
yle+0.050
illi+0.050
nam+0.049
Neg logit contributions
 hit-0.026
 poked-0.024
 shoot-0.024
 searched-0.023
 accidentally-0.023
Token said
Token ID531
Feature activation+1.33e-02

Pos logit contributions
 queens+0.100
ities+0.099
reating+0.098
nam+0.098
 register+0.098
Neg logit contributions
 hit-0.038
 searched-0.035
 poked-0.034
 accidentally-0.033
 shoot-0.032
Token he
Token ID339
Feature activation+4.36e-02

Pos logit contributions
 hit+0.014
 shoot+0.013
 accidentally+0.013
 poked+0.013
 searched+0.012
Neg logit contributions
yle-0.028
 queens-0.028
nam-0.028
iley-0.028
 register-0.028
Token.
Token ID13
Feature activation-5.21e-03

Pos logit contributions
 hit+0.016
 shoot+0.015
 accidentally+0.015
 searched+0.015
 Suddenly+0.014
Neg logit contributions
 queens-0.042
nam-0.040
reating-0.040
ities-0.040
 passports-0.039
Token She
Token ID1375
Feature activation-1.53e-02

Pos logit contributions
 queens+0.011
 penn+0.011
 passports+0.011
nam+0.011
reating+0.011
Neg logit contributions
 Suddenly-0.006
 hit-0.005
 accidentally-0.005
Bang-0.005
 shoot-0.005
Token ran
Token ID4966
Feature activation+4.27e-02

Pos logit contributions
 penn+0.032
 queens+0.032
nam+0.031
 register+0.031
iley+0.031
Neg logit contributions
 hit-0.016
Bang-0.015
 shoot-0.015
 poked-0.014
 accidentally-0.014
Token to
Token ID284
Feature activation+4.60e-02

Pos logit contributions
 hit+0.049
 shoot+0.044
 searched+0.044
Bang+0.042
 poked+0.041
Neg logit contributions
nam-0.093
ities-0.093
 queens-0.091
 penn-0.089
yle-0.088
Token the
Token ID262
Feature activation-7.11e-03

Pos logit contributions
 hit+0.068
 shoot+0.064
 poked+0.060
 searched+0.060
 accidentally+0.059
Neg logit contributions
 queens-0.087
ities-0.083
 penn-0.082
 register-0.081
nam-0.081
Token cash
Token ID5003
Feature activation-2.58e-01

Pos logit contributions
 queens+0.013
nam+0.013
 penn+0.013
overs+0.013
ities+0.013
Neg logit contributions
 hit-0.009
 shoot-0.009
Bang-0.009
 searched-0.008
 accidentally-0.008
Tokenier
Token ID959
Feature activation-1.44e-02

Pos logit contributions
nam+0.361
 queens+0.305
 importantly+0.280
 passports+0.278
 diamonds+0.270
Neg logit contributions
 hit-0.484
 replied-0.472
 poked-0.465
 searched-0.458
 accidentally-0.445
Token to
Token ID284
Feature activation+4.69e-02

Pos logit contributions
 queens+0.034
nam+0.033
illi+0.032
ities+0.032
yle+0.032
Neg logit contributions
 hit-0.014
 searched-0.013
 shoot-0.012
 poked-0.012
 accidentally-0.011
Token buy
Token ID2822
Feature activation-1.12e-01

Pos logit contributions
 hit+0.050
 shoot+0.047
 searched+0.043
 poked+0.042
 fight+0.042
Neg logit contributions
 queens-0.106
 penn-0.104
ities-0.102
 register-0.102
nam-0.101
Token the
Token ID262
Feature activation-5.65e-03

Pos logit contributions
 queens+0.262
ities+0.260
ala+0.248
 singers+0.248
 importantly+0.248
Neg logit contributions
 hit-0.108
 saw-0.096
 searched-0.094
 play-0.092
 poked-0.088
Token toy
Token ID13373
Feature activation-2.51e-02

Pos logit contributions
 queens+0.012
nam+0.011
iley+0.011
ities+0.011
overs+0.011
Neg logit contributions
 hit-0.007
 shoot-0.006
Bang-0.006
 poked-0.006
 accidentally-0.006
Token it
Token ID340
Feature activation+7.82e-02

Pos logit contributions
 queens+0.098
 register+0.098
 penn+0.097
overs+0.096
ities+0.095
Neg logit contributions
 hit-0.085
 shoot-0.081
 searched-0.079
 accidentally-0.078
 poked-0.078
Token is
Token ID318
Feature activation-5.97e-04

Pos logit contributions
Bang+0.092
 shoot+0.086
 hit+0.085
 poked+0.082
 searched+0.077
Neg logit contributions
 penn-0.149
 register-0.146
illi-0.146
 queens-0.146
yle-0.142
Token only
Token ID691
Feature activation-1.03e-02

Pos logit contributions
 queens+0.001
nam+0.001
 penn+0.001
 register+0.001
overs+0.001
Neg logit contributions
 hit-0.001
Bang-0.001
 shoot-0.001
 poked-0.001
 searched-0.001
Token for
Token ID329
Feature activation-1.22e-01

Pos logit contributions
yle+0.018
 queens+0.018
iley+0.018
 register+0.018
ums+0.018
Neg logit contributions
 hit-0.015
 shoot-0.015
 poked-0.014
 searched-0.014
 accidentally-0.014
Token special
Token ID2041
Feature activation+1.35e-02

Pos logit contributions
 register+0.209
yle+0.208
nam+0.205
illi+0.202
 queens+0.201
Neg logit contributions
 hit-0.188
 shoot-0.174
 poked-0.172
 accidentally-0.171
 searched-0.168
Token occasions
Token ID12432
Feature activation-2.58e-01

Pos logit contributions
 hit+0.024
 shoot+0.023
 searched+0.023
 poked+0.023
 fight+0.022
Neg logit contributions
nam-0.019
yle-0.019
illi-0.019
 queens-0.019
 register-0.019
Token.
Token ID13
Feature activation+2.24e-03

Pos logit contributions
 queens+0.590
nam+0.579
 penn+0.562
yle+0.550
iley+0.547
Neg logit contributions
 hit-0.228
 searched-0.218
 accidentally-0.209
house-0.208
 shoot-0.198
Tokenâ
Token ID22940
Feature activation+2.60e-02

Pos logit contributions
 hit+0.003
Bang+0.003
 shoot+0.003
 poked+0.003
 searched+0.003
Neg logit contributions
 queens-0.004
nam-0.004
 penn-0.004
 register-0.004
overs-0.004
Token
Token ID26391
Feature activation+1.19e-01

Pos logit contributions
 hit+0.037
 accidentally+0.037
 poked+0.036
 shoot+0.035
Bang+0.034
Neg logit contributions
iley-0.043
 register-0.043
iza-0.043
overs-0.043
illi-0.042
Token She
Token ID1375
Feature activation-9.35e-03

Pos logit contributions
 hit+0.153
Bang+0.147
 shoot+0.145
 poked+0.143
 searched+0.140
Neg logit contributions
 queens-0.220
overs-0.216
nam-0.215
 penn-0.213
yle-0.213
Token wink
Token ID41955
Feature activation+4.79e-02

Pos logit contributions
 penn+0.018
 register+0.018
 queens+0.018
iley+0.018
illi+0.018
Neg logit contributions
Bang-0.011
 hit-0.011
 shoot-0.010
 poked-0.010
 searched-0.010
TokenThe
Token ID464
Feature activation-1.22e-02

Pos logit contributions
 hit+0.028
Bang+0.027
 shoot+0.026
 poked+0.026
 accidentally+0.025
Neg logit contributions
 queens-0.040
nam-0.040
 penn-0.040
 register-0.040
overs-0.039
Token little
Token ID1310
Feature activation+4.20e-02

Pos logit contributions
ions+0.019
overs+0.018
reating+0.018
 Debbie+0.018
ala+0.018
Neg logit contributions
 hit-0.022
 shoot-0.020
 quarrel-0.020
 fight-0.020
 saw-0.019
Token boy
Token ID2933
Feature activation+1.78e-02

Pos logit contributions
 hit+0.064
 saw+0.056
 shoot+0.055
 poked+0.055
 fight+0.054
Neg logit contributions
reating-0.080
lessness-0.079
 importantly-0.078
ions-0.077
illi-0.076
Token thanked
Token ID26280
Feature activation-5.20e-02

Pos logit contributions
Bang+0.020
 hit+0.018
 shoot+0.018
 poked+0.017
 snowball+0.017
Neg logit contributions
 penn-0.035
iley-0.035
 register-0.034
yle-0.034
 queens-0.034
Token the
Token ID262
Feature activation-4.50e-03

Pos logit contributions
 cents+0.113
 register+0.113
ities+0.112
 queens+0.112
 dollars+0.112
Neg logit contributions
 hit-0.059
 shoot-0.056
 play-0.048
 fight-0.048
 searched-0.047
Token cash
Token ID5003
Feature activation-2.58e-01

Pos logit contributions
ions+0.007
iley+0.006
overs+0.006
nam+0.006
 queens+0.006
Neg logit contributions
 hit-0.008
 shoot-0.008
 fight-0.008
 quarrel-0.008
Bang-0.007
Tokenier
Token ID959
Feature activation-1.17e-02

Pos logit contributions
nam+0.379
 Clare+0.319
 queens+0.307
 Debbie+0.306
 hotels+0.304
Neg logit contributions
 hit-0.474
 replied-0.447
 poked-0.439
 searched-0.421
 fixed-0.416
Token and
Token ID290
Feature activation+5.88e-03

Pos logit contributions
 queens+0.031
nam+0.031
illi+0.030
yle+0.030
iza+0.029
Neg logit contributions
 hit-0.007
 shoot-0.006
 searched-0.006
 fight-0.005
 replied-0.005
Token went
Token ID1816
Feature activation+2.35e-02

Pos logit contributions
 hit+0.005
 searched+0.005
 poked+0.005
 shoot+0.005
 accidentally+0.004
Neg logit contributions
ities-0.014
 queens-0.014
overs-0.014
illi-0.014
reating-0.014
Token home
Token ID1363
Feature activation-2.17e-02

Pos logit contributions
 hit+0.027
 searched+0.025
 shoot+0.024
 play+0.022
 poked+0.022
Neg logit contributions
nam-0.052
ities-0.052
 queens-0.051
yle-0.049
iley-0.049
Token happy
Token ID3772
Feature activation+7.59e-02

Pos logit contributions
iley+0.046
ities+0.046
 queens+0.046
reating+0.045
yle+0.044
Neg logit contributions
 hit-0.025
 searched-0.023
 shoot-0.022
 accidentally-0.022
 fight-0.021
Tokenier
Token ID959
Feature activation-1.13e-02

Pos logit contributions
nam+0.345
 queens+0.267
 Clare+0.267
 importantly+0.264
iley+0.251
Neg logit contributions
 hit-0.501
 searched-0.487
 replied-0.484
 poked-0.480
 accidentally-0.472
Token to
Token ID284
Feature activation+4.83e-02

Pos logit contributions
 queens+0.026
nam+0.026
illi+0.025
yle+0.025
 penn+0.025
Neg logit contributions
 hit-0.011
 searched-0.010
 poked-0.010
 shoot-0.010
 accidentally-0.009
Token pay
Token ID1414
Feature activation-1.37e-01

Pos logit contributions
 hit+0.053
 shoot+0.050
 searched+0.046
 poked+0.046
 accidentally+0.045
Neg logit contributions
 queens-0.105
 penn-0.103
iley-0.102
yle-0.101
ities-0.101
Token.
Token ID13
Feature activation+2.19e-03

Pos logit contributions
 queens+0.284
yle+0.271
ala+0.271
iley+0.269
 importantly+0.266
Neg logit contributions
 hit-0.170
 shoot-0.146
 poked-0.145
 searched-0.144
 saw-0.141
Token The
Token ID383
Feature activation+6.94e-04

Pos logit contributions
 hit+0.002
Bang+0.002
 shoot+0.002
 searched+0.002
 poked+0.002
Neg logit contributions
 queens-0.005
 penn-0.005
nam-0.005
 register-0.005
yle-0.005
Token cash
Token ID5003
Feature activation-2.58e-01

Pos logit contributions
 hit+0.001
 quarrel+0.001
 saw+0.001
 fight+0.001
 accidentally+0.001
Neg logit contributions
ions-0.001
ala-0.001
iley-0.001
reating-0.001
yle-0.001
Tokenier
Token ID959
Feature activation-1.10e-02

Pos logit contributions
nam+0.376
reating+0.304
 Clare+0.301
 queens+0.296
iley+0.292
Neg logit contributions
 hit-0.507
 poked-0.494
 searched-0.492
 replied-0.486
 saw-0.483
Token was
Token ID373
Feature activation+2.13e-02

Pos logit contributions
nam+0.024
 queens+0.024
 penn+0.024
 register+0.023
yle+0.023
Neg logit contributions
 hit-0.011
 searched-0.010
 poked-0.010
 shoot-0.010
 accidentally-0.010
Token very
Token ID845
Feature activation+5.87e-03

Pos logit contributions
 hit+0.029
 searched+0.026
 poked+0.026
 shoot+0.026
 accidentally+0.026
Neg logit contributions
 queens-0.041
yle-0.040
iley-0.040
 penn-0.039
ities-0.039
Token nice
Token ID3621
Feature activation+3.20e-02

Pos logit contributions
 hit+0.008
 shoot+0.007
 poked+0.007
 accidentally+0.007
 searched+0.007
Neg logit contributions
 queens-0.011
reating-0.011
ities-0.011
yle-0.011
iley-0.011
Token and
Token ID290
Feature activation+6.15e-03

Pos logit contributions
 hit+0.020
 searched+0.017
 accidentally+0.017
 poked+0.016
 fight+0.016
Neg logit contributions
nam-0.089
illi-0.084
yle-0.083
 queens-0.082
iza-0.081
TokenOnce
Token ID7454
Feature activation-8.84e-02

Pos logit contributions
 hit+0.024
 shoot+0.022
Bang+0.022
 poked+0.022
 searched+0.021
Neg logit contributions
 queens-0.041
 penn-0.040
 register-0.040
nam-0.040
overs-0.040
Token upon
Token ID2402
Feature activation+1.23e-02

Pos logit contributions
 queens+0.153
 penn+0.150
nam+0.150
 register+0.149
overs+0.147
Neg logit contributions
 hit-0.128
Bang-0.120
 shoot-0.120
 poked-0.119
 searched-0.118
Token a
Token ID257
Feature activation+2.10e-02

Pos logit contributions
 hit+0.020
Bang+0.019
 shoot+0.019
 poked+0.018
 searched+0.018
Neg logit contributions
 queens-0.019
nam-0.019
illi-0.018
iley-0.018
 Clare-0.018
Token time
Token ID640
Feature activation-9.42e-03

Pos logit contributions
 hit+0.035
 shoot+0.035
Bang+0.034
 poked+0.033
 accidentally+0.032
Neg logit contributions
iley-0.032
oll-0.028
illi-0.028
 importantly-0.028
 Clare-0.028
Token,
Token ID11
Feature activation-2.03e-02

Pos logit contributions
 queens+0.018
 penn+0.018
nam+0.017
yle+0.017
iley+0.017
Neg logit contributions
 hit-0.012
Bang-0.011
 shoot-0.011
 poked-0.011
 searched-0.011
Token there
Token ID612
Feature activation+9.63e-02

Pos logit contributions
nam+0.020
illi+0.019
yle+0.018
overs+0.018
 importantly+0.018
Neg logit contributions
 hit-0.041
 shoot-0.040
Bang-0.040
 fight-0.040
 quarrel-0.039
Token were
Token ID547
Feature activation-5.49e-02

Pos logit contributions
Bang+0.107
 hit+0.106
 shoot+0.104
 poked+0.098
 searched+0.093
Neg logit contributions
yle-0.184
illi-0.184
 penn-0.180
iley-0.178
overs-0.178
Token two
Token ID734
Feature activation-2.71e-02

Pos logit contributions
 queens+0.071
 penn+0.069
nam+0.067
 register+0.066
overs+0.066
Neg logit contributions
 hit-0.105
 shoot-0.101
Bang-0.100
 poked-0.099
 searched-0.099
Token friends
Token ID2460
Feature activation-6.77e-02

Pos logit contributions
nam+0.034
 queens+0.033
yle+0.033
reating+0.033
 register+0.033
Neg logit contributions
 hit-0.053
 poked-0.050
 shoot-0.049
 accidentally-0.049
 searched-0.049
Token,
Token ID11
Feature activation-2.05e-02

Pos logit contributions
 queens+0.139
 penn+0.137
nam+0.137
 register+0.136
overs+0.135
Neg logit contributions
 hit-0.076
Bang-0.072
 shoot-0.070
 poked-0.069
 searched-0.068
Token Anna
Token ID11735
Feature activation-2.92e-02

Pos logit contributions
 penn+0.042
 queens+0.042
 register+0.042
nam+0.041
overs+0.041
Neg logit contributions
 hit-0.024
 shoot-0.022
Bang-0.022
 poked-0.022
 searched-0.022
Token see
Token ID766
Feature activation+1.87e-02

Pos logit contributions
 queens+0.029
 penn+0.028
nam+0.028
 register+0.028
overs+0.028
Neg logit contributions
 hit-0.011
 shoot-0.010
Bang-0.010
 poked-0.010
 searched-0.010
Token a
Token ID257
Feature activation+2.02e-02

Pos logit contributions
 hit+0.024
 shoot+0.022
Bang+0.022
 poked+0.022
 searched+0.022
Neg logit contributions
 queens-0.035
 register-0.035
 penn-0.035
nam-0.035
overs-0.035
Token big
Token ID1263
Feature activation+8.57e-02

Pos logit contributions
 searched+0.026
 hit+0.026
Bang+0.025
 poked+0.025
 shoot+0.024
Neg logit contributions
 queens-0.037
 penn-0.037
nam-0.037
 register-0.036
yle-0.035
Token fly
Token ID6129
Feature activation+5.98e-02

Pos logit contributions
Bang+0.100
 hit+0.100
 poked+0.097
 searched+0.096
 shoot+0.095
Neg logit contributions
 penn-0.165
 queens-0.165
nam-0.162
 register-0.161
overs-0.159
Token buzzing
Token ID41719
Feature activation+7.79e-02

Pos logit contributions
 hit+0.091
Bang+0.091
 poked+0.089
 accidentally+0.088
 searched+0.088
Neg logit contributions
 queens-0.092
overs-0.091
 penn-0.091
 register-0.090
nam-0.089
Token around
Token ID1088
Feature activation+1.27e-01

Pos logit contributions
 accidentally+0.124
 hit+0.123
Bang+0.122
 searched+0.118
 poked+0.118
Neg logit contributions
overs-0.116
 queens-0.116
 penn-0.115
 dancers-0.113
 singers-0.112
Token a
Token ID257
Feature activation+1.99e-02

Pos logit contributions
 hit+0.177
 poked+0.164
 searched+0.163
 shoot+0.163
Bang+0.159
Neg logit contributions
 register-0.237
 penn-0.237
 queens-0.234
nam-0.232
oll-0.227
Token flower
Token ID15061
Feature activation-7.06e-03

Pos logit contributions
 searched+0.024
 poked+0.023
 hit+0.023
Bang+0.023
 shoot+0.022
Neg logit contributions
 queens-0.038
 penn-0.037
nam-0.036
 dancers-0.036
 register-0.036
Token.
Token ID13
Feature activation+4.53e-03

Pos logit contributions
 queens+0.012
nam+0.012
 penn+0.012
 register+0.012
overs+0.012
Neg logit contributions
 hit-0.010
 shoot-0.010
Bang-0.009
 poked-0.009
 searched-0.009
Token Sam
Token ID3409
Feature activation+1.69e-02

Pos logit contributions
 hit+0.007
 shoot+0.007
 fight+0.007
Bang+0.007
 wrecked+0.007
Neg logit contributions
overs-0.006
 Mara-0.006
 N-0.006
ums-0.006
 Clara-0.006
Token wants
Token ID3382
Feature activation+4.48e-02

Pos logit contributions
Bang+0.024
 shoot+0.023
house+0.022
 dam+0.022
 hit+0.022
Neg logit contributions
 penn-0.027
 Clare-0.026
iley-0.026
 dancers-0.026
 Erin-0.025
Token because
Token ID780
Feature activation-7.08e-02

Pos logit contributions
Bang+0.033
 hit+0.033
 shoot+0.032
 poked+0.031
 accidentally+0.031
Neg logit contributions
 penn-0.041
 queens-0.040
nam-0.040
ities-0.040
overs-0.040
Token his
Token ID465
Feature activation-3.35e-02

Pos logit contributions
ities+0.128
 register+0.127
yle+0.126
iley+0.126
 queens+0.125
Neg logit contributions
 hit-0.104
 shoot-0.095
 accidentally-0.094
 searched-0.093
 poked-0.091
Token play
Token ID711
Feature activation+3.98e-02

Pos logit contributions
 penn+0.039
nam+0.037
 queens+0.035
 gifts+0.033
 passports+0.033
Neg logit contributions
Bang-0.070
 shoot-0.066
 searched-0.066
 poked-0.064
 accidentally-0.063
Tokenhouse
Token ID4803
Feature activation-1.74e-02

Pos logit contributions
Bang+0.044
 shoot+0.042
 poked+0.041
 hit+0.040
 accidentally+0.038
Neg logit contributions
overs-0.080
 queens-0.075
 register-0.074
 penn-0.073
iest-0.072
Token was
Token ID373
Feature activation+1.96e-02

Pos logit contributions
 penn+0.031
 queens+0.030
 register+0.030
overs+0.030
nam+0.029
Neg logit contributions
Bang-0.022
 shoot-0.021
 poked-0.020
 hit-0.020
 accidentally-0.019
Token broken
Token ID5445
Feature activation+9.67e-02

Pos logit contributions
Bang+0.029
 shoot+0.026
 poked+0.025
 searched+0.025
 Suddenly+0.024
Neg logit contributions
 queens-0.033
nam-0.033
 penn-0.032
reating-0.031
 register-0.030
Token.
Token ID13
Feature activation+1.56e-03

Pos logit contributions
 hit+0.127
 shoot+0.118
 searched+0.116
Bang+0.115
 poked+0.115
Neg logit contributions
 queens-0.183
nam-0.181
 penn-0.179
 register-0.179
iley-0.176
Token His
Token ID2399
Feature activation-1.16e-03

Pos logit contributions
 hit+0.002
 shoot+0.002
Bang+0.002
 quarrel+0.002
 fight+0.002
Neg logit contributions
ums-0.003
 importantly-0.003
overs-0.002
nam-0.002
 penn-0.002
Token mom
Token ID1995
Feature activation-4.80e-02

Pos logit contributions
 penn+0.001
nam+0.001
 queens+0.001
 passports+0.001
 gifts+0.001
Neg logit contributions
Bang-0.003
 searched-0.002
 shoot-0.002
 poked-0.002
 hit-0.002
Token told
Token ID1297
Feature activation-2.77e-02

Pos logit contributions
 register+0.092
illi+0.088
 queens+0.087
 penn+0.086
iza+0.086
Neg logit contributions
Bang-0.059
 shoot-0.054
 BO-0.049
inated-0.048
 SPL-0.048
Token him
Token ID683
Feature activation+4.27e-02

Pos logit contributions
 queens+0.038
 penn+0.038
reating+0.038
overs+0.037
 register+0.037
Neg logit contributions
Bang-0.047
 hit-0.047
 shoot-0.046
 poked-0.045
 accidentally-0.044
TokenThe
Token ID464
Feature activation-1.23e-02

Pos logit contributions
 hit+0.028
 shoot+0.026
Bang+0.026
 poked+0.026
 searched+0.026
Neg logit contributions
 queens-0.038
 penn-0.037
nam-0.037
 register-0.037
overs-0.036
Token little
Token ID1310
Feature activation+4.32e-02

Pos logit contributions
 queens+0.021
 penn+0.021
nam+0.021
 register+0.021
overs+0.021
Neg logit contributions
 hit-0.018
Bang-0.017
 shoot-0.017
 poked-0.017
 searched-0.016
Token girl
Token ID2576
Feature activation-1.73e-02

Pos logit contributions
 hit+0.063
 poked+0.059
 saw+0.058
 searched+0.057
 quarrel+0.056
Neg logit contributions
reating-0.078
ities-0.078
 queens-0.076
illi-0.076
ates-0.075
Token and
Token ID290
Feature activation+6.11e-03

Pos logit contributions
 penn+0.034
 queens+0.034
 register+0.034
iley+0.033
yle+0.033
Neg logit contributions
 hit-0.019
Bang-0.019
 shoot-0.018
 poked-0.018
 accidentally-0.017
Token the
Token ID262
Feature activation-6.54e-03

Pos logit contributions
 hit+0.008
 poked+0.007
 shoot+0.007
 searched+0.007
 accidentally+0.007
Neg logit contributions
 register-0.013
 queens-0.013
oll-0.012
 cents-0.012
ities-0.012
Token grey
Token ID13791
Feature activation+1.65e-01

Pos logit contributions
 queens+0.011
 penn+0.011
nam+0.011
 register+0.011
overs+0.011
Neg logit contributions
 hit-0.010
Bang-0.009
 shoot-0.009
 poked-0.009
 searched-0.009
Token goose
Token ID37246
Feature activation+7.01e-02

Pos logit contributions
 hit+0.251
Bang+0.243
 shoot+0.240
 poked+0.235
 searched+0.234
Neg logit contributions
 queens-0.269
 penn-0.267
nam-0.265
 register-0.264
overs-0.263
Token watched
Token ID7342
Feature activation-3.74e-02

Pos logit contributions
Bang+0.084
 hit+0.083
 shoot+0.079
 poked+0.077
 accidentally+0.077
Neg logit contributions
 penn-0.132
 queens-0.132
 register-0.129
nam-0.128
yle-0.127
Token the
Token ID262
Feature activation-6.77e-03

Pos logit contributions
 queens+0.066
 register+0.065
nam+0.064
 penn+0.063
illi+0.062
Neg logit contributions
 hit-0.055
 shoot-0.053
 poked-0.051
 searched-0.051
Bang-0.050
Token paper
Token ID3348
Feature activation-5.18e-02

Pos logit contributions
 queens+0.011
 penn+0.011
nam+0.011
 register+0.011
overs+0.010
Neg logit contributions
 hit-0.011
Bang-0.010
 shoot-0.010
 searched-0.010
 poked-0.010
Token shapes
Token ID15268
Feature activation-7.50e-02

Pos logit contributions
 queens+0.099
 penn+0.097
nam+0.097
 register+0.096
overs+0.095
Neg logit contributions
 hit-0.065
Bang-0.062
 shoot-0.060
 poked-0.060
 searched-0.059
Token street
Token ID4675
Feature activation-3.50e-04

Pos logit contributions
 queens+0.105
nam+0.103
 penn+0.103
 register+0.102
overs+0.101
Neg logit contributions
 hit-0.052
 poked-0.047
 shoot-0.047
 searched-0.046
Bang-0.046
Token.
Token ID13
Feature activation+4.00e-03

Pos logit contributions
 queens+0.001
 penn+0.001
nam+0.001
 register+0.001
yle+0.001
Neg logit contributions
 hit-0.000
 searched-0.000
 shoot-0.000
 poked-0.000
 accidentally-0.000
Token As
Token ID1081
Feature activation-5.26e-02

Pos logit contributions
 hit+0.007
 shoot+0.006
Bang+0.006
 poked+0.006
 fight+0.006
Neg logit contributions
 Clare-0.006
 Erin-0.006
overs-0.006
nam-0.006
 Debbie-0.006
Token she
Token ID673
Feature activation+9.70e-03

Pos logit contributions
ities+0.095
 cents+0.086
ums+0.086
 dollars+0.086
asers+0.085
Neg logit contributions
 hit-0.089
 accidentally-0.089
 saw-0.082
 poked-0.079
 play-0.079
Token was
Token ID373
Feature activation+2.19e-02

Pos logit contributions
Bang+0.013
 shoot+0.012
 fight+0.010
 hit+0.010
 quarrel+0.010
Neg logit contributions
 penn-0.018
illi-0.018
yle-0.017
iza-0.017
iley-0.017
Token walking
Token ID6155
Feature activation+1.26e-01

Pos logit contributions
Bang+0.040
 shoot+0.036
 hit+0.035
 poked+0.034
 searched+0.033
Neg logit contributions
 dancers-0.030
 penn-0.030
 Clare-0.030
iley-0.030
 register-0.030
Token,
Token ID11
Feature activation-2.23e-02

Pos logit contributions
 hit+0.142
 shoot+0.131
Bang+0.131
 poked+0.129
 searched+0.129
Neg logit contributions
 queens-0.261
nam-0.258
 penn-0.257
 register-0.256
yle-0.253
Token she
Token ID673
Feature activation+9.75e-03

Pos logit contributions
 queens+0.026
 penn+0.025
 register+0.025
ities+0.025
reating+0.025
Neg logit contributions
 hit-0.046
 accidentally-0.044
 poked-0.044
 searched-0.044
 shoot-0.043
Token saw
Token ID2497
Feature activation+5.53e-02

Pos logit contributions
Bang+0.008
 shoot+0.008
 fight+0.007
 snowball+0.007
 quarrel+0.007
Neg logit contributions
iza-0.022
 queens-0.021
iley-0.021
la-0.021
yle-0.021
Token a
Token ID257
Feature activation+1.99e-02

Pos logit contributions
 hit+0.072
Bang+0.067
 shoot+0.067
 poked+0.067
 searched+0.066
Neg logit contributions
 queens-0.104
 penn-0.103
nam-0.102
 register-0.102
overs-0.101
Token big
Token ID1263
Feature activation+8.75e-02

Pos logit contributions
 hit+0.026
Bang+0.025
 searched+0.025
 poked+0.024
 shoot+0.024
Neg logit contributions
 queens-0.037
nam-0.036
 penn-0.036
 register-0.036
yle-0.035
Token They
Token ID1119
Feature activation-1.00e-02

Pos logit contributions
 hit+0.007
Bang+0.007
 shoot+0.007
 poked+0.006
 searched+0.006
Neg logit contributions
 queens-0.010
 penn-0.010
nam-0.010
 register-0.010
yle-0.010
Token are
Token ID389
Feature activation-8.53e-02

Pos logit contributions
 queens+0.016
 penn+0.016
nam+0.016
 register+0.016
overs+0.016
Neg logit contributions
 hit-0.015
Bang-0.014
 shoot-0.014
 poked-0.014
 searched-0.014
Token made
Token ID925
Feature activation-5.17e-02

Pos logit contributions
yle+0.176
 register+0.174
 queens+0.172
reating+0.169
illi+0.167
Neg logit contributions
 hit-0.110
 shoot-0.100
 poked-0.097
 accidentally-0.097
 searched-0.092
Token of
Token ID286
Feature activation-8.72e-02

Pos logit contributions
nam+0.070
 queens+0.069
 penn+0.067
 register+0.067
yle+0.066
Neg logit contributions
 hit-0.098
 shoot-0.094
 poked-0.092
Bang-0.091
 searched-0.090
Token snow
Token ID6729
Feature activation+1.90e-02

Pos logit contributions
 register+0.192
 queens+0.189
yle+0.187
illi+0.187
nam+0.186
Neg logit contributions
 hit-0.096
 shoot-0.087
 poked-0.084
 snowball-0.081
Bang-0.080
Token,
Token ID11
Feature activation-2.26e-02

Pos logit contributions
 hit+0.031
 shoot+0.029
 searched+0.029
 poked+0.029
Bang+0.029
Neg logit contributions
nam-0.030
 queens-0.030
 penn-0.029
 register-0.029
yle-0.029
Token and
Token ID290
Feature activation+9.85e-03

Pos logit contributions
 queens+0.044
 penn+0.043
nam+0.043
overs+0.042
 register+0.042
Neg logit contributions
 hit-0.028
Bang-0.026
 shoot-0.026
 poked-0.026
 searched-0.026
Token snow
Token ID6729
Feature activation+1.96e-02

Pos logit contributions
 hit+0.014
 shoot+0.014
 poked+0.013
 searched+0.013
Bang+0.013
Neg logit contributions
 register-0.018
yle-0.017
illi-0.017
 queens-0.017
nam-0.017
Token melts
Token ID48813
Feature activation+2.23e-02

Pos logit contributions
 hit+0.033
 shoot+0.032
 poked+0.031
Bang+0.031
 searched+0.031
Neg logit contributions
nam-0.029
 queens-0.029
 penn-0.028
 register-0.028
yle-0.028
Token when
Token ID618
Feature activation-9.70e-02

Pos logit contributions
 hit+0.028
 shoot+0.026
 poked+0.026
Bang+0.025
 searched+0.025
Neg logit contributions
 queens-0.043
 register-0.043
nam-0.043
yle-0.042
 penn-0.042
Token it
Token ID340
Feature activation+8.68e-02

Pos logit contributions
 register+0.157
nam+0.156
yle+0.155
 queens+0.153
illi+0.152
Neg logit contributions
 hit-0.158
 accidentally-0.148
 shoot-0.148
 poked-0.144
 searched-0.140
Token away
Token ID1497
Feature activation+2.49e-02

Pos logit contributions
 hit+0.074
 shoot+0.069
 poked+0.067
 searched+0.067
Bang+0.067
Neg logit contributions
 queens-0.106
 register-0.104
nam-0.104
 penn-0.103
iley-0.102
Token.
Token ID13
Feature activation-3.54e-03

Pos logit contributions
 hit+0.027
 shoot+0.025
 searched+0.022
 accidentally+0.022
 poked+0.022
Neg logit contributions
iley-0.053
nam-0.053
illi-0.053
asers-0.053
 register-0.053
Token Emma
Token ID18966
Feature activation-3.68e-03

Pos logit contributions
nam+0.006
 queens+0.006
 penn+0.006
 register+0.006
overs+0.006
Neg logit contributions
 hit-0.005
 shoot-0.005
Bang-0.005
 poked-0.005
 searched-0.004
Token thought
Token ID1807
Feature activation+3.24e-02

Pos logit contributions
 penn+0.007
iley+0.007
yle+0.007
iza+0.007
 Erin+0.007
Neg logit contributions
Bang-0.004
 shoot-0.004
 hit-0.004
 BO-0.004
 fight-0.004
Token it
Token ID340
Feature activation+8.36e-02

Pos logit contributions
 hit+0.042
 shoot+0.040
 searched+0.039
 accidentally+0.039
 poked+0.038
Neg logit contributions
 queens-0.066
nam-0.064
 register-0.061
ities-0.061
overs-0.060
Token was
Token ID373
Feature activation+2.20e-02

Pos logit contributions
Bang+0.109
 hit+0.103
 shoot+0.102
 BO+0.098
 dam+0.097
Neg logit contributions
 Erin-0.135
la-0.132
illi-0.131
iest-0.131
 penn-0.130
Token fun
Token ID1257
Feature activation+4.82e-02

Pos logit contributions
 hit+0.031
Bang+0.030
 shoot+0.029
 poked+0.029
 searched+0.029
Neg logit contributions
 queens-0.039
nam-0.038
 penn-0.038
 register-0.038
overs-0.037
Token and
Token ID290
Feature activation+5.99e-03

Pos logit contributions
 hit+0.044
 searched+0.040
 shoot+0.039
 poked+0.039
 accidentally+0.038
Neg logit contributions
nam-0.117
 queens-0.113
 register-0.112
illi-0.110
ities-0.109
Token could
Token ID714
Feature activation+4.93e-02

Pos logit contributions
 hit+0.009
Bang+0.009
 shoot+0.009
 poked+0.008
 searched+0.008
Neg logit contributions
 queens-0.010
 penn-0.010
nam-0.010
 register-0.010
overs-0.010
Token not
Token ID407
Feature activation-2.43e-02

Pos logit contributions
Bang+0.059
 accidentally+0.053
 searched+0.052
 poked+0.052
 hit+0.051
Neg logit contributions
 queens-0.090
 Clare-0.090
 penn-0.089
 Erin-0.089
nam-0.089
Token wait
Token ID4043
Feature activation-5.65e-02

Pos logit contributions
 queens+0.046
 penn+0.046
yle+0.046
nam+0.045
 register+0.045
Neg logit contributions
Bang-0.028
 searched-0.025
 accidentally-0.025
 hit-0.025
 poked-0.025
TokenThe
Token ID464
Feature activation-6.89e-03

Pos logit contributions
 hit+0.029
Bang+0.026
 shoot+0.025
 poked+0.025
 accidentally+0.024
Neg logit contributions
ities-0.041
 queens-0.041
nam-0.040
 register-0.040
reating-0.040
Token lady
Token ID10846
Feature activation-4.88e-02

Pos logit contributions
ities+0.010
iley+0.009
nam+0.009
yle+0.009
overs+0.009
Neg logit contributions
 hit-0.013
 shoot-0.012
 poked-0.012
 quarrel-0.011
 fight-0.011
Token smiles
Token ID21845
Feature activation+5.50e-02

Pos logit contributions
 queens+0.091
 penn+0.091
 register+0.090
illi+0.089
 dancers+0.088
Neg logit contributions
Bang-0.060
 hit-0.059
 shoot-0.058
 accidentally-0.057
 poked-0.055
Token and
Token ID290
Feature activation+9.38e-03

Pos logit contributions
Bang+0.076
 hit+0.074
 shoot+0.074
 accidentally+0.073
 poked+0.071
Neg logit contributions
 dancers-0.094
 queens-0.093
 singers-0.092
 register-0.092
ities-0.091
Token says
Token ID1139
Feature activation-3.48e-03

Pos logit contributions
 hit+0.011
 shoot+0.010
Bang+0.010
 poked+0.010
 searched+0.010
Neg logit contributions
 queens-0.019
nam-0.019
 penn-0.018
 register-0.018
overs-0.018
Token hello
Token ID23748
Feature activation+7.07e-02

Pos logit contributions
 queens+0.008
nam+0.008
ities+0.008
 register+0.008
overs+0.008
Neg logit contributions
 hit-0.003
 shoot-0.003
 poked-0.003
 accidentally-0.003
 searched-0.003
Token back
Token ID736
Feature activation+6.97e-02

Pos logit contributions
 hit+0.081
 poked+0.075
 shoot+0.074
 searched+0.074
Bang+0.070
Neg logit contributions
nam-0.145
 penn-0.143
 queens-0.142
 register-0.141
yle-0.139
Token.
Token ID13
Feature activation-2.36e-03

Pos logit contributions
 hit+0.072
 shoot+0.064
 poked+0.063
 searched+0.062
house+0.062
Neg logit contributions
nam-0.151
 queens-0.148
 penn-0.147
ities-0.147
 register-0.146
Token She
Token ID1375
Feature activation-5.31e-03

Pos logit contributions
 queens+0.003
nam+0.003
 penn+0.003
 register+0.003
overs+0.003
Neg logit contributions
 hit-0.004
Bang-0.004
 shoot-0.004
 poked-0.004
 searched-0.004
Token asks
Token ID7893
Feature activation+1.93e-03

Pos logit contributions
 queens+0.010
 penn+0.010
 register+0.010
nam+0.010
yle+0.010
Neg logit contributions
 hit-0.006
Bang-0.006
 shoot-0.006
 poked-0.006
 searched-0.006
Token Sara
Token ID24799
Feature activation-4.95e-02

Pos logit contributions
 saw+0.003
 hit+0.003
 One+0.003
 poked+0.003
 Suddenly+0.003
Neg logit contributions
 queens-0.003
 importantly-0.003
nam-0.003
ities-0.003
umm-0.003
Token years
Token ID812
Feature activation-9.77e-02

Pos logit contributions
 Erin+0.002
 register+0.002
reating+0.002
 Clare+0.002
nam+0.002
Neg logit contributions
 hit-0.003
 poked-0.003
 searched-0.003
 snowball-0.003
house-0.003
Token old
Token ID1468
Feature activation+1.06e-01

Pos logit contributions
nam+0.174
 queens+0.174
 register+0.171
ities+0.170
yle+0.170
Neg logit contributions
 hit-0.136
 shoot-0.125
 poked-0.124
 searched-0.122
Bang-0.122
Token.
Token ID13
Feature activation+7.58e-03

Pos logit contributions
 hit+0.072
 poked+0.059
 searched+0.057
 accidentally+0.056
 saw+0.055
Neg logit contributions
iza-0.269
 queens-0.269
overs-0.268
illi-0.265
 Clare-0.264
Token One
Token ID1881
Feature activation-4.39e-03

Pos logit contributions
 hit+0.010
 accidentally+0.010
 shoot+0.010
 poked+0.010
Bang+0.009
Neg logit contributions
ums-0.013
ities-0.012
overs-0.012
 queens-0.012
iley-0.012
Token day
Token ID1110
Feature activation+2.22e-02

Pos logit contributions
overs+0.005
iza+0.005
iley+0.005
 queens+0.005
illi+0.005
Neg logit contributions
Bang-0.008
 hit-0.008
 shoot-0.008
 searched-0.008
 accidentally-0.008
Token,
Token ID11
Feature activation-2.32e-02

Pos logit contributions
 hit+0.027
Bang+0.027
 searched+0.026
 shoot+0.026
 poked+0.025
Neg logit contributions
 queens-0.041
nam-0.040
 penn-0.040
overs-0.039
iley-0.039
Token he
Token ID339
Feature activation+4.73e-02

Pos logit contributions
nam+0.035
 queens+0.035
overs+0.033
 penn+0.032
 dancers+0.032
Neg logit contributions
 hit-0.036
Bang-0.035
 searched-0.035
 shoot-0.034
 poked-0.034
Token wanted
Token ID2227
Feature activation+6.21e-02

Pos logit contributions
 BO+0.060
Bang+0.059
 shoot+0.057
inated+0.056
 snowball+0.055
Neg logit contributions
iza-0.080
iley-0.075
uka-0.074
 dancers-0.073
yle-0.073
Token to
Token ID284
Feature activation+4.84e-02

Pos logit contributions
 hit+0.070
Bang+0.065
 shoot+0.065
 poked+0.064
 searched+0.063
Neg logit contributions
 queens-0.128
 penn-0.127
nam-0.126
 register-0.125
overs-0.124
Token play
Token ID711
Feature activation+3.97e-02

Pos logit contributions
Bang+0.051
 searched+0.046
 hit+0.046
 accidentally+0.045
 poked+0.045
Neg logit contributions
nam-0.098
 queens-0.097
 penn-0.097
 Erin-0.097
yle-0.096
Token outside
Token ID2354
Feature activation+7.58e-02

Pos logit contributions
Bang+0.071
 accidentally+0.064
 hit+0.063
 poked+0.062
 searched+0.061
Neg logit contributions
 dancers-0.053
 penn-0.052
 queens-0.052
 singers-0.051
overs-0.051
Token seen
Token ID1775
Feature activation+4.29e-02

Pos logit contributions
 queens+0.018
nam+0.018
 penn+0.018
 register+0.018
overs+0.018
Neg logit contributions
 hit-0.014
Bang-0.013
 shoot-0.013
 poked-0.013
 searched-0.013
Token again
Token ID757
Feature activation+4.98e-02

Pos logit contributions
 hit+0.041
 shoot+0.036
 poked+0.035
 accidentally+0.035
 searched+0.035
Neg logit contributions
nam-0.098
 penn-0.097
 queens-0.097
 register-0.096
illi-0.095
Token!
Token ID0
Feature activation+2.17e-02

Pos logit contributions
 hit+0.064
 shoot+0.060
 poked+0.058
 accidentally+0.057
 searched+0.057
Neg logit contributions
nam-0.098
 queens-0.096
illi-0.096
 penn-0.096
 register-0.096
Token<|endoftext|>
Token ID50256
Feature activation+2.65e-02

Pos logit contributions
 hit+0.015
Bang+0.014
 shoot+0.013
 searched+0.013
 accidentally+0.013
Neg logit contributions
 queens-0.054
 penn-0.054
nam-0.054
 register-0.053
 singers-0.053
TokenSam
Token ID16305
Feature activation+8.11e-04

Pos logit contributions
 hit+0.026
Bang+0.024
 shoot+0.024
 poked+0.023
 searched+0.023
Neg logit contributions
 queens-0.058
nam-0.058
 penn-0.058
 register-0.057
overs-0.056
Token was
Token ID373
Feature activation+2.44e-02

Pos logit contributions
 shoot+0.001
Bang+0.001
 hit+0.001
 poked+0.001
 fight+0.001
Neg logit contributions
iley-0.001
 register-0.001
illi-0.001
iza-0.001
 Erin-0.001
Token a
Token ID257
Feature activation+2.19e-02

Pos logit contributions
Bang+0.037
 hit+0.036
 shoot+0.036
 poked+0.034
 searched+0.034
Neg logit contributions
overs-0.039
nam-0.039
 penn-0.038
 register-0.038
illi-0.038
Token three
Token ID1115
Feature activation-1.96e-04

Pos logit contributions
 hit+0.031
Bang+0.031
 poked+0.030
 shoot+0.030
 searched+0.030
Neg logit contributions
 queens-0.037
nam-0.037
 penn-0.036
iley-0.036
 Clare-0.036
Token year
Token ID614
Feature activation-7.28e-02

Pos logit contributions
reating+0.000
nam+0.000
 register+0.000
 queens+0.000
 Erin+0.000
Neg logit contributions
 hit-0.000
 poked-0.000
 searched-0.000
 shoot-0.000
 accidentally-0.000
Token old
Token ID1468
Feature activation+1.06e-01

Pos logit contributions
 queens+0.111
 penn+0.109
nam+0.109
 register+0.108
overs+0.107
Neg logit contributions
 hit-0.121
Bang-0.120
 shoot-0.117
 poked-0.116
 searched-0.114
Token boy
Token ID2933
Feature activation+2.22e-02

Pos logit contributions
 hit+0.138
 accidentally+0.129
 poked+0.126
 saw+0.124
 searched+0.123
Neg logit contributions
reating-0.196
 queens-0.195
anges-0.195
illi-0.194
ities-0.193
Token they
Token ID484
Feature activation-8.43e-03

Pos logit contributions
ities+0.121
ums+0.114
asers+0.113
oll+0.111
iv+0.110
Neg logit contributions
 hit-0.072
 accidentally-0.069
 shoot-0.061
 saw-0.059
 finally-0.059
Token walked
Token ID6807
Feature activation+5.49e-02

Pos logit contributions
 queens+0.020
 penn+0.019
overs+0.019
nam+0.019
 register+0.019
Neg logit contributions
 hit-0.007
 searched-0.007
 poked-0.006
 shoot-0.006
Bang-0.006
Token,
Token ID11
Feature activation-2.29e-02

Pos logit contributions
 hit+0.066
Bang+0.062
 shoot+0.062
 poked+0.061
 accidentally+0.059
Neg logit contributions
 queens-0.108
 penn-0.107
 register-0.107
nam-0.106
overs-0.105
Token Tommy
Token ID19919
Feature activation-1.70e-02

Pos logit contributions
 queens+0.043
ities+0.042
asers+0.041
iley+0.041
oll+0.040
Neg logit contributions
 hit-0.034
 accidentally-0.034
 shoot-0.030
 Suddenly-0.030
 poked-0.030
Token noticed
Token ID6810
Feature activation+6.76e-02

Pos logit contributions
 register+0.037
 Erin+0.037
la+0.037
yle+0.037
 Clare+0.037
Neg logit contributions
Bang-0.016
 shoot-0.014
 snowball-0.013
 hit-0.012
 BO-0.012
Token something
Token ID1223
Feature activation-9.12e-02

Pos logit contributions
 hit+0.093
 shoot+0.087
 poked+0.086
 searched+0.086
 accidentally+0.085
Neg logit contributions
 queens-0.124
 register-0.121
overs-0.121
 penn-0.120
nam-0.120
Token strange
Token ID6283
Feature activation+9.46e-02

Pos logit contributions
 queens+0.180
nam+0.174
overs+0.174
 register+0.174
 penn+0.173
Neg logit contributions
 hit-0.116
 shoot-0.109
 poked-0.107
 searched-0.104
Bang-0.103
Token in
Token ID287
Feature activation+2.40e-02

Pos logit contributions
 hit+0.142
Bang+0.136
 shoot+0.135
 poked+0.133
 searched+0.132
Neg logit contributions
 queens-0.157
 penn-0.154
nam-0.154
 register-0.153
overs-0.151
Token the
Token ID262
Feature activation-5.49e-03

Pos logit contributions
 hit+0.027
 shoot+0.024
Bang+0.021
 fight+0.021
 snowball+0.021
Neg logit contributions
oll-0.058
ums-0.057
asers-0.056
 register-0.055
ancer-0.055
Token road
Token ID2975
Feature activation-1.29e-02

Pos logit contributions
 queens+0.012
iley+0.012
yle+0.012
ities+0.012
asers+0.012
Neg logit contributions
 hit-0.006
 searched-0.005
 shoot-0.005
 play-0.005
house-0.005
Token.
Token ID13
Feature activation+8.79e-04

Pos logit contributions
 queens+0.025
 penn+0.025
nam+0.025
iley+0.025
 Clare+0.024
Neg logit contributions
 hit-0.017
 shoot-0.016
 searched-0.015
 poked-0.015
 accidentally-0.015
Token they
Token ID484
Feature activation-6.41e-03

Pos logit contributions
ities+0.051
 register+0.051
oll+0.050
 cents+0.049
ums+0.049
Neg logit contributions
 accidentally-0.027
 hit-0.025
house-0.025
 Suddenly-0.025
 searched-0.024
Token knew
Token ID2993
Feature activation-1.97e-02

Pos logit contributions
 queens+0.013
nam+0.013
 penn+0.013
 register+0.013
overs+0.013
Neg logit contributions
 hit-0.007
 shoot-0.006
Bang-0.006
 poked-0.006
 searched-0.006
Token they
Token ID484
Feature activation-6.08e-03

Pos logit contributions
overs+0.044
 register+0.043
ities+0.043
 queens+0.042
 cents+0.041
Neg logit contributions
 hit-0.021
 accidentally-0.020
 play-0.018
 shoot-0.018
 poked-0.018
Token could
Token ID714
Feature activation+4.72e-02

Pos logit contributions
 queens+0.013
 penn+0.013
nam+0.013
 register+0.013
overs+0.013
Neg logit contributions
 hit-0.006
Bang-0.005
 shoot-0.005
 poked-0.005
 searched-0.005
Token trust
Token ID3774
Feature activation-6.19e-02

Pos logit contributions
Bang+0.061
 hit+0.059
 poked+0.057
 searched+0.056
 shoot+0.056
Neg logit contributions
 penn-0.085
 queens-0.085
 register-0.083
nam-0.083
illi-0.082
Token each
Token ID1123
Feature activation-3.65e-02

Pos logit contributions
 register+0.125
 queens+0.123
oll+0.117
reating+0.114
 cents+0.112
Neg logit contributions
 hit-0.079
 play-0.075
 poked-0.074
 shoot-0.073
 quarrel-0.073
Token other
Token ID584
Feature activation-6.95e-02

Pos logit contributions
 queens+0.057
nam+0.057
 penn+0.054
ities+0.054
 Erin+0.054
Neg logit contributions
 hit-0.064
 shoot-0.060
 poked-0.058
Bang-0.058
 accidentally-0.058
Token no
Token ID645
Feature activation-8.62e-02

Pos logit contributions
 queens+0.144
 penn+0.140
nam+0.139
 register+0.139
yle+0.137
Neg logit contributions
 hit-0.078
 shoot-0.074
 searched-0.073
 accidentally-0.069
 poked-0.068
Token matter
Token ID2300
Feature activation-9.42e-02

Pos logit contributions
 queens+0.164
 register+0.164
overs+0.163
nam+0.162
 penn+0.160
Neg logit contributions
 hit-0.114
 shoot-0.105
 poked-0.105
Bang-0.103
 accidentally-0.102
Token what
Token ID644
Feature activation-1.17e-01

Pos logit contributions
 register+0.182
ums+0.180
 queens+0.178
iza+0.177
 cents+0.176
Neg logit contributions
 searched-0.112
 hit-0.111
 accidentally-0.109
 shoot-0.106
 play-0.102
Token.
Token ID13
Feature activation-4.05e-03

Pos logit contributions
 register+0.211
 queens+0.210
reating+0.203
nam+0.202
overs+0.199
Neg logit contributions
 hit-0.172
 accidentally-0.165
 poked-0.160
 shoot-0.159
 quarrel-0.157
Token they
Token ID484
Feature activation-7.67e-03

Pos logit contributions
 hit+0.009
 shoot+0.009
 poked+0.009
 accidentally+0.009
 searched+0.009
Neg logit contributions
ities-0.012
 register-0.012
iley-0.012
 queens-0.012
ums-0.011
Token were
Token ID547
Feature activation-5.25e-02

Pos logit contributions
 queens+0.016
 penn+0.016
 register+0.016
nam+0.016
overs+0.015
Neg logit contributions
 hit-0.009
 shoot-0.008
Bang-0.008
 poked-0.008
 searched-0.008
Token always
Token ID1464
Feature activation-2.91e-02

Pos logit contributions
yle+0.092
iley+0.092
 queens+0.091
 register+0.091
ities+0.091
Neg logit contributions
 hit-0.076
 shoot-0.071
 poked-0.070
 accidentally-0.070
 searched-0.070
Token together
Token ID1978
Feature activation+1.13e-02

Pos logit contributions
 penn+0.052
 queens+0.052
 register+0.051
illi+0.051
yle+0.051
Neg logit contributions
 hit-0.041
 shoot-0.038
 poked-0.038
 searched-0.037
 accidentally-0.037
Token,
Token ID11
Feature activation-2.13e-02

Pos logit contributions
 hit+0.015
 shoot+0.014
 poked+0.013
 searched+0.013
 accidentally+0.013
Neg logit contributions
nam-0.021
 queens-0.021
 register-0.021
 penn-0.021
yle-0.021
Token even
Token ID772
Feature activation-4.46e-02

Pos logit contributions
 register+0.041
 queens+0.041
illi+0.041
 penn+0.040
yle+0.040
Neg logit contributions
 hit-0.027
 shoot-0.026
 searched-0.025
 accidentally-0.025
 poked-0.025
Token when
Token ID618
Feature activation-9.85e-02

Pos logit contributions
ums+0.082
overs+0.081
 register+0.081
illi+0.080
ities+0.079
Neg logit contributions
 hit-0.063
 shoot-0.060
 accidentally-0.060
 poked-0.060
 searched-0.054
Token they
Token ID484
Feature activation-8.15e-03

Pos logit contributions
ities+0.189
oll+0.188
 register+0.184
nam+0.178
ums+0.178
Neg logit contributions
 accidentally-0.130
 hit-0.120
 play-0.114
 shoot-0.113
 poked-0.107
Token were
Token ID547
Feature activation-5.29e-02

Pos logit contributions
 queens+0.016
 penn+0.016
nam+0.016
 register+0.016
yle+0.015
Neg logit contributions
Bang-0.009
 hit-0.009
 shoot-0.009
 poked-0.009
 snowball-0.009
Token apart
Token ID5475
Feature activation-1.70e-02

Pos logit contributions
 queens+0.093
nam+0.091
 penn+0.091
 register+0.090
yle+0.089
Neg logit contributions
 hit-0.077
 shoot-0.071
 poked-0.071
 searched-0.070
 accidentally-0.070
Token.
Token ID13
Feature activation+2.97e-03

Pos logit contributions
nam+0.037
illi+0.036
 queens+0.036
oll+0.036
reating+0.036
Neg logit contributions
 hit-0.018
 accidentally-0.017
 shoot-0.016
 poked-0.016
 searched-0.016
Token.
Token ID13
Feature activation-2.18e-03

Pos logit contributions
 queens+0.102
iley+0.101
nam+0.099
illi+0.098
 Clare+0.097
Neg logit contributions
 hit-0.064
 shoot-0.059
 searched-0.056
 poked-0.056
 accidentally-0.055
Token He
Token ID679
Feature activation+3.25e-02

Pos logit contributions
 queens+0.004
 register+0.004
overs+0.004
 Erin+0.004
nam+0.004
Neg logit contributions
 hit-0.003
 shoot-0.002
 poked-0.002
Bang-0.002
 searched-0.002
Token was
Token ID373
Feature activation+1.86e-02

Pos logit contributions
Bang+0.036
 shoot+0.035
 hit+0.033
 BO+0.032
 fight+0.032
Neg logit contributions
 penn-0.065
 queens-0.063
nam-0.063
yle-0.062
iza-0.062
Token excited
Token ID6568
Feature activation+9.73e-02

Pos logit contributions
 hit+0.025
 poked+0.023
 accidentally+0.023
 searched+0.023
 shoot+0.023
Neg logit contributions
 queens-0.035
 penn-0.034
nam-0.034
 register-0.034
yle-0.034
Token to
Token ID284
Feature activation+4.59e-02

Pos logit contributions
 hit+0.086
 searched+0.079
 poked+0.074
 shoot+0.074
 accidentally+0.073
Neg logit contributions
nam-0.237
illi-0.232
 queens-0.229
 penn-0.229
yle-0.224
Token get
Token ID651
Feature activation-5.22e-02

Pos logit contributions
 hit+0.050
Bang+0.048
 poked+0.046
 shoot+0.046
 searched+0.046
Neg logit contributions
 queens-0.094
 penn-0.093
nam-0.093
 register-0.092
overs-0.092
Token home
Token ID1363
Feature activation-2.05e-02

Pos logit contributions
ities+0.110
iley+0.106
 queens+0.105
 importantly+0.102
 singers+0.102
Neg logit contributions
 hit-0.067
 poked-0.061
 shoot-0.060
 accidentally-0.058
 searched-0.056
Token and
Token ID290
Feature activation+6.95e-03

Pos logit contributions
iley+0.049
 queens+0.048
ities+0.048
illi+0.047
nam+0.047
Neg logit contributions
 hit-0.019
 shoot-0.016
 searched-0.016
house-0.015
 accidentally-0.015
Token start
Token ID923
Feature activation-2.17e-02

Pos logit contributions
 hit+0.008
 shoot+0.007
 poked+0.007
 searched+0.007
Bang+0.007
Neg logit contributions
 queens-0.014
 penn-0.014
 register-0.014
nam-0.014
overs-0.014
Token crafting
Token ID21671
Feature activation-6.37e-02

Pos logit contributions
 queens+0.040
 register+0.039
ities+0.038
iley+0.038
iza+0.038
Neg logit contributions
 hit-0.031
 shoot-0.030
 searched-0.029
 poked-0.029
 accidentally-0.029
Token.
Token ID13
Feature activation-1.80e-03

Pos logit contributions
 queens+0.136
iley+0.135
 register+0.132
yle+0.129
iza+0.129
Neg logit contributions
 hit-0.070
 searched-0.065
 shoot-0.064
 poked-0.061
 accidentally-0.059
Token tidy
Token ID43044
Feature activation-4.92e-03

Pos logit contributions
 queens+0.182
 penn+0.180
nam+0.180
 register+0.178
overs+0.176
Neg logit contributions
 hit-0.114
Bang-0.108
 shoot-0.107
 poked-0.105
 searched-0.104
Token everything
Token ID2279
Feature activation-1.27e-01

Pos logit contributions
 queens+0.010
nam+0.010
illi+0.010
 cents+0.010
iley+0.010
Neg logit contributions
 hit-0.006
 searched-0.006
 shoot-0.006
 accidentally-0.006
 poked-0.005
Token looked
Token ID3114
Feature activation+9.63e-02

Pos logit contributions
 queens+0.287
nam+0.284
 penn+0.282
 register+0.281
overs+0.278
Neg logit contributions
 hit-0.119
 shoot-0.107
 poked-0.106
 searched-0.106
Bang-0.104
Token,
Token ID11
Feature activation-2.19e-02

Pos logit contributions
 hit+0.110
 shoot+0.101
 poked+0.099
 searched+0.099
Bang+0.099
Neg logit contributions
 queens-0.197
nam-0.194
 penn-0.194
 register-0.192
yle-0.191
Token she
Token ID673
Feature activation+8.34e-03

Pos logit contributions
illi+0.043
 register+0.042
ities+0.042
yle+0.042
iley+0.042
Neg logit contributions
 hit-0.030
 shoot-0.027
 searched-0.027
 accidentally-0.027
 poked-0.026
Token thanked
Token ID26280
Feature activation-5.17e-02

Pos logit contributions
Bang+0.009
 shoot+0.008
 hit+0.008
 fight+0.008
 quarrel+0.007
Neg logit contributions
 queens-0.017
 penn-0.017
 register-0.016
yle-0.016
iley-0.016
Token the
Token ID262
Feature activation-3.14e-03

Pos logit contributions
 cents+0.112
 dollars+0.110
 register+0.110
asers+0.109
 penn+0.109
Neg logit contributions
 shoot-0.056
 hit-0.055
 searched-0.054
 play-0.049
 poked-0.048
Token bunny
Token ID44915
Feature activation+5.22e-02

Pos logit contributions
 queens+0.005
 penn+0.005
 register+0.005
nam+0.005
overs+0.005
Neg logit contributions
 hit-0.005
Bang-0.005
 poked-0.004
 shoot-0.004
 searched-0.004
Token and
Token ID290
Feature activation+7.42e-03

Pos logit contributions
 hit+0.076
 shoot+0.074
 searched+0.074
 poked+0.071
Bang+0.069
Neg logit contributions
nam-0.089
 queens-0.089
 penn-0.088
yle-0.087
 register-0.086
Token they
Token ID484
Feature activation-8.07e-03

Pos logit contributions
 hit+0.008
 searched+0.007
 poked+0.007
 shoot+0.007
 accidentally+0.006
Neg logit contributions
ities-0.017
 register-0.017
 queens-0.017
overs-0.017
yle-0.017
Token played
Token ID2826
Feature activation+3.72e-02

Pos logit contributions
 queens+0.017
 penn+0.017
 register+0.017
nam+0.017
reating+0.017
Neg logit contributions
 hit-0.009
 searched-0.008
 poked-0.008
 shoot-0.008
Bang-0.008
Token p
Token ID279
Feature activation-1.18e-02

Pos logit contributions
 queens+0.089
nam+0.087
iley+0.087
 register+0.087
overs+0.086
Neg logit contributions
 hit-0.069
 shoot-0.064
 poked-0.064
 searched-0.063
Bang-0.062
Tokenears
Token ID4127
Feature activation-1.28e-02

Pos logit contributions
 queens+0.015
nam+0.015
 penn+0.014
 register+0.014
overs+0.014
Neg logit contributions
 hit-0.023
 shoot-0.022
Bang-0.022
 poked-0.021
 searched-0.021
Token.
Token ID13
Feature activation+4.09e-03

Pos logit contributions
iley+0.025
 queens+0.024
 Clare+0.024
 singers+0.024
 Erin+0.024
Neg logit contributions
 hit-0.018
 shoot-0.015
 poked-0.015
 searched-0.015
 accidentally-0.014
Token
Token ID198
Feature activation+2.73e-02

Pos logit contributions
Bang+0.006
 shoot+0.006
 hit+0.006
 poked+0.006
 searched+0.005
Neg logit contributions
 Erin-0.007
 Clare-0.007
nam-0.007
 Mara-0.007
overs-0.006
Token
Token ID198
Feature activation+2.55e-02

Pos logit contributions
 hit+0.038
 shoot+0.037
Bang+0.036
 poked+0.036
 quarrel+0.035
Neg logit contributions
illi-0.047
yle-0.044
 Erin-0.044
 Clare-0.044
overs-0.044
TokenL
Token ID43
Feature activation-1.49e-01

Pos logit contributions
 hit+0.052
 shoot+0.052
Bang+0.052
 searched+0.052
 poked+0.052
Neg logit contributions
nam-0.025
 queens-0.025
illi-0.024
iley-0.023
 penn-0.023
Tokenily
Token ID813
Feature activation-6.93e-03

Pos logit contributions
 queens+0.118
 register+0.115
 penn+0.112
illi+0.112
overs+0.110
Neg logit contributions
 hit-0.356
 shoot-0.352
Bang-0.350
 poked-0.340
 searched-0.339
Token got
Token ID1392
Feature activation-3.48e-02

Pos logit contributions
 girls+0.009
 sisters+0.009
iv+0.009
 children+0.009
 years+0.009
Neg logit contributions
 BO-0.010
 sym-0.010
Bang-0.010
 snowball-0.010
 shoot-0.009
Token very
Token ID845
Feature activation+4.82e-03

Pos logit contributions
nam+0.076
 penn+0.075
 queens+0.075
 register+0.074
overs+0.073
Neg logit contributions
 hit-0.032
Bang-0.032
 shoot-0.031
 searched-0.030
 accidentally-0.030
Token scared
Token ID12008
Feature activation+1.22e-01

Pos logit contributions
 searched+0.006
Bang+0.005
 hit+0.005
 shoot+0.005
 accidentally+0.005
Neg logit contributions
 penn-0.010
nam-0.010
 queens-0.009
ums-0.009
 cents-0.009
Token and
Token ID290
Feature activation+6.49e-03

Pos logit contributions
 hit+0.099
 poked+0.085
 searched+0.081
 accidentally+0.078
 shoot+0.078
Neg logit contributions
nam-0.302
 register-0.299
 queens-0.297
yle-0.295
 penn-0.294
Token toys
Token ID14958
Feature activation-1.15e-01

Pos logit contributions
 register+0.045
yle+0.044
illi+0.044
iley+0.044
overs+0.044
Neg logit contributions
 hit-0.035
 poked-0.033
 shoot-0.033
 accidentally-0.032
 searched-0.030
Token.
Token ID13
Feature activation+1.03e-03

Pos logit contributions
iley+0.266
nam+0.266
 Debbie+0.264
 Clare+0.262
 Erin+0.259
Neg logit contributions
 hit-0.120
 shoot-0.103
 fight-0.103
 accidentally-0.095
 play-0.095
Token They
Token ID1119
Feature activation-1.33e-02

Pos logit contributions
 hit+0.001
Bang+0.001
 shoot+0.001
 poked+0.001
 accidentally+0.001
Neg logit contributions
 queens-0.002
nam-0.002
 penn-0.002
 register-0.002
yle-0.002
Token are
Token ID389
Feature activation-8.66e-02

Pos logit contributions
 queens+0.020
 penn+0.020
nam+0.020
 register+0.019
overs+0.019
Neg logit contributions
 hit-0.022
Bang-0.021
 shoot-0.021
 poked-0.020
 searched-0.020
Token living
Token ID2877
Feature activation-1.07e-01

Pos logit contributions
 register+0.181
yle+0.180
iley+0.178
illi+0.177
reating+0.176
Neg logit contributions
 hit-0.104
 shoot-0.098
 accidentally-0.096
 poked-0.093
 searched-0.086
Token things
Token ID1243
Feature activation-1.60e-01

Pos logit contributions
reating+0.182
 register+0.180
illi+0.179
 Debbie+0.178
 Clare+0.175
Neg logit contributions
 hit-0.164
 accidentally-0.157
 poked-0.152
 fight-0.150
 shoot-0.149
Token.
Token ID13
Feature activation+1.26e-03

Pos logit contributions
iley+0.302
nam+0.301
 queens+0.301
yle+0.297
illi+0.296
Neg logit contributions
 hit-0.224
 shoot-0.207
 poked-0.197
 accidentally-0.193
 searched-0.193
Token You
Token ID921
Feature activation-1.61e-02

Pos logit contributions
Bang+0.002
 hit+0.002
 shoot+0.002
 poked+0.001
 accidentally+0.001
Neg logit contributions
 penn-0.002
 register-0.002
 queens-0.002
nam-0.002
yle-0.002
Token should
Token ID815
Feature activation+3.65e-02

Pos logit contributions
 queens+0.028
nam+0.028
 penn+0.028
ities+0.026
 register+0.026
Neg logit contributions
Bang-0.022
 hit-0.021
 SPL-0.020
 snowball-0.020
 shoot-0.020
Token be
Token ID307
Feature activation-4.96e-02

Pos logit contributions
 hit+0.043
 shoot+0.040
Bang+0.039
 poked+0.038
 searched+0.038
Neg logit contributions
 queens-0.075
nam-0.074
 penn-0.073
 register-0.073
overs-0.072
Token gentle
Token ID10296
Feature activation+4.61e-02

Pos logit contributions
 queens+0.074
nam+0.073
 penn+0.073
 register+0.069
overs+0.069
Neg logit contributions
 hit-0.082
Bang-0.082
 shoot-0.080
 searched-0.078
 poked-0.077
Token party
Token ID2151
Feature activation-7.31e-02

Pos logit contributions
 queens+0.011
 penn+0.011
nam+0.011
 register+0.011
overs+0.011
Neg logit contributions
 hit-0.009
Bang-0.009
 shoot-0.009
 poked-0.008
 searched-0.008
Token,
Token ID11
Feature activation-2.49e-02

Pos logit contributions
nam+0.168
 penn+0.165
 queens+0.164
yle+0.162
ities+0.162
Neg logit contributions
 hit-0.069
 shoot-0.060
 searched-0.060
 accidentally-0.060
 poked-0.060
Token Lily
Token ID20037
Feature activation-2.71e-02

Pos logit contributions
 register+0.051
ums+0.050
iley+0.050
ities+0.050
 cents+0.050
Neg logit contributions
 hit-0.031
 accidentally-0.030
 poked-0.027
 searched-0.027
 shoot-0.027
Token saw
Token ID2497
Feature activation+5.11e-02

Pos logit contributions
 dancers+0.059
 singers+0.059
 queens+0.058
 register+0.058
 Clare+0.058
Neg logit contributions
Bang-0.025
 shoot-0.023
 snowball-0.022
 hit-0.020
 BO-0.020
Token a
Token ID257
Feature activation+1.74e-02

Pos logit contributions
 hit+0.062
 poked+0.056
 accidentally+0.054
 searched+0.053
 shoot+0.053
Neg logit contributions
 cents-0.103
ities-0.102
iley-0.102
 register-0.102
overs-0.101
Token lot
Token ID1256
Feature activation-1.76e-01

Pos logit contributions
 hit+0.023
Bang+0.022
 shoot+0.022
 poked+0.021
 searched+0.021
Neg logit contributions
 queens-0.032
 penn-0.032
nam-0.032
 register-0.031
overs-0.031
Token of
Token ID286
Feature activation-8.70e-02

Pos logit contributions
ities+0.343
iley+0.327
nam+0.326
 Erin+0.316
 Debbie+0.306
Neg logit contributions
 hit-0.262
 poked-0.222
house-0.220
 play-0.209
 shoot-0.209
Token y
Token ID331
Feature activation-3.07e-02

Pos logit contributions
 register+0.125
ities+0.125
overs+0.121
iley+0.121
 Erin+0.121
Neg logit contributions
 hit-0.155
 poked-0.144
 shoot-0.143
 accidentally-0.139
Bang-0.138
Tokenummy
Token ID13513
Feature activation+1.59e-03

Pos logit contributions
nam+0.039
 queens+0.036
illi+0.036
 register+0.036
 Erin+0.035
Neg logit contributions
 hit-0.060
 poked-0.056
 shoot-0.056
 searched-0.056
 accidentally-0.055
Token food
Token ID2057
Feature activation-1.23e-01

Pos logit contributions
 hit+0.003
 poked+0.002
 snowball+0.002
 fight+0.002
 accidentally+0.002
Neg logit contributions
nam-0.003
yle-0.003
lessness-0.003
 Erin-0.003
ala-0.003
Token.
Token ID13
Feature activation+2.63e-03

Pos logit contributions
nam+0.301
 Erin+0.286
yle+0.286
iley+0.285
ubb+0.281
Neg logit contributions
 hit-0.120
 fight-0.097
 saw-0.094
 play-0.093
 searched-0.093
Token it
Token ID340
Feature activation+8.53e-02

Pos logit contributions
 register+0.057
 queens+0.057
overs+0.056
illi+0.056
iley+0.055
Neg logit contributions
 hit-0.052
 shoot-0.050
Bang-0.048
 poked-0.048
 searched-0.048
Token's
Token ID338
Feature activation-8.87e-03

Pos logit contributions
 hit+0.080
Bang+0.078
 shoot+0.074
 poked+0.072
 accidentally+0.069
Neg logit contributions
 penn-0.187
 queens-0.185
 register-0.183
nam-0.178
yle-0.178
Token important
Token ID1593
Feature activation+1.00e-02

Pos logit contributions
 queens+0.015
 register+0.015
nam+0.015
 penn+0.015
overs+0.015
Neg logit contributions
 hit-0.013
Bang-0.012
 shoot-0.012
 poked-0.012
 searched-0.012
Token to
Token ID284
Feature activation+4.90e-02

Pos logit contributions
 hit+0.010
 shoot+0.009
 poked+0.009
 searched+0.009
Bang+0.009
Neg logit contributions
 queens-0.022
nam-0.022
 register-0.022
 penn-0.022
yle-0.022
Token take
Token ID1011
Feature activation-4.89e-02

Pos logit contributions
 hit+0.058
 shoot+0.054
Bang+0.052
 poked+0.051
 searched+0.051
Neg logit contributions
 queens-0.102
 register-0.100
overs-0.100
nam-0.100
 penn-0.099
Token responsibility
Token ID5798
Feature activation-1.51e-01

Pos logit contributions
 queens+0.080
nam+0.079
 register+0.078
yle+0.078
illi+0.077
Neg logit contributions
 hit-0.078
 shoot-0.074
Bang-0.074
 searched-0.073
 poked-0.073
Token and
Token ID290
Feature activation+9.52e-03

Pos logit contributions
nam+0.328
 queens+0.321
illi+0.317
yle+0.313
iley+0.311
Neg logit contributions
 hit-0.163
 searched-0.149
 shoot-0.148
 accidentally-0.140
 poked-0.138
Token help
Token ID1037
Feature activation-7.40e-02

Pos logit contributions
 hit+0.012
 shoot+0.012
 poked+0.011
 searched+0.011
Bang+0.011
Neg logit contributions
 queens-0.018
illi-0.018
 register-0.018
overs-0.018
yle-0.018
Token others
Token ID1854
Feature activation-1.20e-01

Pos logit contributions
 queens+0.107
 register+0.106
illi+0.105
nam+0.103
 penn+0.103
Neg logit contributions
 hit-0.133
 shoot-0.129
 poked-0.125
 accidentally-0.124
 searched-0.123
Token when
Token ID618
Feature activation-9.63e-02

Pos logit contributions
 queens+0.237
nam+0.229
 penn+0.228
 register+0.228
illi+0.226
Neg logit contributions
 hit-0.148
 shoot-0.141
 searched-0.137
 poked-0.134
 accidentally-0.134
Token they
Token ID484
Feature activation-4.74e-03

Pos logit contributions
illi+0.131
 queens+0.131
 register+0.130
yle+0.128
nam+0.128
Neg logit contributions
 hit-0.176
 shoot-0.168
 accidentally-0.167
 poked-0.165
Bang-0.163
Token They
Token ID1119
Feature activation-2.10e-02

Pos logit contributions
overs+0.007
 queens+0.007
 penn+0.007
 Erin+0.007
nam+0.007
Neg logit contributions
 hit-0.005
 shoot-0.004
 poked-0.004
Bang-0.004
 accidentally-0.004
Token promised
Token ID8072
Feature activation-7.88e-02

Pos logit contributions
 queens+0.040
 penn+0.039
 register+0.039
nam+0.039
overs+0.039
Neg logit contributions
 hit-0.027
 shoot-0.025
 searched-0.025
Bang-0.025
 poked-0.025
Token to
Token ID284
Feature activation+4.47e-02

Pos logit contributions
nam+0.203
oll+0.203
 register+0.200
asers+0.200
illi+0.199
Neg logit contributions
 hit-0.060
 shoot-0.054
 accidentally-0.048
 fight-0.048
 searched-0.047
Token have
Token ID423
Feature activation-2.75e-02

Pos logit contributions
 hit+0.048
 shoot+0.046
 play+0.042
 searched+0.042
 fight+0.041
Neg logit contributions
 register-0.102
asers-0.101
nam-0.101
 penn-0.099
yle-0.098
Token more
Token ID517
Feature activation-7.87e-02

Pos logit contributions
 register+0.055
nam+0.055
yle+0.054
 penn+0.054
ums+0.053
Neg logit contributions
 hit-0.034
 searched-0.033
 poked-0.032
Bang-0.031
 shoot-0.031
Token parties
Token ID4671
Feature activation-1.63e-01

Pos logit contributions
yle+0.162
 register+0.160
nam+0.159
 Erin+0.158
illi+0.156
Neg logit contributions
 hit-0.090
 searched-0.083
 shoot-0.083
 poked-0.082
 accidentally-0.077
Token in
Token ID287
Feature activation+2.10e-02

Pos logit contributions
 penn+0.367
nam+0.365
iley+0.363
 register+0.360
yle+0.359
Neg logit contributions
 hit-0.153
 searched-0.145
 shoot-0.135
 play-0.125
 accidentally-0.125
Token the
Token ID262
Feature activation-4.45e-03

Pos logit contributions
 hit+0.028
 shoot+0.026
 fight+0.025
 play+0.024
 searched+0.024
Neg logit contributions
oll-0.042
 register-0.041
asers-0.041
ities-0.041
ums-0.041
Token future
Token ID2003
Feature activation-1.86e-02

Pos logit contributions
 queens+0.007
 register+0.007
 penn+0.007
nam+0.007
overs+0.007
Neg logit contributions
 hit-0.007
 poked-0.007
Bang-0.007
 shoot-0.007
 accidentally-0.006
Token.
Token ID13
Feature activation-3.06e-03

Pos logit contributions
nam+0.038
 penn+0.037
yle+0.036
 register+0.036
 queens+0.036
Neg logit contributions
 hit-0.022
 searched-0.021
 shoot-0.020
 accidentally-0.020
house-0.019
Token Then
Token ID3244
Feature activation-2.08e-02

Pos logit contributions
 queens+0.007
nam+0.007
 penn+0.007
 register+0.007
yle+0.007
Neg logit contributions
 hit-0.003
Bang-0.003
 shoot-0.003
 searched-0.002
 poked-0.002