TOP ACTIVATIONS
MAX = 0.149

and clean your boo - bo o . Then you can
it on your boo - bo o . And Lily ,
my cleaned her boo - bo o with a wet cloth
all about her boo - bo o knee . From that
will heal your boo - bo o ." Tim
put on her boo - bo o . Lily remembered how
mom the bad boo - bo o . Her mom kissed
to clean her boo - bo o . She got some
will heal your boo - bo o ." Lisa
help clean your boo - bo o ," her mom said
all about her boo - bo o and was happy to
help heal his boo - bo o . Tim my was
so happy that he hugged Bunny tight . Bunny felt guilty
care of his boo - bo o and told him to
shows her his boo - bo o . She is scared
mom kissed the boo - bo o and put a band
and hugged his M ummy Bear . He knew that she
help heal the boo - bo o .
. The little boo - bo o on Tim 's knee
powder on the boo - bo o . The powder made

MIN ACTIVATIONS
MIN = -0.156

went she searched for or nam ents , and the more
wanted to see the or nam ents up close . They
He quickly hung colorful or nam ents and tw ink ling
who liked to collect or nam ents . Everywhere she went
They reached for the or nam ents and tried to take
can we have some or nam ents for our snow man
box full of beautiful or nam ents .
park filled with colourful or nam ents . Jimmy looked out
. They were called or nam ents and they were very
tree with lights and or nam ents . They also saw
tree could see lots of av oc ados that the supplier
a tree with shiny or nam ents hanging from its branches
take one of the or nam ents outside for a walk
a tall tree . Un bek now st to him ,
They reached for the or nam ents and touched them softly
to look at the or nam ents on the tree .
big tree with many or nam ents on it . The
also saw some new or nam ents that Santa had hung
a box of shiny or nam ents that spark led in
and lots of shiny or nam ents . L ila wanted

INTERVAL 0.073 - 0.149
CONTAINS 0.788%

It was the deepest sea that anyone had ever seen .
to help any harmless creatures that he found . <|endoftext|> Once
. Then he wrote his name inside the circle .
little girl . " Me too !" bark ed the dog
time . From that day on , Kitty was

INTERVAL -0.003 - 0.073
CONTAINS 52.975%

she really liked playing with it . One day , when
very happy living on the farm . Every day
she smiled at John every time he came to school .
. <|endoftext|> Once there was a boy called Billy who was
excited about her adventure that she wanted to do it again

INTERVAL -0.079 - -0.003
CONTAINS 46.077%

a closer look , but his dad said no .
The pretty frog looked at him and said , " I
again !" But the bad bear just laughed
me the orange car !" Sam says . He tries to
before they could escape , the police came and stopped them

INTERVAL -0.156 - -0.079
CONTAINS 0.160%

We wanted to make a menu with healthy food , but
. They liked to make sand castles and dig holes .
bright . It has new books and toys and a big
ily and the witch played games , ran around , and
twins who loved to play games . One day , they
Token and
Token ID290
Feature activation-4.71e-03

Pos logit contributions
ina+0.005
 roast+0.005
ies+0.005
 polar+0.005
ie+0.005
Neg logit contributions
Robert-0.007
 Robert-0.007
Rober-0.006
iable-0.006
ados-0.006
Token clean
Token ID3424
Feature activation+5.28e-04

Pos logit contributions
Robert+0.010
 Robert+0.009
 Jerry+0.009
iable+0.009
 Kyle+0.009
Neg logit contributions
ina-0.006
ies-0.006
ines-0.005
ie-0.005
aa-0.005
Token your
Token ID534
Feature activation-2.67e-02

Pos logit contributions
 roast+0.001
ina+0.001
 polar+0.001
ies+0.001
aa+0.001
Neg logit contributions
Robert-0.001
 Robert-0.001
ados-0.001
iable-0.001
 Jerry-0.001
Token boo
Token ID22513
Feature activation+5.01e-02

Pos logit contributions
ados+0.045
Robert+0.044
 Robert+0.041
jected+0.040
Rober+0.040
Neg logit contributions
ina-0.040
 roast-0.038
aa-0.037
 polar-0.036
ie-0.035
Token-
Token ID12
Feature activation+2.13e-02

Pos logit contributions
 roast+0.061
 polar+0.057
 camp+0.057
ina+0.056
 ig+0.053
Neg logit contributions
Robert-0.097
jected-0.094
ados-0.094
iable-0.093
iece-0.090
Tokenbo
Token ID2127
Feature activation+1.49e-01

Pos logit contributions
ie+0.036
ina+0.035
 roast+0.035
ies+0.035
aa+0.033
Neg logit contributions
Robert-0.035
 Robert-0.032
Rober-0.030
 Kyle-0.030
ados-0.029
Tokeno
Token ID78
Feature activation+1.15e-01

Pos logit contributions
ies+0.142
ina+0.142
ie+0.140
 roast+0.139
aa+0.128
Neg logit contributions
Robert-0.354
 Robert-0.330
Rober-0.321
 Kyle-0.314
ados-0.313
Token.
Token ID13
Feature activation+1.39e-02

Pos logit contributions
ie+0.164
ies+0.163
 roast+0.155
ina+0.155
 sleep+0.151
Neg logit contributions
Robert-0.231
 Robert-0.210
 Kyle-0.202
Rober-0.202
Terry-0.201
Token Then
Token ID3244
Feature activation+1.39e-02

Pos logit contributions
ies+0.024
ina+0.024
ie+0.024
 roast+0.023
 camp+0.023
Neg logit contributions
Robert-0.021
 Robert-0.019
jected-0.018
ados-0.018
 Jerry-0.018
Token you
Token ID345
Feature activation-4.94e-02

Pos logit contributions
 roast+0.021
ina+0.021
ies+0.020
ie+0.020
 polar+0.020
Neg logit contributions
Robert-0.025
 Robert-0.023
Rober-0.022
ados-0.022
iable-0.022
Token can
Token ID460
Feature activation+1.06e-02

Pos logit contributions
jected+0.075
iable+0.072
Robert+0.072
 Robert+0.069
 thirteen+0.067
Neg logit contributions
ina-0.077
ies-0.071
 polar-0.069
rim-0.069
 particular-0.068
Token it
Token ID340
Feature activation+6.14e-04

Pos logit contributions
ie+0.024
 sleep+0.022
 work+0.022
ies+0.021
 roast+0.021
Neg logit contributions
Robert-0.062
Rober-0.060
Terry-0.057
jected-0.056
Mic-0.055
Token on
Token ID319
Feature activation-9.96e-03

Pos logit contributions
ie+0.001
ies+0.001
 sleep+0.001
 scrub+0.001
 roast+0.001
Neg logit contributions
Robert-0.001
 Robert-0.001
 Kyle-0.001
Terry-0.001
Rober-0.001
Token your
Token ID534
Feature activation-3.00e-02

Pos logit contributions
Robert+0.021
jected+0.020
Rober+0.019
Terry+0.019
iece+0.019
Neg logit contributions
 sleep-0.012
ie-0.011
 camp-0.011
 roast-0.011
 work-0.010
Token boo
Token ID22513
Feature activation+5.33e-02

Pos logit contributions
Robert+0.057
 Robert+0.051
Rober+0.049
iable+0.049
jected+0.049
Neg logit contributions
 roast-0.043
 sleep-0.042
ies-0.042
ina-0.042
 polar-0.041
Token-
Token ID12
Feature activation+2.05e-02

Pos logit contributions
 roast+0.063
ina+0.059
 polar+0.058
 camp+0.058
 scrub+0.055
Neg logit contributions
Robert-0.109
ados-0.101
jected-0.100
iable-0.100
 Robert-0.099
Tokenbo
Token ID2127
Feature activation+1.47e-01

Pos logit contributions
ie+0.033
ina+0.033
 roast+0.032
aa+0.032
ies+0.031
Neg logit contributions
Robert-0.035
 Robert-0.032
 Kyle-0.031
Rober-0.030
ados-0.030
Tokeno
Token ID78
Feature activation+1.15e-01

Pos logit contributions
ina+0.102
ies+0.100
 roast+0.097
ie+0.096
aa+0.091
Neg logit contributions
Robert-0.389
 Robert-0.365
Rober-0.356
ados-0.350
 Kyle-0.349
Token.
Token ID13
Feature activation+9.67e-03

Pos logit contributions
ie+0.122
ies+0.121
ina+0.114
 sleep+0.112
 roast+0.110
Neg logit contributions
Robert-0.277
 Robert-0.255
 Kyle-0.249
Rober-0.248
Terry-0.247
Token And
Token ID843
Feature activation-3.69e-02

Pos logit contributions
 roast+0.016
ina+0.015
 polar+0.015
 sleep+0.015
ies+0.014
Neg logit contributions
Robert-0.016
 Robert-0.014
iable-0.014
Rober-0.014
ados-0.014
Token Lily
Token ID20037
Feature activation+3.83e-03

Pos logit contributions
Robert+0.064
Rober+0.056
 Robert+0.056
ados+0.055
jected+0.055
Neg logit contributions
 roast-0.059
ina-0.057
ies-0.056
 sleep-0.056
ie-0.056
Token,
Token ID11
Feature activation+3.83e-03

Pos logit contributions
 roast+0.005
ina+0.005
 polar+0.005
ies+0.005
 camp+0.005
Neg logit contributions
Robert-0.007
 Robert-0.007
jected-0.006
iable-0.006
ados-0.006
Tokenmy
Token ID1820
Feature activation+3.56e-02

Pos logit contributions
 roast+0.031
 outage+0.030
 camp+0.029
 Kang+0.029
 experiments+0.029
Neg logit contributions
jected-0.012
Robert-0.012
iable-0.011
 Robert-0.011
 Jerry-0.011
Token cleaned
Token ID20750
Feature activation+4.98e-03

Pos logit contributions
ina+0.055
 roast+0.053
 outage+0.052
ucks+0.052
 particular+0.052
Neg logit contributions
Robert-0.054
 Robert-0.052
jected-0.049
 Jerry-0.048
iable-0.047
Token her
Token ID607
Feature activation+1.09e-02

Pos logit contributions
 roast+0.008
ina+0.008
ies+0.008
 polar+0.007
ie+0.007
Neg logit contributions
Robert-0.008
 Robert-0.008
ados-0.007
iable-0.007
Rober-0.007
Token boo
Token ID22513
Feature activation+4.71e-02

Pos logit contributions
ina+0.016
aa+0.016
 roast+0.015
 polar+0.015
ies+0.015
Neg logit contributions
Robert-0.018
ados-0.017
 Robert-0.017
Rober-0.016
iable-0.016
Token-
Token ID12
Feature activation+1.96e-02

Pos logit contributions
 roast+0.050
ina+0.048
 polar+0.047
 camp+0.046
ies+0.045
Neg logit contributions
Robert-0.101
 Robert-0.094
ados-0.094
jected-0.093
iable-0.093
Tokenbo
Token ID2127
Feature activation+1.46e-01

Pos logit contributions
ie+0.032
 roast+0.032
ina+0.031
ies+0.031
aa+0.030
Neg logit contributions
Robert-0.033
 Robert-0.030
 Kyle-0.029
Rober-0.029
ados-0.028
Tokeno
Token ID78
Feature activation+1.09e-01

Pos logit contributions
ina+0.139
ies+0.139
ie+0.138
 roast+0.135
aa+0.127
Neg logit contributions
Robert-0.351
 Robert-0.325
Rober-0.319
 Kyle-0.312
iable-0.309
Token with
Token ID351
Feature activation-3.50e-03

Pos logit contributions
ie+0.174
ies+0.172
 roast+0.168
 scrub+0.165
 sleep+0.165
Neg logit contributions
Robert-0.202
 Robert-0.180
Rober-0.176
 Kyle-0.176
Terry-0.173
Token a
Token ID257
Feature activation+2.41e-02

Pos logit contributions
Robert+0.006
 Robert+0.005
Rober+0.005
ados+0.005
iable+0.005
Neg logit contributions
 roast-0.006
ina-0.006
ies-0.006
ie-0.005
 polar-0.005
Token wet
Token ID9583
Feature activation+4.28e-02

Pos logit contributions
ina+0.030
 roast+0.029
ies+0.029
ie+0.028
 polar+0.027
Neg logit contributions
Robert-0.049
 Robert-0.045
Rober-0.043
iable-0.043
jected-0.043
Token cloth
Token ID16270
Feature activation+2.53e-04

Pos logit contributions
ina+0.056
 roast+0.055
ies+0.053
 polar+0.050
ines+0.050
Neg logit contributions
Robert-0.080
 Robert-0.075
ados-0.072
 Jerry-0.071
jected-0.071
Token all
Token ID477
Feature activation+3.56e-02

Pos logit contributions
Robert+0.103
jected+0.099
Rober+0.093
 eighteen+0.093
Roy+0.093
Neg logit contributions
 sleep-0.037
ie-0.037
ies-0.035
 scrub-0.034
 camp-0.034
Token about
Token ID546
Feature activation+2.11e-02

Pos logit contributions
 roast+0.044
ina+0.044
ies+0.042
 polar+0.041
ie+0.041
Neg logit contributions
Robert-0.073
 Robert-0.068
ados-0.064
Rober-0.064
iable-0.064
Token her
Token ID607
Feature activation+5.06e-03

Pos logit contributions
 sleep+0.025
ies+0.025
ina+0.025
 scrub+0.025
ie+0.025
Neg logit contributions
Robert-0.043
jected-0.041
Rober-0.038
iable-0.038
 Robert-0.038
Token boo
Token ID22513
Feature activation+5.54e-02

Pos logit contributions
ies+0.007
 roast+0.007
ina+0.007
 sleep+0.007
ie+0.007
Neg logit contributions
Robert-0.009
 Robert-0.008
Rober-0.008
iable-0.008
jected-0.008
Token-
Token ID12
Feature activation+2.70e-02

Pos logit contributions
 roast+0.053
ina+0.052
ies+0.050
ie+0.049
 polar+0.048
Neg logit contributions
Robert-0.130
 Robert-0.121
ados-0.117
Rober-0.117
iable-0.117
Tokenbo
Token ID2127
Feature activation+1.46e-01

Pos logit contributions
ie+0.042
aa+0.039
ina+0.039
ies+0.037
 roast+0.035
Neg logit contributions
Robert-0.048
 Robert-0.045
 Kyle-0.044
ados-0.043
Rober-0.043
Tokeno
Token ID78
Feature activation+1.12e-01

Pos logit contributions
ina+0.088
ie+0.085
ies+0.083
aa+0.073
 roast+0.065
Neg logit contributions
Robert-0.406
Rober-0.383
 Robert-0.381
 thirteen-0.369
ados-0.369
Token knee
Token ID10329
Feature activation+5.19e-02

Pos logit contributions
ie+0.138
ies+0.127
ina+0.126
 sleep+0.116
 scrub+0.109
Neg logit contributions
Robert-0.254
Rober-0.231
Terry-0.227
 Robert-0.225
Kyle-0.221
Token.
Token ID13
Feature activation-2.31e-04

Pos logit contributions
ina+0.047
ie+0.047
 sleep+0.044
ies+0.044
 scrub+0.041
Neg logit contributions
Robert-0.132
Rober-0.120
 Robert-0.118
Terry-0.117
 thirteen-0.116
Token From
Token ID3574
Feature activation-4.91e-02

Pos logit contributions
Robert+0.000
iable+0.000
 Robert+0.000
jected+0.000
Rober+0.000
Neg logit contributions
 roast-0.000
ina-0.000
 sleep-0.000
ie-0.000
 scrub-0.000
Token that
Token ID326
Feature activation+1.06e-01

Pos logit contributions
Robert+0.082
 Robert+0.075
iable+0.071
jected+0.070
Rober+0.070
Neg logit contributions
 roast-0.081
ina-0.078
ies-0.077
 polar-0.076
ie-0.075
Token will
Token ID481
Feature activation+2.20e-02

Pos logit contributions
 roast+0.083
ie+0.079
 sleep+0.079
 scrub+0.077
ina+0.077
Neg logit contributions
Robert-0.177
Rober-0.161
 Robert-0.156
ados-0.156
Terry-0.154
Token heal
Token ID12035
Feature activation+2.63e-02

Pos logit contributions
ina+0.029
ies+0.028
ie+0.026
 polar+0.026
aa+0.026
Neg logit contributions
Robert-0.041
iable-0.039
 Robert-0.039
jected-0.037
 Jerry-0.037
Token your
Token ID534
Feature activation-2.64e-02

Pos logit contributions
 roast+0.032
ies+0.032
ie+0.032
ina+0.031
 sleep+0.030
Neg logit contributions
Robert-0.055
 Robert-0.050
Rober-0.049
ados-0.048
 Kyle-0.048
Token boo
Token ID22513
Feature activation+4.84e-02

Pos logit contributions
Robert+0.044
 Robert+0.041
ados+0.039
Rober+0.037
jected+0.037
Neg logit contributions
ina-0.042
 roast-0.040
ie-0.039
ies-0.038
aa-0.037
Token-
Token ID12
Feature activation+2.01e-02

Pos logit contributions
 roast+0.065
ina+0.062
 polar+0.061
 camp+0.061
 scrub+0.059
Neg logit contributions
Robert-0.087
jected-0.082
iable-0.082
ados-0.082
 Robert-0.080
Tokenbo
Token ID2127
Feature activation+1.46e-01

Pos logit contributions
ie+0.034
 roast+0.034
ina+0.033
ies+0.033
aa+0.032
Neg logit contributions
Robert-0.033
 Robert-0.030
 Kyle-0.028
Rober-0.028
ados-0.028
Tokeno
Token ID78
Feature activation+1.09e-01

Pos logit contributions
 roast+0.152
ina+0.148
 polar+0.142
ies+0.141
ie+0.139
Neg logit contributions
Robert-0.322
 Robert-0.298
iable-0.291
ados-0.290
jected-0.289
Token."
Token ID526
Feature activation-1.62e-02

Pos logit contributions
ies+0.129
 roast+0.129
ie+0.128
ina+0.126
 sleep+0.121
Neg logit contributions
Robert-0.232
 Robert-0.213
Rober-0.206
 Kyle-0.204
ados-0.201
Token
Token ID198
Feature activation-7.67e-03

Pos logit contributions
Robert+0.028
 Robert+0.025
ados+0.024
Rober+0.024
iable+0.024
Neg logit contributions
 roast-0.026
ina-0.026
ies-0.025
ie-0.025
 polar-0.024
Token
Token ID198
Feature activation-1.01e-02

Pos logit contributions
Robert+0.011
 Robert+0.010
 Jerry+0.010
Rober+0.009
Terry+0.009
Neg logit contributions
ina-0.014
 roast-0.014
ies-0.014
 polar-0.014
 camp-0.013
TokenTim
Token ID14967
Feature activation-1.97e-02

Pos logit contributions
Robert+0.019
 Robert+0.017
ados+0.016
Rober+0.016
 Kyle+0.016
Neg logit contributions
 roast-0.014
ies-0.014
ie-0.014
ina-0.014
 scrub-0.014
Token put
Token ID1234
Feature activation+4.41e-02

Pos logit contributions
ina+0.038
ies+0.037
 roast+0.036
 polar+0.036
aa+0.035
Neg logit contributions
Robert-0.075
 Robert-0.071
iable-0.068
 Jerry-0.068
ados-0.067
Token on
Token ID319
Feature activation-1.01e-02

Pos logit contributions
ie+0.056
 roast+0.055
ina+0.055
ies+0.055
 scrub+0.053
Neg logit contributions
Robert-0.092
 Robert-0.082
Rober-0.082
iable-0.079
jected-0.079
Token her
Token ID607
Feature activation+8.31e-03

Pos logit contributions
Robert+0.021
jected+0.019
Rober+0.019
 thirteen+0.018
iable+0.018
Neg logit contributions
 sleep-0.013
 roast-0.013
 scrub-0.012
ie-0.012
ina-0.012
Token boo
Token ID22513
Feature activation+5.06e-02

Pos logit contributions
ina+0.011
 roast+0.011
ies+0.010
ie+0.010
 polar+0.010
Neg logit contributions
Robert-0.016
 Robert-0.015
ados-0.014
iable-0.014
Rober-0.014
Token-
Token ID12
Feature activation+1.68e-02

Pos logit contributions
 roast+0.061
 camp+0.055
 polar+0.055
ina+0.055
 scrub+0.052
Neg logit contributions
Robert-0.100
ados-0.094
jected-0.093
iable-0.092
iece-0.091
Tokenbo
Token ID2127
Feature activation+1.45e-01

Pos logit contributions
ie+0.027
ina+0.026
 roast+0.026
ies+0.026
aa+0.025
Neg logit contributions
Robert-0.030
 Robert-0.027
 Kyle-0.026
Rober-0.026
ados-0.025
Tokeno
Token ID78
Feature activation+1.09e-01

Pos logit contributions
ina+0.092
ies+0.088
ie+0.086
 roast+0.083
aa+0.079
Neg logit contributions
Robert-0.392
 Robert-0.368
Rober-0.362
ados-0.356
iable-0.354
Token.
Token ID13
Feature activation-3.44e-03

Pos logit contributions
ie+0.123
ies+0.119
ina+0.118
 sleep+0.116
 roast+0.110
Neg logit contributions
Robert-0.252
 Robert-0.230
Rober-0.229
Terry-0.223
 Kyle-0.223
Token Lily
Token ID20037
Feature activation-7.75e-03

Pos logit contributions
Robert+0.006
iable+0.006
 Robert+0.005
jected+0.005
Rober+0.005
Neg logit contributions
 roast-0.005
 sleep-0.005
ina-0.005
ies-0.005
 scrub-0.005
Token remembered
Token ID12086
Feature activation-4.18e-02

Pos logit contributions
Robert+0.015
 Robert+0.014
jected+0.013
Rober+0.013
iable+0.013
Neg logit contributions
 roast-0.010
ina-0.010
 polar-0.010
ies-0.010
aa-0.009
Token how
Token ID703
Feature activation+6.56e-02

Pos logit contributions
Robert+0.079
jected+0.070
 Robert+0.070
Rober+0.069
ados+0.068
Neg logit contributions
ina-0.059
ie-0.059
 roast-0.058
ies-0.058
 sleep-0.057
Token mom
Token ID1995
Feature activation+5.84e-02

Pos logit contributions
ina+0.020
 roast+0.020
ies+0.019
ie+0.019
aa+0.019
Neg logit contributions
Robert-0.029
 Robert-0.027
ados-0.026
Rober-0.026
iable-0.026
Token the
Token ID262
Feature activation+1.19e-02

Pos logit contributions
ie+0.078
ies+0.076
ina+0.073
 roast+0.071
 sleep+0.068
Neg logit contributions
Robert-0.121
jected-0.110
 Robert-0.110
Rober-0.108
ados-0.107
Token bad
Token ID2089
Feature activation-1.75e-03

Pos logit contributions
 roast+0.016
ina+0.016
ies+0.016
ie+0.016
 polar+0.015
Neg logit contributions
Robert-0.023
 Robert-0.021
Rober-0.020
ados-0.020
iable-0.020
Token boo
Token ID22513
Feature activation+5.30e-02

Pos logit contributions
Robert+0.003
 Robert+0.003
ados+0.003
 Kyle+0.003
 Jerry+0.003
Neg logit contributions
 roast-0.003
 Chick-0.002
ina-0.002
ili-0.002
 scrub-0.002
Token-
Token ID12
Feature activation+2.07e-02

Pos logit contributions
 roast+0.058
ina+0.054
 camp+0.053
 polar+0.052
 scrub+0.051
Neg logit contributions
Robert-0.112
jected-0.104
ados-0.104
 Robert-0.103
iable-0.103
Tokenbo
Token ID2127
Feature activation+1.45e-01

Pos logit contributions
ie+0.034
ina+0.032
aa+0.032
ies+0.031
 roast+0.031
Neg logit contributions
Robert-0.037
 Robert-0.034
 Kyle-0.032
Rober-0.032
ados-0.031
Tokeno
Token ID78
Feature activation+1.15e-01

Pos logit contributions
ina+0.090
ies+0.087
ie+0.086
 roast+0.084
aa+0.077
Neg logit contributions
Robert-0.395
 Robert-0.370
Rober-0.367
ados-0.358
iable-0.356
Token.
Token ID13
Feature activation-4.28e-03

Pos logit contributions
ie+0.134
ies+0.127
ina+0.124
 roast+0.122
 sleep+0.119
Neg logit contributions
Robert-0.268
 Robert-0.244
Rober-0.242
Terry-0.236
 Kyle-0.235
Token Her
Token ID2332
Feature activation+3.57e-02

Pos logit contributions
Robert+0.007
iable+0.006
 Robert+0.006
jected+0.006
Rober+0.006
Neg logit contributions
 roast-0.007
ina-0.007
 sleep-0.007
ies-0.007
ie-0.007
Token mom
Token ID1995
Feature activation+4.03e-02

Pos logit contributions
 roast+0.053
ina+0.053
ie+0.050
 camp+0.049
 sorts+0.048
Neg logit contributions
Robert-0.060
 Robert-0.056
ados-0.053
 Kyle-0.053
 Jerry-0.052
Token kissed
Token ID27946
Feature activation-1.12e-02

Pos logit contributions
 roast+0.058
ina+0.057
 camp+0.056
 sleep+0.054
aa+0.054
Neg logit contributions
Robert-0.072
jected-0.067
 Robert-0.066
iable-0.065
 Jerry-0.061
Token to
Token ID284
Feature activation+2.48e-02

Pos logit contributions
 roast+0.027
ina+0.027
ies+0.026
ie+0.026
 sleep+0.025
Neg logit contributions
Robert-0.043
 Robert-0.040
Rober-0.038
iable-0.038
ados-0.038
Token clean
Token ID3424
Feature activation-3.84e-03

Pos logit contributions
ina+0.036
ies+0.035
aa+0.033
ie+0.033
 roast+0.033
Neg logit contributions
Robert-0.046
 Robert-0.043
 Jerry-0.041
Rober-0.041
 Kyle-0.040
Token her
Token ID607
Feature activation+1.14e-02

Pos logit contributions
Robert+0.005
 Robert+0.005
ados+0.005
 Jerry+0.004
 Kyle+0.004
Neg logit contributions
 roast-0.008
 polar-0.007
ina-0.007
aa-0.007
ies-0.007
Token boo
Token ID22513
Feature activation+5.02e-02

Pos logit contributions
ina+0.017
 roast+0.016
aa+0.016
 polar+0.016
ie+0.015
Neg logit contributions
Robert-0.020
ados-0.018
 Robert-0.018
Rober-0.017
iable-0.017
Token-
Token ID12
Feature activation+1.99e-02

Pos logit contributions
 roast+0.061
ina+0.057
 camp+0.057
 polar+0.056
 ig+0.052
Neg logit contributions
Robert-0.099
jected-0.093
ados-0.093
iable-0.092
 Robert-0.091
Tokenbo
Token ID2127
Feature activation+1.45e-01

Pos logit contributions
ie+0.035
ina+0.034
 roast+0.033
ies+0.033
aa+0.032
Neg logit contributions
Robert-0.032
 Robert-0.029
 Kyle-0.027
Rober-0.027
ados-0.027
Tokeno
Token ID78
Feature activation+1.13e-01

Pos logit contributions
ie+0.118
ies+0.117
ina+0.116
 roast+0.109
aa+0.103
Neg logit contributions
Robert-0.369
 Robert-0.345
Rober-0.338
 Kyle-0.331
 thirteen-0.328
Token.
Token ID13
Feature activation+6.21e-04

Pos logit contributions
ie+0.165
ies+0.157
 sleep+0.149
ina+0.148
 roast+0.146
Neg logit contributions
Robert-0.234
 Robert-0.213
 Kyle-0.208
Terry-0.208
Rober-0.205
Token She
Token ID1375
Feature activation+2.54e-02

Pos logit contributions
 roast+0.001
ina+0.001
ies+0.001
ie+0.001
 polar+0.001
Neg logit contributions
Robert-0.001
 Robert-0.001
Rober-0.001
ados-0.001
iable-0.001
Token got
Token ID1392
Feature activation-3.33e-03

Pos logit contributions
ina+0.038
 camp+0.038
aa+0.037
 roast+0.037
ines+0.037
Neg logit contributions
Robert-0.039
 Robert-0.037
jected-0.036
iable-0.035
 Jerry-0.034
Token some
Token ID617
Feature activation+1.14e-02

Pos logit contributions
Robert+0.005
 Robert+0.004
ados+0.004
jected+0.004
Rober+0.004
Neg logit contributions
ina-0.006
 roast-0.006
ies-0.006
ie-0.006
aa-0.006
Token will
Token ID481
Feature activation+1.33e-02

Pos logit contributions
ina+0.033
 roast+0.032
ies+0.032
 polar+0.031
ie+0.031
Neg logit contributions
Robert-0.048
 Robert-0.045
jected-0.044
iable-0.044
ados-0.043
Token heal
Token ID12035
Feature activation+2.04e-02

Pos logit contributions
ina+0.017
ies+0.016
ie+0.015
 roast+0.015
 polar+0.015
Neg logit contributions
Robert-0.026
 Robert-0.024
iable-0.024
 thirteen-0.023
jected-0.023
Token your
Token ID534
Feature activation-2.67e-02

Pos logit contributions
ies+0.023
ie+0.022
 roast+0.022
ina+0.022
 sleep+0.021
Neg logit contributions
Robert-0.046
 Robert-0.042
Rober-0.041
ados-0.040
iable-0.040
Token boo
Token ID22513
Feature activation+4.99e-02

Pos logit contributions
Robert+0.033
ados+0.030
 Robert+0.029
iable+0.028
jected+0.028
Neg logit contributions
ina-0.051
 roast-0.050
ie-0.049
 sorts-0.048
ies-0.047
Token-
Token ID12
Feature activation+2.21e-02

Pos logit contributions
 roast+0.063
ina+0.059
 polar+0.058
 camp+0.058
 ig+0.056
Neg logit contributions
Robert-0.094
jected-0.090
ados-0.089
iable-0.088
 Robert-0.086
Tokenbo
Token ID2127
Feature activation+1.44e-01

Pos logit contributions
ie+0.037
ina+0.037
 roast+0.037
ies+0.036
aa+0.036
Neg logit contributions
Robert-0.036
 Robert-0.033
 Kyle-0.031
Rober-0.031
ados-0.030
Tokeno
Token ID78
Feature activation+1.12e-01

Pos logit contributions
 roast+0.130
ina+0.129
ies+0.125
ie+0.122
 polar+0.118
Neg logit contributions
Robert-0.343
 Robert-0.319
Rober-0.309
ados-0.308
iable-0.307
Token."
Token ID526
Feature activation-1.61e-02

Pos logit contributions
ies+0.141
ie+0.140
 roast+0.137
ina+0.137
 sleep+0.130
Neg logit contributions
Robert-0.241
 Robert-0.221
 Kyle-0.213
Rober-0.212
Terry-0.209
Token
Token ID198
Feature activation-5.36e-03

Pos logit contributions
Robert+0.037
iable+0.036
jected+0.035
 thirteen+0.034
ados+0.034
Neg logit contributions
ina-0.015
 sleep-0.015
 roast-0.014
ies-0.013
 scrub-0.013
Token
Token ID198
Feature activation-8.60e-03

Pos logit contributions
Robert+0.009
 Robert+0.008
Rober+0.008
 Jerry+0.008
 Kyle+0.008
Neg logit contributions
 roast-0.009
ies-0.009
ina-0.009
ie-0.008
 polar-0.008
TokenLisa
Token ID44203
Feature activation-5.13e-02

Pos logit contributions
Robert+0.015
ados+0.015
 Robert+0.014
iable+0.013
 thirteen+0.013
Neg logit contributions
ina-0.013
 scrub-0.012
ies-0.012
 roast-0.012
ie-0.012
Token help
Token ID1037
Feature activation+3.05e-02

Pos logit contributions
ina+0.007
ies+0.007
ie+0.007
aa+0.006
ucks+0.006
Neg logit contributions
Robert-0.011
iable-0.011
 Robert-0.011
 thirteen-0.011
 Jerry-0.010
Token clean
Token ID3424
Feature activation-9.80e-03

Pos logit contributions
ina+0.052
 roast+0.052
 polar+0.051
ies+0.050
 camp+0.049
Neg logit contributions
Robert-0.046
 Robert-0.042
iable-0.042
ados-0.040
 Jerry-0.039
Token your
Token ID534
Feature activation-3.01e-02

Pos logit contributions
Robert+0.019
 Robert+0.017
Rober+0.017
jected+0.016
iable+0.016
Neg logit contributions
ina-0.013
 roast-0.013
ies-0.013
ie-0.013
 polar-0.013
Token boo
Token ID22513
Feature activation+4.92e-02

Pos logit contributions
ados+0.032
Robert+0.031
 Robert+0.028
iece+0.027
iable+0.026
Neg logit contributions
ina-0.062
 roast-0.059
 sorts-0.059
aa-0.057
iona-0.057
Token-
Token ID12
Feature activation+2.15e-02

Pos logit contributions
 roast+0.061
 polar+0.057
ina+0.057
 camp+0.057
 ig+0.054
Neg logit contributions
Robert-0.093
iable-0.089
ados-0.089
jected-0.088
 Robert-0.085
Tokenbo
Token ID2127
Feature activation+1.44e-01

Pos logit contributions
 roast+0.039
ina+0.039
ie+0.038
ies+0.038
 polar+0.037
Neg logit contributions
Robert-0.032
 Robert-0.029
Rober-0.027
ados-0.027
 Kyle-0.027
Tokeno
Token ID78
Feature activation+1.11e-01

Pos logit contributions
 roast+0.132
ina+0.131
ies+0.127
ie+0.125
 polar+0.119
Neg logit contributions
Robert-0.341
 Robert-0.318
Rober-0.308
ados-0.306
iable-0.306
Token,"
Token ID553
Feature activation-1.67e-02

Pos logit contributions
ies+0.156
ie+0.156
 roast+0.153
ina+0.152
 sleep+0.145
Neg logit contributions
Robert-0.217
 Robert-0.198
Rober-0.190
 Kyle-0.188
Terry-0.185
Token her
Token ID607
Feature activation-1.04e-02

Pos logit contributions
Robert+0.021
 Robert+0.019
 Jerry+0.018
 Kyle+0.017
ados+0.017
Neg logit contributions
 roast-0.034
ina-0.033
 camp-0.032
 polar-0.032
ies-0.032
Token mom
Token ID1995
Feature activation+2.21e-02

Pos logit contributions
Robert+0.016
 Robert+0.015
Rober+0.014
 Kyle+0.014
ados+0.014
Neg logit contributions
 roast-0.018
 sorts-0.017
ina-0.016
 camp-0.016
ie-0.016
Token said
Token ID531
Feature activation+2.81e-02

Pos logit contributions
 roast+0.024
ina+0.024
ies+0.023
 polar+0.023
 camp+0.022
Neg logit contributions
Robert-0.048
 Robert-0.045
iable-0.044
jected-0.044
Rober-0.043
Token all
Token ID477
Feature activation+2.67e-02

Pos logit contributions
Robert+0.119
jected+0.112
 eighteen+0.109
 seventeen+0.108
 thirteen+0.108
Neg logit contributions
ie-0.047
ies-0.046
 sleep-0.045
 camp-0.044
 scrub-0.043
Token about
Token ID546
Feature activation+1.33e-02

Pos logit contributions
 roast+0.038
ina+0.038
 polar+0.037
aa+0.037
ies+0.036
Neg logit contributions
Robert-0.048
 Robert-0.046
 Jerry-0.043
 Kyle-0.042
ados-0.041
Token her
Token ID607
Feature activation+1.46e-03

Pos logit contributions
ina+0.019
 roast+0.019
ies+0.018
ie+0.018
 polar+0.018
Neg logit contributions
Robert-0.025
 Robert-0.022
jected-0.022
Rober-0.022
iable-0.022
Token boo
Token ID22513
Feature activation+5.04e-02

Pos logit contributions
ina+0.002
 roast+0.002
ucks+0.002
ili+0.002
aa+0.002
Neg logit contributions
Robert-0.002
 Robert-0.002
iable-0.002
ados-0.002
 Jerry-0.002
Token-
Token ID12
Feature activation+2.35e-02

Pos logit contributions
 roast+0.057
 polar+0.051
 camp+0.051
ina+0.051
 scrub+0.049
Neg logit contributions
Robert-0.105
ados-0.100
iable-0.098
 Robert-0.098
jected-0.098
Tokenbo
Token ID2127
Feature activation+1.44e-01

Pos logit contributions
ie+0.037
ina+0.034
aa+0.033
ies+0.032
 roast+0.030
Neg logit contributions
Robert-0.044
 Robert-0.041
 Kyle-0.039
 thirteen-0.039
Rober-0.039
Tokeno
Token ID78
Feature activation+1.07e-01

Pos logit contributions
ina+0.089
ies+0.087
ie+0.085
 roast+0.081
aa+0.074
Neg logit contributions
Robert-0.389
 Robert-0.364
Rober-0.361
ados-0.352
iable-0.351
Token and
Token ID290
Feature activation+1.27e-02

Pos logit contributions
ie+0.145
ies+0.139
ina+0.134
 sleep+0.129
 roast+0.127
Neg logit contributions
Robert-0.229
Rober-0.209
 Robert-0.203
Terry-0.201
 Kyle-0.198
Token was
Token ID373
Feature activation+1.97e-02

Pos logit contributions
 roast+0.016
ina+0.016
ies+0.015
ie+0.015
 polar+0.015
Neg logit contributions
Robert-0.025
 Robert-0.024
iable-0.022
ados-0.022
 Kyle-0.022
Token happy
Token ID3772
Feature activation-3.10e-02

Pos logit contributions
 roast+0.027
ina+0.026
ies+0.026
ie+0.026
 polar+0.025
Neg logit contributions
Robert-0.038
 Robert-0.035
Rober-0.033
iable-0.033
ados-0.033
Token to
Token ID284
Feature activation+3.59e-02

Pos logit contributions
Robert+0.050
 Robert+0.047
ados+0.044
 Kyle+0.043
 Jerry+0.043
Neg logit contributions
 roast-0.052
ina-0.050
 polar-0.049
ies-0.048
aa-0.048
Token help
Token ID1037
Feature activation+3.79e-02

Pos logit contributions
ina+0.033
 roast+0.033
ies+0.033
ie+0.031
 polar+0.030
Neg logit contributions
Robert-0.068
 Robert-0.063
iable-0.061
 Jerry-0.060
Rober-0.060
Token heal
Token ID12035
Feature activation+3.00e-02

Pos logit contributions
 roast+0.060
ina+0.060
ie+0.059
ies+0.059
 polar+0.057
Neg logit contributions
Robert-0.065
 Robert-0.058
Rober-0.056
jected-0.055
ados-0.055
Token his
Token ID465
Feature activation-8.90e-03

Pos logit contributions
ie+0.038
ies+0.038
ina+0.037
 roast+0.036
 sleep+0.035
Neg logit contributions
Robert-0.063
Rober-0.056
 Robert-0.056
 thirteen-0.056
jected-0.055
Token boo
Token ID22513
Feature activation+5.38e-02

Pos logit contributions
Robert+0.011
 Robert+0.010
ados+0.010
iable+0.009
Rober+0.009
Neg logit contributions
ina-0.017
 roast-0.017
 sorts-0.016
aa-0.016
ie-0.016
Token-
Token ID12
Feature activation+2.21e-02

Pos logit contributions
 roast+0.061
ina+0.058
 polar+0.056
 camp+0.055
ies+0.055
Neg logit contributions
Robert-0.113
 Robert-0.105
ados-0.103
jected-0.103
iable-0.103
Tokenbo
Token ID2127
Feature activation+1.44e-01

Pos logit contributions
ie+0.037
ina+0.035
aa+0.035
ies+0.034
 roast+0.034
Neg logit contributions
Robert-0.038
 Robert-0.035
 Kyle-0.034
Rober-0.033
ados-0.032
Tokeno
Token ID78
Feature activation+1.12e-01

Pos logit contributions
ies+0.143
ie+0.142
ina+0.142
aa+0.131
 roast+0.131
Neg logit contributions
Robert-0.341
 Robert-0.316
Rober-0.312
 Kyle-0.304
ados-0.302
Token.
Token ID13
Feature activation-2.04e-04

Pos logit contributions
ie+0.160
ies+0.154
 sleep+0.147
ina+0.147
 roast+0.143
Neg logit contributions
Robert-0.229
 Robert-0.205
 Kyle-0.202
Terry-0.202
Rober-0.202
Token Tim
Token ID5045
Feature activation-1.52e-02

Pos logit contributions
Robert+0.000
 Robert+0.000
ados+0.000
Rober+0.000
iable+0.000
Neg logit contributions
ina-0.000
 roast-0.000
ies-0.000
ie-0.000
 polar-0.000
Tokenmy
Token ID1820
Feature activation+3.34e-02

Pos logit contributions
Robert+0.022
jected+0.021
 Robert+0.020
iable+0.020
Rober+0.019
Neg logit contributions
 roast-0.028
 camp-0.025
 soak-0.024
 polar-0.024
 outage-0.024
Token was
Token ID373
Feature activation+1.43e-04

Pos logit contributions
 roast+0.046
ina+0.045
 camp+0.043
 polar+0.042
ies+0.042
Neg logit contributions
Robert-0.062
jected-0.058
 Robert-0.058
iable-0.055
Rober-0.055
Token so
Token ID523
Feature activation+2.26e-02

Pos logit contributions
Robert+0.009
 Robert+0.008
Rober+0.008
ados+0.008
iable+0.008
Neg logit contributions
 roast-0.010
ina-0.010
ies-0.010
ie-0.010
 polar-0.010
Token happy
Token ID3772
Feature activation-4.80e-02

Pos logit contributions
 roast+0.028
ina+0.028
ies+0.028
ie+0.027
 polar+0.026
Neg logit contributions
Robert-0.046
 Robert-0.042
Rober-0.041
iable-0.041
ados-0.040
Token that
Token ID326
Feature activation+7.67e-02

Pos logit contributions
Robert+0.089
 Robert+0.081
ados+0.077
Rober+0.077
iable+0.077
Neg logit contributions
 roast-0.069
ina-0.068
ies-0.067
ie-0.066
 polar-0.065
Token he
Token ID339
Feature activation-2.12e-04

Pos logit contributions
 roast+0.135
ina+0.134
ies+0.131
ie+0.131
 polar+0.129
Neg logit contributions
Robert-0.118
 Robert-0.104
Rober-0.100
ados-0.100
iable-0.100
Token hugged
Token ID41130
Feature activation-3.12e-03

Pos logit contributions
Robert+0.000
 Robert+0.000
Rober+0.000
iable+0.000
jected+0.000
Neg logit contributions
 roast-0.000
ina-0.000
ies-0.000
ie-0.000
 polar-0.000
Token Bunny
Token ID28683
Feature activation+1.43e-01

Pos logit contributions
Robert+0.006
 Robert+0.005
iable+0.005
Rober+0.005
jected+0.005
Neg logit contributions
 roast-0.005
ina-0.005
ie-0.005
ies-0.005
 polar-0.005
Token tight
Token ID5381
Feature activation+1.69e-02

Pos logit contributions
ie+0.184
 roast+0.184
ies+0.184
ina+0.183
 sleep+0.177
Neg logit contributions
Robert-0.287
 Robert-0.257
iable-0.255
Rober-0.254
ados-0.252
Token.
Token ID13
Feature activation+1.45e-02

Pos logit contributions
 sleep+0.014
ina+0.013
ie+0.013
ies+0.012
 scrub+0.012
Neg logit contributions
Robert-0.043
Rober-0.040
iable-0.040
Terry-0.039
Kyle-0.038
Token Bunny
Token ID28683
Feature activation+1.05e-01

Pos logit contributions
ies+0.026
ina+0.026
 roast+0.026
ie+0.026
 scrub+0.024
Neg logit contributions
Robert-0.022
 Robert-0.020
 Jerry-0.019
ados-0.019
 Kyle-0.018
Token felt
Token ID2936
Feature activation+2.39e-02

Pos logit contributions
 roast+0.131
ina+0.127
ies+0.124
aa+0.119
 polar+0.118
Neg logit contributions
Robert-0.208
 Robert-0.198
Rober-0.186
jected-0.185
 Jerry-0.182
Token guilty
Token ID6717
Feature activation-3.46e-02

Pos logit contributions
 sleep+0.031
 roast+0.031
 polar+0.030
 scrub+0.030
ina+0.029
Neg logit contributions
Robert-0.047
ados-0.043
 Robert-0.042
iable-0.041
Rober-0.041
Token care
Token ID1337
Feature activation+1.17e-02

Pos logit contributions
Robert+0.028
Rober+0.025
iable+0.025
jected+0.025
Terry+0.025
Neg logit contributions
ie-0.016
 sleep-0.016
 roast-0.015
 work-0.015
 scrub-0.015
Token of
Token ID286
Feature activation+2.61e-02

Pos logit contributions
ie+0.008
ina+0.008
ies+0.008
 scrub+0.008
 roast+0.007
Neg logit contributions
Robert-0.031
 Robert-0.029
Rober-0.028
 Kyle-0.028
iable-0.028
Token his
Token ID465
Feature activation-3.01e-03

Pos logit contributions
 roast+0.029
ie+0.029
 sleep+0.028
 scrub+0.028
 ig+0.028
Neg logit contributions
Robert-0.059
jected-0.054
Rober-0.054
iable-0.051
Terry-0.051
Token boo
Token ID22513
Feature activation+4.57e-02

Pos logit contributions
Robert+0.006
 Robert+0.005
Rober+0.005
iable+0.005
ados+0.005
Neg logit contributions
 roast-0.004
ina-0.004
ies-0.004
ie-0.004
 polar-0.004
Token-
Token ID12
Feature activation+1.74e-02

Pos logit contributions
 roast+0.041
ina+0.041
ies+0.039
ie+0.038
 polar+0.037
Neg logit contributions
Robert-0.109
 Robert-0.101
Rober-0.098
ados-0.098
iable-0.098
Tokenbo
Token ID2127
Feature activation+1.43e-01

Pos logit contributions
ie+0.028
ina+0.027
aa+0.026
ies+0.026
 roast+0.025
Neg logit contributions
Robert-0.031
 Robert-0.029
 Kyle-0.028
Rober-0.028
Terry-0.026
Tokeno
Token ID78
Feature activation+1.05e-01

Pos logit contributions
ina+0.084
ie+0.083
ies+0.080
aa+0.067
 roast+0.064
Neg logit contributions
Robert-0.407
Rober-0.385
 Robert-0.380
 Kyle-0.365
 thirteen-0.365
Token and
Token ID290
Feature activation+7.33e-03

Pos logit contributions
ie+0.145
ies+0.133
ina+0.124
 sleep+0.124
 scrub+0.123
Neg logit contributions
Robert-0.239
Rober-0.219
Terry-0.211
 Robert-0.210
Kyle-0.206
Token told
Token ID1297
Feature activation+2.06e-02

Pos logit contributions
ina+0.010
 roast+0.009
ies+0.009
ie+0.009
 polar+0.009
Neg logit contributions
Robert-0.014
 Robert-0.013
iable-0.013
ados-0.013
 Jerry-0.013
Token him
Token ID683
Feature activation-1.05e-03

Pos logit contributions
ie+0.029
 sleep+0.028
 roast+0.027
ies+0.027
 scrub+0.026
Neg logit contributions
Robert-0.042
jected-0.038
Rober-0.037
 Robert-0.036
Terry-0.036
Token to
Token ID284
Feature activation+2.12e-02

Pos logit contributions
Robert+0.002
Rober+0.002
jected+0.002
 Robert+0.002
iable+0.002
Neg logit contributions
ies-0.001
ie-0.001
 roast-0.001
 sleep-0.001
ina-0.001
Token shows
Token ID2523
Feature activation-3.38e-02

Pos logit contributions
Robert+0.022
 Robert+0.020
jected+0.020
ados+0.020
iable+0.020
Neg logit contributions
 roast-0.011
ies-0.011
ina-0.011
 polar-0.010
 sleep-0.010
Token her
Token ID607
Feature activation+1.62e-02

Pos logit contributions
Robert+0.064
Rober+0.058
 Robert+0.058
jected+0.057
iable+0.057
Neg logit contributions
ie-0.049
ies-0.048
ina-0.046
 sleep-0.046
 roast-0.045
Token his
Token ID465
Feature activation-3.34e-03

Pos logit contributions
 roast+0.024
ies+0.024
ie+0.024
ina+0.023
 scrub+0.023
Neg logit contributions
Robert-0.030
 Robert-0.026
jected-0.026
Rober-0.026
iable-0.025
Token boo
Token ID22513
Feature activation+4.76e-02

Pos logit contributions
Robert+0.006
 Robert+0.006
ados+0.005
iable+0.005
Rober+0.005
Neg logit contributions
 roast-0.005
ina-0.005
ie-0.005
ies-0.005
 polar-0.004
Token-
Token ID12
Feature activation+1.47e-02

Pos logit contributions
 roast+0.051
ina+0.048
 camp+0.046
 polar+0.045
ies+0.044
Neg logit contributions
Robert-0.104
 Robert-0.096
ados-0.095
jected-0.094
iable-0.094
Tokenbo
Token ID2127
Feature activation+1.42e-01

Pos logit contributions
ie+0.024
ina+0.023
aa+0.023
ies+0.022
 roast+0.022
Neg logit contributions
Robert-0.026
 Robert-0.024
 Kyle-0.023
Rober-0.023
ados-0.023
Tokeno
Token ID78
Feature activation+1.11e-01

Pos logit contributions
ies+0.088
ina+0.086
ie+0.086
aa+0.075
 roast+0.068
Neg logit contributions
Robert-0.397
Rober-0.374
 Robert-0.371
ados-0.358
 Kyle-0.355
Token.
Token ID13
Feature activation+3.10e-03

Pos logit contributions
ie+0.117
ies+0.114
ina+0.100
 sleep+0.099
 roast+0.095
Neg logit contributions
Robert-0.278
Rober-0.252
 Robert-0.252
Terry-0.249
 Kyle-0.245
Token She
Token ID1375
Feature activation+2.26e-02

Pos logit contributions
 roast+0.004
ina+0.004
 polar+0.004
 sleep+0.004
ies+0.004
Neg logit contributions
Robert-0.006
iable-0.006
jected-0.006
 Robert-0.006
ados-0.006
Token is
Token ID318
Feature activation-1.48e-02

Pos logit contributions
ina+0.035
 roast+0.033
ie+0.032
ies+0.032
aa+0.031
Neg logit contributions
Robert-0.038
 Robert-0.036
 thirteen-0.034
iable-0.034
 Kyle-0.034
Token scared
Token ID12008
Feature activation+4.27e-02

Pos logit contributions
Robert+0.026
 Robert+0.024
Rober+0.023
ados+0.023
iable+0.023
Neg logit contributions
 roast-0.023
ina-0.023
ies-0.022
ie-0.022
 polar-0.022
Token mom
Token ID1995
Feature activation+4.03e-02

Pos logit contributions
 roast+0.053
ina+0.053
ie+0.050
 camp+0.049
 sorts+0.048
Neg logit contributions
Robert-0.060
 Robert-0.056
ados-0.053
 Kyle-0.053
 Jerry-0.052
Token kissed
Token ID27946
Feature activation-1.12e-02

Pos logit contributions
 roast+0.058
ina+0.057
 camp+0.056
 sleep+0.054
aa+0.054
Neg logit contributions
Robert-0.072
jected-0.067
 Robert-0.066
iable-0.065
 Jerry-0.061
Token the
Token ID262
Feature activation+7.58e-03

Pos logit contributions
Robert+0.023
iable+0.021
Rober+0.021
 Robert+0.021
jected+0.020
Neg logit contributions
ie-0.016
ina-0.015
ies-0.015
 roast-0.014
 sleep-0.014
Token boo
Token ID22513
Feature activation+5.07e-02

Pos logit contributions
 roast+0.010
ina+0.010
ies+0.010
ie+0.009
 polar+0.009
Neg logit contributions
Robert-0.015
 Robert-0.014
Rober-0.013
ados-0.013
iable-0.013
Token-
Token ID12
Feature activation+2.14e-02

Pos logit contributions
 roast+0.053
ina+0.050
 camp+0.048
ies+0.047
 polar+0.047
Neg logit contributions
Robert-0.111
 Robert-0.103
jected-0.102
ados-0.102
iable-0.101
Tokenbo
Token ID2127
Feature activation+1.40e-01

Pos logit contributions
ie+0.034
ina+0.033
aa+0.032
 roast+0.032
ies+0.032
Neg logit contributions
Robert-0.038
 Robert-0.036
 Kyle-0.034
Rober-0.033
ados-0.033
Tokeno
Token ID78
Feature activation+1.10e-01

Pos logit contributions
ina+0.088
ies+0.086
 roast+0.085
ie+0.084
aa+0.077
Neg logit contributions
Robert-0.380
 Robert-0.356
Rober-0.350
ados-0.344
iable-0.343
Token and
Token ID290
Feature activation+9.62e-03

Pos logit contributions
ie+0.152
ies+0.146
 sleep+0.138
 roast+0.136
ina+0.135
Neg logit contributions
Robert-0.243
 Robert-0.218
Rober-0.218
 Kyle-0.215
Terry-0.214
Token put
Token ID1234
Feature activation+4.75e-02

Pos logit contributions
ina+0.013
 roast+0.013
ies+0.012
aa+0.012
ie+0.012
Neg logit contributions
Robert-0.018
 Robert-0.017
 Jerry-0.016
iable-0.016
jected-0.016
Token a
Token ID257
Feature activation+4.64e-03

Pos logit contributions
ie+0.065
ies+0.061
 roast+0.061
 scrub+0.061
 sleep+0.061
Neg logit contributions
Robert-0.096
Rober-0.086
iable-0.085
 Robert-0.085
Terry-0.082
Token band
Token ID4097
Feature activation-1.42e-03

Pos logit contributions
ina+0.006
 roast+0.005
ies+0.005
ie+0.005
 polar+0.005
Neg logit contributions
Robert-0.009
 Robert-0.009
Rober-0.008
iable-0.008
jected-0.008
Token and
Token ID290
Feature activation+1.51e-02

Pos logit contributions
Robert+0.121
iable+0.113
Rober+0.108
ados+0.108
 Robert+0.107
Neg logit contributions
ies-0.038
ina-0.037
 sleep-0.034
 scrub-0.033
ie-0.033
Token hugged
Token ID41130
Feature activation-1.49e-03

Pos logit contributions
 roast+0.017
ina+0.016
ies+0.016
ie+0.016
 scrub+0.015
Neg logit contributions
Robert-0.033
 Robert-0.030
Rober-0.030
iable-0.030
ados-0.030
Token his
Token ID465
Feature activation+9.50e-03

Pos logit contributions
Robert+0.003
 Robert+0.003
ados+0.003
Rober+0.003
iable+0.003
Neg logit contributions
 roast-0.002
ina-0.002
ies-0.002
ie-0.002
 polar-0.002
Token M
Token ID337
Feature activation+9.58e-02

Pos logit contributions
ina+0.012
 roast+0.012
ie+0.011
aa+0.011
ies+0.011
Neg logit contributions
Robert-0.018
 Robert-0.018
ados-0.017
Rober-0.016
jected-0.016
Tokenummy
Token ID13513
Feature activation+7.34e-02

Pos logit contributions
 roast+0.175
 camp+0.162
 march+0.159
 sleep+0.158
 polar+0.158
Neg logit contributions
Robert-0.124
ados-0.123
 Robert-0.117
jected-0.114
Rober-0.107
Token Bear
Token ID14732
Feature activation+1.39e-01

Pos logit contributions
ies+0.085
 roast+0.085
ie+0.084
ina+0.083
 sleep+0.081
Neg logit contributions
Robert-0.160
 Robert-0.143
iable-0.143
Rober-0.143
jected-0.139
Token.
Token ID13
Feature activation+7.40e-03

Pos logit contributions
ies+0.160
ie+0.158
 roast+0.153
ina+0.152
 sleep+0.148
Neg logit contributions
Robert-0.312
Rober-0.283
iable-0.282
 Robert-0.275
Terry-0.273
Token He
Token ID679
Feature activation+1.10e-02

Pos logit contributions
ies+0.012
ina+0.012
ie+0.012
 roast+0.012
 polar+0.012
Neg logit contributions
Robert-0.012
 Robert-0.011
ados-0.010
Rober-0.010
 Jerry-0.010
Token knew
Token ID2993
Feature activation-3.33e-02

Pos logit contributions
 roast+0.014
ina+0.014
ies+0.013
 polar+0.013
ie+0.013
Neg logit contributions
Robert-0.021
 Robert-0.020
jected-0.019
iable-0.019
Rober-0.019
Token that
Token ID326
Feature activation+6.85e-02

Pos logit contributions
Robert+0.058
 Robert+0.052
Rober+0.050
ados+0.050
iable+0.050
Neg logit contributions
 roast-0.052
ina-0.051
ies-0.050
ie-0.050
 polar-0.049
Token she
Token ID673
Feature activation+3.67e-03

Pos logit contributions
 roast+0.094
ina+0.093
ies+0.091
ie+0.089
 polar+0.088
Neg logit contributions
Robert-0.129
 Robert-0.120
ados-0.113
Rober-0.112
iable-0.112
Token help
Token ID1037
Feature activation+3.73e-02

Pos logit contributions
ina+0.037
ies+0.034
ines+0.031
ie+0.031
 roast+0.031
Neg logit contributions
Robert-0.048
iable-0.045
 Robert-0.044
 Jerry-0.044
jected-0.041
Token heal
Token ID12035
Feature activation+2.82e-02

Pos logit contributions
 roast+0.061
ina+0.060
ies+0.060
ie+0.059
 sleep+0.057
Neg logit contributions
Robert-0.063
 Robert-0.056
Rober-0.054
jected-0.053
ados-0.053
Token the
Token ID262
Feature activation-7.56e-03

Pos logit contributions
ie+0.037
ies+0.037
 roast+0.036
ina+0.036
 sleep+0.034
Neg logit contributions
Robert-0.058
 Robert-0.052
Rober-0.052
jected-0.050
 thirteen-0.050
Token boo
Token ID22513
Feature activation+4.61e-02

Pos logit contributions
Robert+0.013
 Robert+0.012
jected+0.012
Rober+0.011
iable+0.011
Neg logit contributions
ina-0.011
 roast-0.011
 sorts-0.010
ies-0.010
ie-0.010
Token-
Token ID12
Feature activation+1.83e-02

Pos logit contributions
 roast+0.055
 camp+0.051
 polar+0.051
ina+0.051
 scrub+0.049
Neg logit contributions
Robert-0.091
iable-0.085
jected-0.085
ados-0.085
 Robert-0.084
Tokenbo
Token ID2127
Feature activation+1.38e-01

Pos logit contributions
ina+0.032
ie+0.032
 roast+0.032
ies+0.031
aa+0.030
Neg logit contributions
Robert-0.029
 Robert-0.026
Rober-0.024
 Kyle-0.024
ados-0.024
Tokeno
Token ID78
Feature activation+1.05e-01

Pos logit contributions
 roast+0.111
ina+0.109
ies+0.105
ie+0.103
 polar+0.099
Neg logit contributions
Robert-0.342
 Robert-0.320
Rober-0.310
ados-0.310
iable-0.309
Token.
Token ID13
Feature activation+7.35e-03

Pos logit contributions
ie+0.150
ies+0.147
ina+0.142
 roast+0.141
 sleep+0.138
Neg logit contributions
Robert-0.213
 Robert-0.193
Rober-0.188
 Kyle-0.187
Terry-0.186
Token
Token ID220
Feature activation+2.43e-02

Pos logit contributions
 roast+0.011
ina+0.011
ies+0.011
ie+0.011
 polar+0.010
Neg logit contributions
Robert-0.013
 Robert-0.012
Rober-0.011
ados-0.011
iable-0.011
Token
Token ID198
Feature activation-1.37e-02

Pos logit contributions
 roast+0.036
ina+0.035
ies+0.035
 polar+0.034
ie+0.034
Neg logit contributions
Robert-0.044
 Robert-0.040
Rober-0.038
iable-0.038
 Jerry-0.038
Token
Token ID198
Feature activation-1.72e-02

Pos logit contributions
Robert+0.021
 Robert+0.018
 Jerry+0.017
Rober+0.016
Terry+0.016
Neg logit contributions
 roast-0.026
ies-0.026
 polar-0.026
ina-0.025
 scrub-0.024
Token.
Token ID13
Feature activation+7.36e-03

Pos logit contributions
Robert+0.062
 Robert+0.057
Rober+0.055
iable+0.055
ados+0.054
Neg logit contributions
 roast-0.040
ina-0.040
ies-0.039
ie-0.039
 sleep-0.037
Token The
Token ID383
Feature activation+3.13e-02

Pos logit contributions
 roast+0.011
ina+0.010
ies+0.010
ie+0.010
 polar+0.010
Neg logit contributions
Robert-0.014
 Robert-0.012
Rober-0.012
iable-0.012
ados-0.012
Token little
Token ID1310
Feature activation+5.27e-02

Pos logit contributions
ina+0.053
ies+0.052
 roast+0.051
ie+0.051
 outage+0.048
Neg logit contributions
Robert-0.049
 Robert-0.043
Rober-0.043
 thirteen-0.042
jected-0.042
Token boo
Token ID22513
Feature activation+4.60e-02

Pos logit contributions
 roast+0.069
ina+0.066
ines+0.062
ili+0.061
iona+0.061
Neg logit contributions
Robert-0.098
 Robert-0.094
ados-0.092
 Kyle-0.090
 Jerry-0.089
Token-
Token ID12
Feature activation+1.90e-02

Pos logit contributions
 roast+0.059
 camp+0.055
ina+0.053
 scrub+0.052
 polar+0.052
Neg logit contributions
Robert-0.087
jected-0.083
ados-0.082
 Robert-0.081
iable-0.080
Tokenbo
Token ID2127
Feature activation+1.38e-01

Pos logit contributions
ie+0.026
 roast+0.025
ina+0.024
ies+0.024
aa+0.024
Neg logit contributions
Robert-0.038
 Robert-0.035
Rober-0.034
ados-0.033
 Kyle-0.033
Tokeno
Token ID78
Feature activation+1.08e-01

Pos logit contributions
 roast+0.132
ina+0.126
 polar+0.121
ies+0.120
 camp+0.120
Neg logit contributions
Robert-0.313
 Robert-0.291
jected-0.289
iable-0.280
ados-0.279
Token on
Token ID319
Feature activation-6.35e-05

Pos logit contributions
 roast+0.108
ina+0.106
ies+0.105
ie+0.104
 sleep+0.099
Neg logit contributions
Robert-0.249
 Robert-0.230
Rober-0.224
iable-0.222
ados-0.221
Token Tim
Token ID5045
Feature activation+1.13e-02

Pos logit contributions
Robert+0.000
Rober+0.000
iable+0.000
 Robert+0.000
jected+0.000
Neg logit contributions
ie-0.000
 roast-0.000
ies-0.000
 polar-0.000
ina-0.000
Token's
Token ID338
Feature activation+3.24e-02

Pos logit contributions
 roast+0.021
ina+0.021
ies+0.021
ie+0.021
 polar+0.020
Neg logit contributions
Robert-0.016
 Robert-0.014
iable-0.013
ados-0.013
Rober-0.013
Token knee
Token ID10329
Feature activation+4.33e-02

Pos logit contributions
 sleep+0.046
 scrub+0.044
ies+0.044
 roast+0.043
ie+0.043
Neg logit contributions
Robert-0.063
 Robert-0.057
iable-0.056
jected-0.055
Rober-0.055
Token powder
Token ID11913
Feature activation+3.19e-02

Pos logit contributions
 roast+0.033
ina+0.033
ies+0.032
ie+0.032
 polar+0.031
Neg logit contributions
Robert-0.046
 Robert-0.042
ados-0.041
Rober-0.041
iable-0.041
Token on
Token ID319
Feature activation-1.23e-02

Pos logit contributions
ie+0.040
ies+0.040
 scrub+0.039
ina+0.037
 roast+0.036
Neg logit contributions
Robert-0.073
 Robert-0.067
Rober-0.065
 Kyle-0.064
Terry-0.062
Token the
Token ID262
Feature activation-8.33e-03

Pos logit contributions
Robert+0.030
jected+0.027
Rober+0.027
iable+0.027
Terry+0.026
Neg logit contributions
 sleep-0.013
ie-0.012
 scrub-0.012
 Chick-0.012
 roast-0.012
Token boo
Token ID22513
Feature activation+4.62e-02

Pos logit contributions
Robert+0.016
 Robert+0.014
Rober+0.014
iable+0.014
ados+0.013
Neg logit contributions
 roast-0.012
ina-0.012
ies-0.012
ie-0.011
 polar-0.011
Token-
Token ID12
Feature activation+1.67e-02

Pos logit contributions
 roast+0.050
ina+0.046
 camp+0.045
 polar+0.045
ies+0.044
Neg logit contributions
Robert-0.099
ados-0.092
jected-0.091
 Robert-0.091
iable-0.091
Tokenbo
Token ID2127
Feature activation+1.38e-01

Pos logit contributions
ie+0.026
ina+0.026
 roast+0.025
aa+0.025
ies+0.025
Neg logit contributions
Robert-0.030
 Robert-0.028
 Kyle-0.026
Rober-0.026
ados-0.025
Tokeno
Token ID78
Feature activation+1.06e-01

Pos logit contributions
ina+0.091
ies+0.087
ie+0.085
 roast+0.084
aa+0.080
Neg logit contributions
Robert-0.376
 Robert-0.352
Rober-0.349
ados-0.338
 Kyle-0.337
Token.
Token ID13
Feature activation-1.41e-02

Pos logit contributions
ie+0.134
ies+0.129
ina+0.127
 roast+0.123
 sleep+0.123
Neg logit contributions
Robert-0.240
Rober-0.217
 Robert-0.216
 Kyle-0.210
Terry-0.208
Token The
Token ID383
Feature activation+1.85e-02

Pos logit contributions
Robert+0.023
 Robert+0.021
ados+0.020
Rober+0.020
iable+0.020
Neg logit contributions
 roast-0.023
ina-0.023
ies-0.022
ie-0.022
 polar-0.022
Token powder
Token ID11913
Feature activation+4.74e-02

Pos logit contributions
 roast+0.035
 polar+0.033
ina+0.033
ies+0.033
ie+0.032
Neg logit contributions
Robert-0.026
 Robert-0.023
jected-0.023
Rober-0.022
ados-0.022
Token made
Token ID925
Feature activation+3.14e-02

Pos logit contributions
 roast+0.048
ina+0.047
ies+0.045
 polar+0.044
ie+0.043
Neg logit contributions
Robert-0.106
 Robert-0.099
ados-0.096
jected-0.096
iable-0.095
Token went
Token ID1816
Feature activation+1.63e-02

Pos logit contributions
 roast+0.028
aa+0.026
ina+0.026
 polar+0.026
 camp+0.025
Neg logit contributions
Robert-0.029
 Robert-0.028
jected-0.027
ados-0.026
Rober-0.026
Token she
Token ID673
Feature activation+7.60e-03

Pos logit contributions
ie+0.022
ina+0.022
ies+0.022
 roast+0.020
 sleep+0.020
Neg logit contributions
Robert-0.033
jected-0.029
Rober-0.029
 Robert-0.029
iable-0.028
Token searched
Token ID16499
Feature activation+6.77e-02

Pos logit contributions
 roast+0.012
aa+0.011
 outage+0.011
 polar+0.011
ucks+0.011
Neg logit contributions
Robert-0.012
 Robert-0.012
jected-0.011
iable-0.011
Rober-0.010
Token for
Token ID329
Feature activation-2.24e-02

Pos logit contributions
 roast+0.092
ina+0.092
ies+0.091
ie+0.090
 polar+0.087
Neg logit contributions
Robert-0.130
 Robert-0.119
Rober-0.114
iable-0.114
ados-0.113
Token or
Token ID393
Feature activation-6.35e-02

Pos logit contributions
Robert+0.044
jected+0.041
 Robert+0.039
 Kyle+0.039
iable+0.039
Neg logit contributions
ies-0.031
ie-0.030
 roast-0.029
 sleep-0.028
 camp-0.028
Tokennam
Token ID7402
Feature activation-1.56e-01

Pos logit contributions
Robert+0.054
 Robert+0.043
ados+0.040
Rober+0.040
jected+0.038
Neg logit contributions
 roast-0.155
ies-0.154
ie-0.153
ina-0.152
 sleep-0.152
Tokenents
Token ID658
Feature activation-9.07e-03

Pos logit contributions
Robert+0.217
 Robert+0.194
Rober+0.182
iable+0.179
jected+0.178
Neg logit contributions
ies-0.293
ina-0.293
ie-0.289
 roast-0.287
aa-0.273
Token,
Token ID11
Feature activation-6.28e-03

Pos logit contributions
Robert+0.021
Rober+0.019
 Robert+0.019
jected+0.018
 Kyle+0.018
Neg logit contributions
ies-0.011
ie-0.011
ina-0.010
 sleep-0.009
 roast-0.009
Token and
Token ID290
Feature activation-1.84e-02

Pos logit contributions
Robert+0.014
jected+0.013
Rober+0.012
 Robert+0.012
iable+0.012
Neg logit contributions
ies-0.007
 roast-0.007
ina-0.007
ie-0.007
 sleep-0.007
Token the
Token ID262
Feature activation+3.05e-03

Pos logit contributions
Robert+0.036
 Robert+0.032
Rober+0.032
jected+0.032
ados+0.031
Neg logit contributions
ina-0.025
ie-0.025
 roast-0.025
ies-0.025
 scrub-0.023
Token more
Token ID517
Feature activation-2.42e-04

Pos logit contributions
ies+0.003
 work+0.003
ie+0.003
 sleep+0.003
 plan+0.003
Neg logit contributions
Robert-0.007
 Kyle-0.006
jected-0.006
iable-0.006
Kyle-0.006
Token wanted
Token ID2227
Feature activation-1.52e-02

Pos logit contributions
Robert+0.039
 Robert+0.036
ados+0.035
Rober+0.035
iable+0.035
Neg logit contributions
 roast-0.015
ina-0.015
ies-0.015
ie-0.014
 polar-0.014
Token to
Token ID284
Feature activation-1.21e-02

Pos logit contributions
Robert+0.030
 Robert+0.028
Rober+0.027
jected+0.027
iable+0.027
Neg logit contributions
 roast-0.020
ina-0.019
ies-0.019
ie-0.019
 polar-0.019
Token see
Token ID766
Feature activation-1.72e-02

Pos logit contributions
Robert+0.025
 Robert+0.024
 Jerry+0.023
iable+0.023
 Kyle+0.022
Neg logit contributions
ina-0.015
 polar-0.014
ies-0.014
ie-0.013
aa-0.013
Token the
Token ID262
Feature activation-3.42e-02

Pos logit contributions
Robert+0.028
 Robert+0.026
iable+0.024
ados+0.024
 Jerry+0.024
Neg logit contributions
ina-0.028
 roast-0.028
aa-0.027
ies-0.027
ie-0.026
Token or
Token ID393
Feature activation-5.88e-02

Pos logit contributions
Robert+0.067
 Robert+0.061
iable+0.058
jected+0.058
 Kyle+0.058
Neg logit contributions
 roast-0.046
ies-0.045
ina-0.045
ie-0.044
 polar-0.043
Tokennam
Token ID7402
Feature activation-1.49e-01

Pos logit contributions
Robert+0.074
 Robert+0.064
Rober+0.060
iable+0.059
ados+0.059
Neg logit contributions
 roast-0.119
ina-0.118
ies-0.117
ie-0.116
 polar-0.114
Tokenents
Token ID658
Feature activation-6.15e-03

Pos logit contributions
Robert+0.195
 Robert+0.172
Rober+0.161
ados+0.160
iable+0.159
Neg logit contributions
 roast-0.291
ina-0.291
ies-0.288
ie-0.284
 polar-0.278
Token up
Token ID510
Feature activation-7.17e-03

Pos logit contributions
Robert+0.013
 Robert+0.012
Rober+0.012
jected+0.011
ados+0.011
Neg logit contributions
ies-0.008
ie-0.008
 roast-0.008
ina-0.007
 sleep-0.007
Token close
Token ID1969
Feature activation-1.29e-02

Pos logit contributions
Robert+0.016
iable+0.014
jected+0.014
ados+0.014
 Robert+0.014
Neg logit contributions
ies-0.008
ina-0.008
ie-0.008
 roast-0.008
 scrub-0.008
Token.
Token ID13
Feature activation-1.90e-02

Pos logit contributions
Robert+0.028
iable+0.026
jected+0.026
Rober+0.026
 Robert+0.025
Neg logit contributions
ies-0.015
ie-0.015
ina-0.015
 roast-0.014
 sleep-0.013
Token They
Token ID1119
Feature activation-4.54e-03

Pos logit contributions
Robert+0.040
jected+0.037
iable+0.037
ados+0.036
Terry+0.036
Neg logit contributions
 roast-0.021
 sleep-0.020
 camp-0.020
ies-0.020
ina-0.020
Token He
Token ID679
Feature activation-4.06e-03

Pos logit contributions
Robert+0.003
iable+0.003
jected+0.003
ados+0.003
Rober+0.003
Neg logit contributions
 roast-0.003
ina-0.003
 sleep-0.003
 scrub-0.003
 polar-0.003
Token quickly
Token ID2952
Feature activation-7.24e-03

Pos logit contributions
Robert+0.007
 Robert+0.007
 Kyle+0.006
jected+0.006
 thirteen+0.006
Neg logit contributions
ina-0.005
 roast-0.005
ie-0.005
ies-0.005
aa-0.005
Token hung
Token ID9174
Feature activation+9.06e-03

Pos logit contributions
Robert+0.016
 Robert+0.015
Rober+0.014
ados+0.014
iable+0.014
Neg logit contributions
 roast-0.008
ina-0.008
ies-0.008
ie-0.008
 scrub-0.008
Token colorful
Token ID20239
Feature activation-2.21e-02

Pos logit contributions
ies+0.010
 roast+0.010
 polar+0.010
ina+0.010
 camp+0.009
Neg logit contributions
Robert-0.021
jected-0.019
iable-0.019
Mic-0.018
Rober-0.018
Token or
Token ID393
Feature activation-4.10e-02

Pos logit contributions
Robert+0.042
 Robert+0.037
Rober+0.037
jected+0.037
iable+0.037
Neg logit contributions
ies-0.033
 roast-0.032
ina-0.031
ie-0.031
 camp-0.030
Tokennam
Token ID7402
Feature activation-1.49e-01

Pos logit contributions
Robert+0.055
ados+0.050
 Robert+0.047
jected+0.046
 Jerry+0.045
Neg logit contributions
 roast-0.080
ies-0.080
 scrub-0.079
 sleep-0.077
ina-0.077
Tokenents
Token ID658
Feature activation-2.98e-03

Pos logit contributions
Robert+0.210
 Robert+0.189
Rober+0.178
iable+0.175
ados+0.175
Neg logit contributions
ina-0.278
ies-0.277
 roast-0.275
ie-0.271
 polar-0.259
Token and
Token ID290
Feature activation-3.27e-03

Pos logit contributions
Robert+0.007
Rober+0.006
 Robert+0.006
Mic+0.006
Terry+0.006
Neg logit contributions
ies-0.004
ie-0.004
ina-0.004
 roast-0.003
 scrub-0.003
Token tw
Token ID665
Feature activation+3.86e-02

Pos logit contributions
Robert+0.007
Rober+0.007
iable+0.006
jected+0.006
ados+0.006
Neg logit contributions
 roast-0.004
 scrub-0.004
ies-0.004
ina-0.004
 sleep-0.003
Tokenink
Token ID676
Feature activation+5.29e-02

Pos logit contributions
 roast+0.055
 polar+0.054
 sleep+0.052
 camp+0.051
ina+0.049
Neg logit contributions
Robert-0.070
ados-0.066
iable-0.064
 Robert-0.064
 eighteen-0.064
Tokenling
Token ID1359
Feature activation+4.78e-02

Pos logit contributions
ies+0.094
ie+0.092
ina+0.091
 scrub+0.081
aa+0.080
Neg logit contributions
Robert-0.091
 Robert-0.080
Rober-0.079
 Jerry-0.077
ados-0.077
Token who
Token ID508
Feature activation+4.23e-02

Pos logit contributions
Robert+0.002
 Robert+0.002
 Jerry+0.002
jected+0.002
iable+0.001
Neg logit contributions
 roast-0.001
 camp-0.001
ies-0.001
ucks-0.001
 polar-0.001
Token liked
Token ID8288
Feature activation-3.91e-03

Pos logit contributions
ucks+0.060
ies+0.059
 roast+0.058
ina+0.058
 outage+0.056
Neg logit contributions
Robert-0.071
jected-0.068
 Robert-0.066
Rober-0.064
 Jerry-0.062
Token to
Token ID284
Feature activation+6.95e-03

Pos logit contributions
Robert+0.007
 Robert+0.007
ados+0.007
Rober+0.006
iable+0.006
Neg logit contributions
 roast-0.005
ina-0.005
ies-0.005
ie-0.005
 polar-0.005
Token collect
Token ID2824
Feature activation+6.18e-03

Pos logit contributions
ies+0.007
ina+0.007
ie+0.006
aa+0.006
 polar+0.006
Neg logit contributions
Robert-0.015
 Robert-0.015
 Jerry-0.014
ados-0.014
 Kyle-0.014
Token or
Token ID393
Feature activation-4.91e-02

Pos logit contributions
ies+0.008
ie+0.008
 roast+0.008
ina+0.008
 polar+0.007
Neg logit contributions
Robert-0.013
 Robert-0.012
jected-0.011
Rober-0.011
iable-0.011
Tokennam
Token ID7402
Feature activation-1.48e-01

Pos logit contributions
Robert+0.038
 Robert+0.029
jected+0.026
Rober+0.026
ados+0.025
Neg logit contributions
 roast-0.125
ies-0.123
ina-0.123
ie-0.122
 sleep-0.120
Tokenents
Token ID658
Feature activation+1.56e-03

Pos logit contributions
Robert+0.211
 Robert+0.190
Rober+0.179
jected+0.176
iable+0.174
Neg logit contributions
ies-0.276
ina-0.274
ie-0.272
 roast-0.268
aa-0.254
Token.
Token ID13
Feature activation-5.61e-03

Pos logit contributions
ies+0.002
ie+0.002
ina+0.002
 roast+0.002
 sleep+0.002
Neg logit contributions
Robert-0.004
 Robert-0.003
Rober-0.003
jected-0.003
 Kyle-0.003
Token Everywhere
Token ID48201
Feature activation+3.21e-02

Pos logit contributions
Robert+0.008
 Robert+0.007
ados+0.006
Rober+0.006
 Jerry+0.006
Neg logit contributions
ies-0.011
 roast-0.011
ina-0.011
 polar-0.010
ie-0.010
Token she
Token ID673
Feature activation+1.79e-02

Pos logit contributions
 roast+0.054
ina+0.053
ies+0.052
ie+0.052
 polar+0.051
Neg logit contributions
Robert-0.052
 Robert-0.047
Rober-0.044
ados-0.044
iable-0.044
Token went
Token ID1816
Feature activation+1.63e-02

Pos logit contributions
 roast+0.028
aa+0.026
ina+0.026
 polar+0.026
 camp+0.025
Neg logit contributions
Robert-0.029
 Robert-0.028
jected-0.027
ados-0.026
Rober-0.026
Token They
Token ID1119
Feature activation+2.42e-03

Pos logit contributions
Robert+0.007
iable+0.007
jected+0.007
ados+0.007
iece+0.006
Neg logit contributions
 roast-0.005
 sleep-0.005
 camp-0.005
 scrub-0.005
ina-0.004
Token reached
Token ID4251
Feature activation+2.15e-02

Pos logit contributions
ina+0.003
 roast+0.003
ies+0.003
ie+0.003
 polar+0.003
Neg logit contributions
Robert-0.005
 Robert-0.004
Rober-0.004
iable-0.004
ados-0.004
Token for
Token ID329
Feature activation-2.82e-02

Pos logit contributions
ina+0.039
aa+0.039
ie+0.039
rim+0.039
ies+0.039
Neg logit contributions
Robert-0.028
 Robert-0.028
 Kyle-0.025
 twelve-0.024
 thirteen-0.024
Token the
Token ID262
Feature activation-2.87e-02

Pos logit contributions
Robert+0.052
jected+0.049
iable+0.047
Rober+0.046
ados+0.046
Neg logit contributions
 roast-0.042
 camp-0.039
 sleep-0.039
 polar-0.038
ies-0.038
Token or
Token ID393
Feature activation-4.57e-02

Pos logit contributions
Robert+0.057
 Kyle+0.054
jected+0.052
iece+0.051
Kyle+0.051
Neg logit contributions
 roast-0.037
ies-0.036
ie-0.036
 work-0.036
 sleep-0.036
Tokennam
Token ID7402
Feature activation-1.48e-01

Pos logit contributions
Robert+0.053
ados+0.046
Rober+0.044
jected+0.043
iable+0.043
Neg logit contributions
 roast-0.099
 scrub-0.097
 sleep-0.094
ies-0.093
ie-0.093
Tokenents
Token ID658
Feature activation-1.92e-03

Pos logit contributions
Robert+0.204
 Robert+0.183
Rober+0.171
iable+0.169
jected+0.168
Neg logit contributions
ina-0.281
ies-0.280
 roast-0.279
ie-0.275
 polar-0.264
Token and
Token ID290
Feature activation-5.54e-03

Pos logit contributions
Robert+0.004
Rober+0.004
 Robert+0.004
jected+0.004
ados+0.004
Neg logit contributions
ies-0.002
ie-0.002
ina-0.002
 roast-0.002
 sleep-0.002
Token tried
Token ID3088
Feature activation+1.02e-02

Pos logit contributions
Robert+0.012
Rober+0.011
iable+0.011
jected+0.011
ados+0.011
Neg logit contributions
 roast-0.007
 scrub-0.006
 sleep-0.006
ina-0.005
ies-0.005
Token to
Token ID284
Feature activation-1.19e-02

Pos logit contributions
 roast+0.011
ies+0.011
ina+0.011
 scrub+0.011
 camp+0.010
Neg logit contributions
Robert-0.023
jected-0.022
Rober-0.021
 Robert-0.021
ados-0.020
Token take
Token ID1011
Feature activation-1.57e-03

Pos logit contributions
Robert+0.025
 Robert+0.023
Rober+0.022
iable+0.022
ados+0.022
Neg logit contributions
ina-0.014
 roast-0.014
ies-0.014
ie-0.013
 polar-0.013
Token can
Token ID460
Feature activation-3.95e-03

Pos logit contributions
 roast+0.000
ina+0.000
ies+0.000
ie+0.000
 sleep+0.000
Neg logit contributions
Robert-0.000
jected-0.000
 Robert-0.000
Rober-0.000
ados-0.000
Token we
Token ID356
Feature activation-5.29e-02

Pos logit contributions
Robert+0.006
 Robert+0.005
Rober+0.005
ados+0.005
jected+0.005
Neg logit contributions
 roast-0.007
ina-0.007
ies-0.007
ie-0.007
 polar-0.007
Token have
Token ID423
Feature activation-1.73e-02

Pos logit contributions
Robert+0.117
 Robert+0.109
iable+0.105
Rober+0.105
ados+0.104
Neg logit contributions
ina-0.055
 roast-0.055
ies-0.054
ie-0.052
 polar-0.052
Token some
Token ID617
Feature activation+2.17e-02

Pos logit contributions
Robert+0.032
jected+0.030
iece+0.028
Rober+0.028
 Kyle+0.028
Neg logit contributions
 roast-0.025
 camp-0.024
 sleep-0.024
 work-0.023
 scrub-0.023
Token or
Token ID393
Feature activation-4.65e-02

Pos logit contributions
 roast+0.031
ina+0.031
ies+0.030
ie+0.030
 polar+0.029
Neg logit contributions
Robert-0.040
 Robert-0.037
Rober-0.035
iable-0.035
ados-0.035
Tokennam
Token ID7402
Feature activation-1.46e-01

Pos logit contributions
Robert+0.069
jected+0.064
Rober+0.060
 Robert+0.058
Terry+0.057
Neg logit contributions
 roast-0.088
 sleep-0.083
ies-0.082
 camp-0.081
ie-0.080
Tokenents
Token ID658
Feature activation+1.93e-03

Pos logit contributions
Robert+0.201
 Robert+0.180
Rober+0.168
jected+0.165
ados+0.165
Neg logit contributions
ina-0.276
ies-0.276
 roast-0.273
ie-0.271
 polar-0.258
Token for
Token ID329
Feature activation-4.91e-03

Pos logit contributions
ina+0.002
ies+0.002
ie+0.002
 roast+0.002
 sleep+0.002
Neg logit contributions
Robert-0.004
 Robert-0.004
Rober-0.004
ados-0.004
jected-0.004
Token our
Token ID674
Feature activation-5.72e-02

Pos logit contributions
Robert+0.008
jected+0.008
 Robert+0.008
Rober+0.007
iable+0.007
Neg logit contributions
 roast-0.008
ina-0.007
 sleep-0.007
ie-0.007
 camp-0.007
Token snow
Token ID6729
Feature activation+3.83e-02

Pos logit contributions
Robert+0.119
 Robert+0.108
jected+0.106
iable+0.105
Rober+0.105
Neg logit contributions
 roast-0.069
ies-0.069
ina-0.067
ie-0.067
 sleep-0.066
Tokenman
Token ID805
Feature activation+3.77e-02

Pos logit contributions
 roast+0.047
ina+0.047
ies+0.046
ie+0.046
 polar+0.044
Neg logit contributions
Robert-0.079
 Robert-0.072
Rober-0.070
iable-0.069
jected-0.069
Token box
Token ID3091
Feature activation-7.20e-02

Pos logit contributions
Robert+0.048
 Robert+0.044
ados+0.042
Rober+0.042
iable+0.041
Neg logit contributions
 roast-0.040
ina-0.040
ies-0.039
ie-0.039
 polar-0.038
Token full
Token ID1336
Feature activation-3.31e-02

Pos logit contributions
Robert+0.140
 Robert+0.128
Rober+0.123
ados+0.123
iable+0.122
Neg logit contributions
 roast-0.096
ina-0.095
ies-0.093
ie-0.091
 polar-0.090
Token of
Token ID286
Feature activation-3.33e-03

Pos logit contributions
Robert+0.083
Rober+0.077
 Robert+0.077
iable+0.076
jected+0.075
Neg logit contributions
 roast-0.027
ina-0.026
ie-0.026
ies-0.026
 polar-0.025
Token beautiful
Token ID4950
Feature activation-9.08e-03

Pos logit contributions
Robert+0.006
 Robert+0.005
ados+0.005
Rober+0.005
 Jerry+0.005
Neg logit contributions
ina-0.005
 roast-0.005
aa-0.005
ies-0.005
ie-0.005
Token or
Token ID393
Feature activation-3.91e-02

Pos logit contributions
Robert+0.016
 Robert+0.015
ados+0.014
Rober+0.014
 Kyle+0.013
Neg logit contributions
 roast-0.014
ina-0.014
aa-0.013
ie-0.013
 polar-0.013
Tokennam
Token ID7402
Feature activation-1.46e-01

Pos logit contributions
Robert+0.032
 Robert+0.025
Rober+0.023
ados+0.022
jected+0.022
Neg logit contributions
 roast-0.097
ina-0.096
ies-0.096
ie-0.094
 polar-0.094
Tokenents
Token ID658
Feature activation-5.05e-03

Pos logit contributions
Robert+0.199
 Robert+0.177
Rober+0.166
iable+0.165
ados+0.164
Neg logit contributions
ina-0.278
ies-0.276
 roast-0.275
ie-0.271
 polar-0.261
Token.
Token ID13
Feature activation-8.74e-03

Pos logit contributions
Robert+0.011
 Robert+0.010
Rober+0.010
 Kyle+0.010
iable+0.010
Neg logit contributions
ies-0.006
ie-0.006
ina-0.006
 roast-0.006
 sleep-0.005
Token
Token ID220
Feature activation+1.93e-02

Pos logit contributions
Robert+0.013
 Robert+0.011
Rober+0.011
ados+0.010
 Jerry+0.010
Neg logit contributions
 roast-0.017
ina-0.016
ies-0.016
 polar-0.016
ie-0.016
Token
Token ID198
Feature activation-1.36e-02

Pos logit contributions
 roast+0.030
 polar+0.029
ies+0.028
ina+0.028
ie+0.028
Neg logit contributions
Robert-0.034
 Robert-0.031
Rober-0.030
 Kyle-0.029
 Jerry-0.029
Token
Token ID198
Feature activation-1.64e-02

Pos logit contributions
Robert+0.022
 Robert+0.019
Rober+0.019
Terry+0.018
 Jerry+0.017
Neg logit contributions
 roast-0.026
 polar-0.025
ies-0.025
 ig-0.025
ina-0.024
Token park
Token ID3952
Feature activation-2.70e-02

Pos logit contributions
 camp+0.021
 roast+0.021
 polar+0.020
 sleep+0.020
 ig+0.020
Neg logit contributions
Robert-0.037
ados-0.035
 Robert-0.034
jected-0.033
Rober-0.033
Token filled
Token ID5901
Feature activation+3.22e-02

Pos logit contributions
Robert+0.059
ados+0.054
Rober+0.053
 Robert+0.053
iable+0.053
Neg logit contributions
ina-0.030
 roast-0.030
 sleep-0.029
ies-0.029
ie-0.029
Token with
Token ID351
Feature activation-2.26e-02

Pos logit contributions
 roast+0.039
ie+0.039
ina+0.038
ies+0.038
 sleep+0.037
Neg logit contributions
Robert-0.065
iable-0.061
jected-0.060
 thirteen-0.059
Rober-0.059
Token colourful
Token ID44799
Feature activation+5.49e-03

Pos logit contributions
Robert+0.045
jected+0.042
iable+0.041
 Robert+0.041
Rober+0.041
Neg logit contributions
 polar-0.030
 roast-0.029
ies-0.029
 sleep-0.029
 camp-0.028
Token or
Token ID393
Feature activation-2.98e-02

Pos logit contributions
 roast+0.008
ies+0.008
ina+0.007
 polar+0.007
ie+0.007
Neg logit contributions
Robert-0.010
 Robert-0.010
iable-0.009
jected-0.009
Rober-0.009
Tokennam
Token ID7402
Feature activation-1.45e-01

Pos logit contributions
Robert+0.054
jected+0.050
 Robert+0.049
ados+0.049
Rober+0.048
Neg logit contributions
 roast-0.044
 polar-0.043
ies-0.042
 camp-0.041
ina-0.041
Tokenents
Token ID658
Feature activation+5.31e-03

Pos logit contributions
Robert+0.207
 Robert+0.188
Rober+0.176
iable+0.174
ados+0.174
Neg logit contributions
ina-0.266
ies-0.266
 roast-0.262
ie-0.260
 polar-0.250
Token.
Token ID13
Feature activation-3.81e-03

Pos logit contributions
ies+0.006
ina+0.006
ie+0.006
 roast+0.006
 polar+0.005
Neg logit contributions
Robert-0.012
 Robert-0.011
Rober-0.011
iable-0.011
jected-0.011
Token Jimmy
Token ID12963
Feature activation-1.01e-02

Pos logit contributions
Robert+0.006
iable+0.006
jected+0.006
ados+0.006
 Robert+0.006
Neg logit contributions
 roast-0.006
 sleep-0.006
 camp-0.006
ina-0.006
 polar-0.006
Token looked
Token ID3114
Feature activation+9.72e-03

Pos logit contributions
Robert+0.020
 Robert+0.019
jected+0.017
iable+0.017
Rober+0.017
Neg logit contributions
 roast-0.013
ina-0.012
ies-0.012
 polar-0.012
ie-0.012
Token out
Token ID503
Feature activation-3.37e-02

Pos logit contributions
ies+0.012
ie+0.012
ina+0.011
 polar+0.011
 scrub+0.011
Neg logit contributions
Robert-0.021
ados-0.019
jected-0.018
 Robert-0.018
iable-0.018
Token.
Token ID13
Feature activation+6.16e-03

Pos logit contributions
ina+0.037
ies+0.036
ie+0.035
 roast+0.035
 sleep+0.035
Neg logit contributions
Robert-0.075
Rober-0.069
 Robert-0.068
jected-0.067
ados-0.066
Token They
Token ID1119
Feature activation+8.29e-03

Pos logit contributions
ies+0.011
ina+0.011
ie+0.011
 roast+0.010
 polar+0.010
Neg logit contributions
Robert-0.009
 Robert-0.009
 Jerry-0.008
 Kyle-0.008
Rober-0.008
Token were
Token ID547
Feature activation-3.04e-02

Pos logit contributions
 roast+0.011
 polar+0.010
ina+0.010
aa+0.010
ucks+0.010
Neg logit contributions
Robert-0.016
 Robert-0.015
iable-0.014
jected-0.014
Rober-0.014
Token called
Token ID1444
Feature activation+5.35e-02

Pos logit contributions
Robert+0.046
 Robert+0.043
 Jerry+0.040
 thirteen+0.040
Rober+0.039
Neg logit contributions
ina-0.053
aa-0.052
ie-0.052
ies-0.051
 roast-0.051
Token or
Token ID393
Feature activation-5.12e-02

Pos logit contributions
 roast+0.079
 camp+0.075
 polar+0.073
ies+0.072
 sleep+0.072
Neg logit contributions
Robert-0.102
jected-0.095
iable-0.090
 Robert-0.089
Rober-0.089
Tokennam
Token ID7402
Feature activation-1.44e-01

Pos logit contributions
Robert+0.045
jected+0.035
ados+0.033
Rober+0.033
 Robert+0.033
Neg logit contributions
 roast-0.127
ies-0.125
 sleep-0.123
 scrub-0.123
ina-0.122
Tokenents
Token ID658
Feature activation+1.08e-03

Pos logit contributions
Robert+0.197
 Robert+0.175
Rober+0.164
iable+0.162
jected+0.162
Neg logit contributions
ina-0.274
ies-0.274
 roast-0.273
ie-0.268
 polar-0.260
Token and
Token ID290
Feature activation+3.05e-03

Pos logit contributions
ies+0.001
ie+0.001
ina+0.001
 roast+0.001
 camp+0.001
Neg logit contributions
Robert-0.002
Rober-0.002
 Robert-0.002
jected-0.002
iable-0.002
Token they
Token ID484
Feature activation-1.31e-02

Pos logit contributions
 roast+0.004
ies+0.004
 scrub+0.004
ina+0.004
 sleep+0.004
Neg logit contributions
Robert-0.006
Rober-0.006
jected-0.006
 Robert-0.006
ados-0.005
Token were
Token ID547
Feature activation-3.02e-02

Pos logit contributions
Robert+0.025
 Robert+0.023
iable+0.022
jected+0.022
Rober+0.022
Neg logit contributions
 roast-0.017
ina-0.017
 polar-0.017
ies-0.017
aa-0.016
Token very
Token ID845
Feature activation+1.92e-03

Pos logit contributions
Robert+0.053
 Robert+0.048
Rober+0.046
ados+0.046
iable+0.046
Neg logit contributions
 roast-0.046
ina-0.046
ies-0.045
ie-0.044
 polar-0.043
Token tree
Token ID5509
Feature activation-1.00e-02

Pos logit contributions
Robert+0.057
 Robert+0.053
ados+0.050
Rober+0.050
iable+0.050
Neg logit contributions
ina-0.043
 roast-0.043
ies-0.042
ie-0.041
 polar-0.040
Token with
Token ID351
Feature activation-3.95e-02

Pos logit contributions
Robert+0.019
 Robert+0.018
Rober+0.017
ados+0.017
iable+0.017
Neg logit contributions
 roast-0.014
ina-0.014
ies-0.013
ie-0.013
 polar-0.013
Token lights
Token ID7588
Feature activation-4.02e-02

Pos logit contributions
Robert+0.075
iable+0.069
jected+0.068
Rober+0.068
 Robert+0.065
Neg logit contributions
 roast-0.058
 polar-0.057
 ig-0.056
 camp-0.054
ies-0.053
Token and
Token ID290
Feature activation-1.27e-02

Pos logit contributions
Robert+0.088
 Robert+0.080
Rober+0.079
iable+0.078
jected+0.077
Neg logit contributions
ina-0.047
ies-0.047
 roast-0.046
ie-0.044
 polar-0.042
Token or
Token ID393
Feature activation-4.78e-02

Pos logit contributions
Robert+0.022
 Robert+0.020
Rober+0.019
iable+0.019
ados+0.019
Neg logit contributions
 roast-0.020
ina-0.020
ies-0.020
ie-0.019
 polar-0.019
Tokennam
Token ID7402
Feature activation-1.43e-01

Pos logit contributions
Robert+0.091
jected+0.083
iable+0.081
Rober+0.080
 Robert+0.080
Neg logit contributions
 roast-0.070
ies-0.066
 sleep-0.066
 polar-0.065
 camp-0.065
Tokenents
Token ID658
Feature activation+1.08e-02

Pos logit contributions
Robert+0.202
 Robert+0.181
Rober+0.170
iable+0.167
jected+0.167
Neg logit contributions
ies-0.268
ina-0.267
 roast-0.262
ie-0.260
aa-0.249
Token.
Token ID13
Feature activation-6.84e-03

Pos logit contributions
ies+0.013
ina+0.013
ie+0.012
 roast+0.012
 polar+0.011
Neg logit contributions
Robert-0.024
 Robert-0.022
Rober-0.022
jected-0.021
iable-0.021
Token They
Token ID1119
Feature activation-7.32e-04

Pos logit contributions
Robert+0.015
iable+0.014
jected+0.014
ados+0.013
Rober+0.013
Neg logit contributions
 roast-0.008
 camp-0.007
 polar-0.007
 Ch-0.007
 sleep-0.007
Token also
Token ID635
Feature activation+3.90e-02

Pos logit contributions
Robert+0.002
 Robert+0.001
ados+0.001
Rober+0.001
iable+0.001
Neg logit contributions
 roast-0.001
ina-0.001
ies-0.001
ie-0.001
 polar-0.001
Token saw
Token ID2497
Feature activation-3.13e-02

Pos logit contributions
ina+0.032
 roast+0.032
ies+0.031
ie+0.030
 polar+0.028
Neg logit contributions
Robert-0.096
ados-0.090
 Robert-0.089
Rober-0.087
iable-0.087
Token tree
Token ID5509
Feature activation+3.16e-02

Pos logit contributions
ie+0.003
ies+0.003
 roast+0.003
ina+0.003
 sleep+0.003
Neg logit contributions
Robert-0.007
Rober-0.006
 Robert-0.006
 Kyle-0.006
iable-0.006
Token could
Token ID714
Feature activation+4.41e-03

Pos logit contributions
ies+0.033
ie+0.033
 roast+0.032
ina+0.032
 scrub+0.029
Neg logit contributions
Robert-0.073
 Robert-0.066
Rober-0.066
iable-0.064
 Kyle-0.064
Token see
Token ID766
Feature activation-1.63e-02

Pos logit contributions
ina+0.005
ies+0.005
 roast+0.005
 polar+0.004
ie+0.004
Neg logit contributions
Robert-0.010
 Robert-0.009
iable-0.009
Rober-0.009
ados-0.009
Token lots
Token ID6041
Feature activation-7.75e-02

Pos logit contributions
Robert+0.036
Rober+0.033
jected+0.033
 Robert+0.032
 Kyle+0.032
Neg logit contributions
ie-0.020
ies-0.018
ina-0.017
 roast-0.016
 polar-0.016
Token of
Token ID286
Feature activation-2.45e-02

Pos logit contributions
Robert+0.190
 Robert+0.176
Rober+0.173
jected+0.170
iable+0.170
Neg logit contributions
ie-0.068
ies-0.067
 roast-0.064
ina-0.064
 sleep-0.060
Token av
Token ID1196
Feature activation-1.43e-01

Pos logit contributions
Robert+0.042
 Robert+0.038
jected+0.037
Rober+0.036
iable+0.036
Neg logit contributions
ie-0.039
ies-0.039
 roast-0.038
ina-0.037
 sleep-0.036
Tokenoc
Token ID420
Feature activation-6.07e-02

Pos logit contributions
Robert+0.359
 Robert+0.336
 Kyle+0.332
Rober+0.328
jected+0.317
Neg logit contributions
ie-0.117
ies-0.115
 roast-0.104
 sleep-0.094
ina-0.094
Tokenados
Token ID22484
Feature activation-1.05e-01

Pos logit contributions
Robert+0.071
Luke+0.059
Rober+0.058
 Kyle+0.058
Marie+0.058
Neg logit contributions
ie-0.131
ies-0.128
unn-0.124
 work-0.122
 kinds-0.115
Token that
Token ID326
Feature activation+6.92e-02

Pos logit contributions
Robert+0.227
 Robert+0.206
Rober+0.205
jected+0.202
 Kyle+0.199
Neg logit contributions
ies-0.124
ie-0.120
ina-0.118
 roast-0.117
 sleep-0.110
Token the
Token ID262
Feature activation+1.76e-03

Pos logit contributions
ie+0.071
ina+0.071
 roast+0.071
ies+0.067
 sleep+0.063
Neg logit contributions
Robert-0.160
Rober-0.145
ados-0.141
jected-0.140
 Robert-0.139
Token supplier
Token ID22693
Feature activation-6.71e-03

Pos logit contributions
 work+0.002
 sleep+0.002
 plan+0.002
ies+0.002
 camp+0.002
Neg logit contributions
Robert-0.004
jected-0.003
iable-0.003
iece-0.003
 Kyle-0.003
Token a
Token ID257
Feature activation-1.97e-02

Pos logit contributions
Robert+0.061
 Robert+0.055
Rober+0.053
iable+0.053
jected+0.053
Neg logit contributions
 roast-0.060
ina-0.060
ies-0.059
ie-0.059
 polar-0.059
Token tree
Token ID5509
Feature activation-2.07e-02

Pos logit contributions
Robert+0.035
 Robert+0.031
Rober+0.030
iable+0.030
 Jerry+0.029
Neg logit contributions
ina-0.029
 roast-0.029
ie-0.028
ies-0.028
 scrub-0.028
Token with
Token ID351
Feature activation-4.69e-02

Pos logit contributions
Robert+0.033
 Robert+0.030
jected+0.029
 Jerry+0.028
ados+0.028
Neg logit contributions
 roast-0.033
 polar-0.033
ina-0.032
ies-0.032
aa-0.032
Token shiny
Token ID22441
Feature activation-1.22e-02

Pos logit contributions
Robert+0.085
iable+0.076
 Robert+0.076
jected+0.075
Rober+0.074
Neg logit contributions
 roast-0.072
 polar-0.068
ies-0.068
 ig-0.067
ina-0.067
Token or
Token ID393
Feature activation-3.91e-02

Pos logit contributions
Robert+0.024
 Robert+0.021
Rober+0.020
jected+0.020
iable+0.020
Neg logit contributions
ies-0.018
 roast-0.017
ina-0.017
ie-0.017
 polar-0.016
Tokennam
Token ID7402
Feature activation-1.41e-01

Pos logit contributions
Robert+0.057
jected+0.049
 Robert+0.049
iable+0.048
ados+0.047
Neg logit contributions
 roast-0.073
ies-0.071
ina-0.069
 polar-0.069
 sleep-0.069
Tokenents
Token ID658
Feature activation-9.87e-04

Pos logit contributions
Robert+0.198
 Robert+0.178
Rober+0.166
iable+0.164
jected+0.163
Neg logit contributions
ies-0.263
ina-0.263
 roast-0.258
ie-0.257
aa-0.245
Token hanging
Token ID10938
Feature activation+7.87e-03

Pos logit contributions
Robert+0.002
 Robert+0.002
Rober+0.002
 Kyle+0.002
jected+0.002
Neg logit contributions
ies-0.001
ie-0.001
ina-0.001
 roast-0.001
 sleep-0.001
Token from
Token ID422
Feature activation-3.04e-02

Pos logit contributions
ies+0.008
ina+0.007
 roast+0.007
ie+0.007
 Ch+0.007
Neg logit contributions
Robert-0.019
Luke-0.018
iable-0.017
 Kyle-0.017
 Robert-0.017
Token its
Token ID663
Feature activation-1.54e-02

Pos logit contributions
Robert+0.061
jected+0.056
iable+0.054
 Robert+0.053
 Kyle+0.053
Neg logit contributions
ie-0.039
 roast-0.039
 sleep-0.038
 camp-0.037
ies-0.037
Token branches
Token ID13737
Feature activation+1.94e-02

Pos logit contributions
Robert+0.033
 Robert+0.029
iable+0.028
jected+0.028
 Kyle+0.028
Neg logit contributions
 roast-0.020
ies-0.020
 sleep-0.020
 ig-0.019
ie-0.019
Token take
Token ID1011
Feature activation-2.38e-03

Pos logit contributions
 roast+0.004
ina+0.004
ies+0.004
ie+0.004
 polar+0.004
Neg logit contributions
Robert-0.010
 Robert-0.009
Rober-0.009
ados-0.009
iable-0.009
Token one
Token ID530
Feature activation+1.70e-02

Pos logit contributions
jected+0.005
Robert+0.005
Rober+0.004
iable+0.004
 thirteen+0.004
Neg logit contributions
 sleep-0.003
 work-0.003
 camp-0.003
 roast-0.003
 polar-0.003
Token of
Token ID286
Feature activation+1.60e-02

Pos logit contributions
ie+0.019
 roast+0.018
ina+0.018
ies+0.018
 sleep+0.018
Neg logit contributions
Robert-0.038
 Robert-0.035
Rober-0.034
 Kyle-0.033
jected-0.033
Token the
Token ID262
Feature activation-1.22e-02

Pos logit contributions
 roast+0.022
 camp+0.021
 sleep+0.021
 polar+0.021
ie+0.021
Neg logit contributions
Robert-0.030
jected-0.028
iable-0.028
Rober-0.027
 thirteen-0.027
Token or
Token ID393
Feature activation-3.79e-02

Pos logit contributions
Robert+0.024
 Kyle+0.022
jected+0.022
iece+0.022
Luke+0.021
Neg logit contributions
 work-0.016
ies-0.016
ie-0.016
 plan-0.015
 sleep-0.015
Tokennam
Token ID7402
Feature activation-1.41e-01

Pos logit contributions
Robert+0.057
jected+0.053
Rober+0.050
ados+0.050
 thirteen+0.048
Neg logit contributions
 roast-0.067
 sleep-0.065
ies-0.064
ie-0.063
 scrub-0.063
Tokenents
Token ID658
Feature activation+2.21e-03

Pos logit contributions
Robert+0.203
 Robert+0.185
Rober+0.173
jected+0.172
 Kyle+0.171
Neg logit contributions
ies-0.257
ina-0.256
ie-0.252
 roast-0.249
aa-0.237
Token outside
Token ID2354
Feature activation+2.63e-02

Pos logit contributions
ie+0.003
ies+0.003
ina+0.003
 roast+0.002
 sleep+0.002
Neg logit contributions
Robert-0.005
 Robert-0.004
Rober-0.004
jected-0.004
 Kyle-0.004
Token for
Token ID329
Feature activation-9.63e-03

Pos logit contributions
ina+0.032
 roast+0.032
ie+0.032
ies+0.031
 sleep+0.031
Neg logit contributions
Robert-0.055
 Robert-0.049
Rober-0.049
iable-0.049
jected-0.048
Token a
Token ID257
Feature activation+5.96e-03

Pos logit contributions
Robert+0.017
jected+0.016
iable+0.015
Rober+0.015
ados+0.015
Neg logit contributions
 roast-0.015
 sleep-0.015
 camp-0.014
 scrub-0.014
 work-0.014
Token walk
Token ID2513
Feature activation+2.88e-02

Pos logit contributions
 roast+0.007
 sleep+0.007
 camp+0.007
ie+0.006
 scrub+0.006
Neg logit contributions
Robert-0.013
ados-0.012
jected-0.012
 Robert-0.012
 Kyle-0.011
Token a
Token ID257
Feature activation-2.75e-02

Pos logit contributions
Robert+0.060
Rober+0.054
jected+0.053
iable+0.053
 Robert+0.053
Neg logit contributions
 roast-0.049
 polar-0.049
ina-0.049
 camp-0.047
ie-0.047
Token tall
Token ID7331
Feature activation-3.11e-02

Pos logit contributions
Robert+0.050
 Robert+0.046
Rober+0.044
iable+0.043
 Jerry+0.042
Neg logit contributions
ina-0.039
 roast-0.039
ie-0.038
ies-0.038
 scrub-0.036
Token tree
Token ID5509
Feature activation-2.80e-02

Pos logit contributions
Robert+0.059
 Robert+0.054
Rober+0.052
ados+0.051
iable+0.051
Neg logit contributions
 roast-0.043
ina-0.043
ies-0.042
ie-0.041
 polar-0.041
Token.
Token ID13
Feature activation-7.21e-03

Pos logit contributions
Robert+0.053
 Robert+0.048
ados+0.046
Rober+0.046
iable+0.046
Neg logit contributions
 roast-0.038
ina-0.038
ies-0.037
ie-0.037
 polar-0.036
Token Un
Token ID791
Feature activation-3.65e-02

Pos logit contributions
Robert+0.010
 Robert+0.010
 Kyle+0.009
Rober+0.009
ados+0.008
Neg logit contributions
ies-0.013
ie-0.013
ina-0.013
 roast-0.013
 scrub-0.013
Tokenbek
Token ID47083
Feature activation-1.40e-01

Pos logit contributions
Robert+0.066
 Robert+0.061
ados+0.059
Rober+0.058
 thirteen+0.057
Neg logit contributions
ina-0.054
ies-0.052
ie-0.052
 roast-0.052
aa-0.050
Tokennow
Token ID2197
Feature activation+2.20e-02

Pos logit contributions
Robert+0.183
 Robert+0.150
Rober+0.147
iable+0.143
Terry+0.137
Neg logit contributions
ina-0.285
ies-0.274
 roast-0.273
ie-0.271
aa-0.267
Tokenst
Token ID301
Feature activation+4.57e-02

Pos logit contributions
 roast+0.029
ina+0.029
ies+0.028
ie+0.028
 polar+0.027
Neg logit contributions
Robert-0.043
 Robert-0.040
Rober-0.038
iable-0.038
ados-0.038
Token to
Token ID284
Feature activation+1.35e-02

Pos logit contributions
 roast+0.072
ina+0.068
 polar+0.067
ies+0.067
 scrub+0.065
Neg logit contributions
Robert-0.078
 Robert-0.071
iable-0.068
ados-0.068
Rober-0.067
Token him
Token ID683
Feature activation-9.75e-03

Pos logit contributions
 roast+0.019
 sleep+0.019
 camp+0.018
ina+0.018
 polar+0.018
Neg logit contributions
Robert-0.025
 Robert-0.023
jected-0.023
ados-0.023
Rober-0.022
Token,
Token ID11
Feature activation-3.78e-03

Pos logit contributions
Robert+0.017
 Robert+0.015
iable+0.014
ados+0.014
Rober+0.014
Neg logit contributions
 roast-0.015
ina-0.015
ies-0.015
 polar-0.014
ie-0.014
Token They
Token ID1119
Feature activation+1.02e-02

Pos logit contributions
Robert+0.017
 Robert+0.016
Rober+0.015
iable+0.015
ados+0.015
Neg logit contributions
 roast-0.011
ina-0.011
ies-0.011
ie-0.010
 polar-0.010
Token reached
Token ID4251
Feature activation+2.63e-02

Pos logit contributions
 roast+0.010
ina+0.010
ies+0.010
ie+0.010
 scrub+0.010
Neg logit contributions
Robert-0.023
ados-0.021
 Robert-0.021
Rober-0.021
iable-0.021
Token for
Token ID329
Feature activation-2.48e-02

Pos logit contributions
ina+0.041
ie+0.040
ies+0.039
aa+0.039
 polar+0.039
Neg logit contributions
Robert-0.041
 Robert-0.040
 Kyle-0.037
ados-0.036
 twelve-0.036
Token the
Token ID262
Feature activation-2.49e-02

Pos logit contributions
Robert+0.050
jected+0.049
iable+0.047
ados+0.046
iece+0.045
Neg logit contributions
 roast-0.033
 camp-0.031
 sleep-0.031
 polar-0.029
 scrub-0.029
Token or
Token ID393
Feature activation-4.44e-02

Pos logit contributions
Robert+0.049
 Kyle+0.046
jected+0.045
iable+0.044
 Robert+0.044
Neg logit contributions
ies-0.032
 roast-0.032
 work-0.031
ie-0.031
 camp-0.030
Tokennam
Token ID7402
Feature activation-1.40e-01

Pos logit contributions
Robert+0.039
ados+0.033
Rober+0.031
jected+0.030
 Robert+0.030
Neg logit contributions
 roast-0.107
 scrub-0.106
 sleep-0.103
ies-0.103
ina-0.102
Tokenents
Token ID658
Feature activation+2.96e-03

Pos logit contributions
Robert+0.194
 Robert+0.175
Rober+0.164
jected+0.161
iable+0.161
Neg logit contributions
ina-0.264
ies-0.264
 roast-0.261
ie-0.259
aa-0.248
Token and
Token ID290
Feature activation-8.11e-03

Pos logit contributions
ies+0.003
ie+0.003
ina+0.003
 roast+0.003
 sleep+0.003
Neg logit contributions
Robert-0.007
Rober-0.006
 Robert-0.006
jected-0.006
ados-0.006
Token touched
Token ID12615
Feature activation+4.99e-02

Pos logit contributions
Robert+0.020
Rober+0.018
iable+0.018
ados+0.018
jected+0.017
Neg logit contributions
 scrub-0.008
 roast-0.008
 sleep-0.007
 use-0.007
 called-0.007
Token them
Token ID606
Feature activation-1.04e-02

Pos logit contributions
 roast+0.059
ies+0.058
ina+0.057
ie+0.057
 polar+0.055
Neg logit contributions
Robert-0.107
jected-0.098
Rober-0.096
 Robert-0.095
iable-0.095
Token softly
Token ID26625
Feature activation+3.78e-02

Pos logit contributions
Robert+0.026
Rober+0.024
Terry+0.024
 Robert+0.023
Kyle+0.023
Neg logit contributions
ies-0.010
 sleep-0.009
 scrub-0.009
ie-0.009
 roast-0.009
Token to
Token ID284
Feature activation+1.92e-02

Pos logit contributions
 roast+0.007
ina+0.007
ies+0.006
ie+0.006
 polar+0.006
Neg logit contributions
Robert-0.008
 Robert-0.008
ados-0.007
Rober-0.007
iable-0.007
Token look
Token ID804
Feature activation+7.29e-03

Pos logit contributions
ina+0.017
ies+0.017
 roast+0.016
ie+0.016
 polar+0.015
Neg logit contributions
Robert-0.045
 Robert-0.043
 Kyle-0.041
 Jerry-0.041
iable-0.041
Token at
Token ID379
Feature activation-2.25e-02

Pos logit contributions
 roast+0.011
ina+0.011
ies+0.011
ie+0.011
 polar+0.011
Neg logit contributions
Robert-0.013
 Robert-0.011
Rober-0.011
ados-0.011
iable-0.011
Token the
Token ID262
Feature activation+1.98e-03

Pos logit contributions
Robert+0.038
 Robert+0.034
ados+0.033
Rober+0.032
iable+0.032
Neg logit contributions
 roast-0.036
ina-0.036
ies-0.035
ie-0.034
 polar-0.034
Token or
Token ID393
Feature activation-4.01e-02

Pos logit contributions
ina+0.002
 roast+0.002
ies+0.002
 polar+0.002
 camp+0.002
Neg logit contributions
Robert-0.004
 Robert-0.004
jected-0.004
iable-0.004
Rober-0.004
Tokennam
Token ID7402
Feature activation-1.39e-01

Pos logit contributions
Robert+0.045
 Robert+0.038
ados+0.036
jected+0.036
Rober+0.036
Neg logit contributions
 roast-0.087
ina-0.085
ies-0.085
ie-0.085
 sleep-0.083
Tokenents
Token ID658
Feature activation+1.21e-02

Pos logit contributions
Robert+0.198
 Robert+0.181
Rober+0.170
ados+0.169
jected+0.167
Neg logit contributions
ina-0.255
ies-0.254
ie-0.250
 roast-0.248
aa-0.234
Token on
Token ID319
Feature activation-1.82e-02

Pos logit contributions
ie+0.015
ies+0.015
ina+0.015
 roast+0.014
 sleep+0.013
Neg logit contributions
Robert-0.026
 Robert-0.024
Rober-0.024
 Kyle-0.023
Terry-0.023
Token the
Token ID262
Feature activation-5.33e-03

Pos logit contributions
jected+0.044
Robert+0.041
iable+0.039
iece+0.038
Rober+0.037
Neg logit contributions
 work-0.017
 camp-0.017
ie-0.016
 sleep-0.016
ies-0.016
Token tree
Token ID5509
Feature activation+3.01e-02

Pos logit contributions
Robert+0.012
jected+0.011
 Kyle+0.011
Terry+0.011
Kyle+0.011
Neg logit contributions
 sleep-0.006
 ig-0.005
ie-0.005
 roast-0.005
 camp-0.005
Token.
Token ID13
Feature activation-2.95e-03

Pos logit contributions
ina+0.034
 roast+0.034
ie+0.034
ies+0.033
 sleep+0.032
Neg logit contributions
Robert-0.066
 Robert-0.060
Rober-0.060
ados-0.058
iable-0.058
Token big
Token ID1263
Feature activation-1.77e-02

Pos logit contributions
ina+0.004
 roast+0.004
ie+0.004
ies+0.004
 scrub+0.004
Neg logit contributions
Robert-0.005
 Robert-0.005
Rober-0.004
iable-0.004
ados-0.004
Token tree
Token ID5509
Feature activation-5.01e-03

Pos logit contributions
Robert+0.033
 Robert+0.031
ados+0.029
Rober+0.029
iable+0.029
Neg logit contributions
ina-0.025
 roast-0.025
ies-0.024
ie-0.024
 polar-0.023
Token with
Token ID351
Feature activation-3.53e-02

Pos logit contributions
Robert+0.009
 Robert+0.008
Rober+0.008
ados+0.008
iable+0.008
Neg logit contributions
 roast-0.007
ina-0.007
ies-0.007
ie-0.007
 polar-0.007
Token many
Token ID867
Feature activation-4.64e-02

Pos logit contributions
Robert+0.069
iable+0.066
jected+0.064
Rober+0.063
 Robert+0.060
Neg logit contributions
 roast-0.051
 polar-0.050
 ig-0.049
 Ch-0.047
 camp-0.046
Token or
Token ID393
Feature activation-4.30e-02

Pos logit contributions
Robert+0.081
 Robert+0.074
Rober+0.070
iable+0.070
ados+0.070
Neg logit contributions
 roast-0.071
ina-0.070
ies-0.069
ie-0.068
 polar-0.067
Tokennam
Token ID7402
Feature activation-1.39e-01

Pos logit contributions
Robert+0.075
jected+0.070
iable+0.067
Rober+0.065
 Robert+0.065
Neg logit contributions
 roast-0.071
 polar-0.067
ies-0.066
 sleep-0.066
 camp-0.066
Tokenents
Token ID658
Feature activation+3.54e-03

Pos logit contributions
Robert+0.191
 Robert+0.171
Rober+0.160
iable+0.158
jected+0.158
Neg logit contributions
ina-0.263
ies-0.263
 roast-0.261
ie-0.257
 polar-0.248
Token on
Token ID319
Feature activation-2.37e-02

Pos logit contributions
ies+0.004
ie+0.004
ina+0.004
 roast+0.004
 sleep+0.004
Neg logit contributions
Robert-0.008
 Robert-0.007
Rober-0.007
jected-0.007
iable-0.007
Token it
Token ID340
Feature activation+8.82e-03

Pos logit contributions
Robert+0.049
jected+0.048
iable+0.047
Rober+0.044
iece+0.043
Neg logit contributions
 roast-0.029
 camp-0.029
 sleep-0.028
 work-0.027
 ig-0.026
Token.
Token ID13
Feature activation+4.37e-03

Pos logit contributions
ina+0.010
 roast+0.009
ies+0.009
ie+0.009
 sleep+0.009
Neg logit contributions
Robert-0.020
 Robert-0.018
Rober-0.018
jected-0.017
iable-0.017
Token The
Token ID383
Feature activation+2.15e-02

Pos logit contributions
 roast+0.006
ina+0.006
ies+0.006
ie+0.006
 polar+0.005
Neg logit contributions
Robert-0.008
 Robert-0.008
iable-0.008
jected-0.007
ados-0.007
Token also
Token ID635
Feature activation+4.41e-02

Pos logit contributions
 roast+0.007
ina+0.006
ies+0.006
ie+0.006
 polar+0.006
Neg logit contributions
Robert-0.013
 Robert-0.012
ados-0.012
Rober-0.012
iable-0.012
Token saw
Token ID2497
Feature activation-3.25e-02

Pos logit contributions
 roast+0.045
ina+0.045
ies+0.043
ie+0.043
 polar+0.042
Neg logit contributions
Robert-0.099
 Robert-0.092
Rober-0.089
iable-0.088
ados-0.088
Token some
Token ID617
Feature activation+9.17e-04

Pos logit contributions
Robert+0.059
jected+0.054
Rober+0.052
iable+0.052
 Robert+0.051
Neg logit contributions
 polar-0.049
 roast-0.049
ies-0.048
ina-0.047
 camp-0.047
Token new
Token ID649
Feature activation-4.42e-02

Pos logit contributions
 roast+0.001
ina+0.001
ies+0.001
ie+0.001
 polar+0.001
Neg logit contributions
Robert-0.002
 Robert-0.001
ados-0.001
iable-0.001
Rober-0.001
Token or
Token ID393
Feature activation-4.14e-02

Pos logit contributions
Robert+0.072
 Robert+0.067
ados+0.066
 Kyle+0.061
Rober+0.060
Neg logit contributions
 roast-0.069
ina-0.066
aa-0.065
 polar-0.063
 scrub-0.062
Tokennam
Token ID7402
Feature activation-1.39e-01

Pos logit contributions
Robert+0.047
 Robert+0.039
jected+0.039
Rober+0.038
ados+0.038
Neg logit contributions
ies-0.090
 roast-0.089
ina-0.087
ie-0.087
 scrub-0.086
Tokenents
Token ID658
Feature activation+1.16e-03

Pos logit contributions
Robert+0.183
 Robert+0.162
Rober+0.152
iable+0.150
ados+0.150
Neg logit contributions
ina-0.271
 roast-0.270
ies-0.268
ie-0.264
 polar-0.258
Token that
Token ID326
Feature activation+6.28e-02

Pos logit contributions
ies+0.001
ie+0.001
ina+0.001
 roast+0.001
 sleep+0.001
Neg logit contributions
Robert-0.003
Rober-0.002
 Robert-0.002
jected-0.002
iable-0.002
Token Santa
Token ID8909
Feature activation-9.75e-03

Pos logit contributions
 roast+0.074
ina+0.073
ies+0.072
ie+0.070
 camp+0.068
Neg logit contributions
Robert-0.134
Rober-0.121
jected-0.121
iable-0.120
ados-0.119
Token had
Token ID550
Feature activation-2.83e-02

Pos logit contributions
Robert+0.020
 Robert+0.018
Rober+0.017
ados+0.017
iable+0.017
Neg logit contributions
ina-0.012
 roast-0.012
ies-0.012
ie-0.012
 polar-0.012
Token hung
Token ID9174
Feature activation+1.37e-02

Pos logit contributions
Robert+0.051
Rober+0.046
ados+0.046
jected+0.046
 Robert+0.046
Neg logit contributions
 roast-0.041
ina-0.041
ies-0.041
 sleep-0.039
 polar-0.039
Token a
Token ID257
Feature activation+6.43e-03

Pos logit contributions
Robert+0.062
 Robert+0.056
ados+0.055
jected+0.055
iable+0.055
Neg logit contributions
 roast-0.050
 scrub-0.048
 sleep-0.047
ina-0.047
ies-0.047
Token box
Token ID3091
Feature activation-5.75e-02

Pos logit contributions
ina+0.009
 roast+0.009
ies+0.009
ie+0.009
 polar+0.008
Neg logit contributions
Robert-0.012
 Robert-0.011
Rober-0.010
iable-0.010
ados-0.010
Token of
Token ID286
Feature activation-7.80e-03

Pos logit contributions
Robert+0.119
 Robert+0.110
Rober+0.106
ados+0.106
iable+0.106
Neg logit contributions
 roast-0.069
ina-0.069
ies-0.068
ie-0.066
 polar-0.064
Token shiny
Token ID22441
Feature activation-1.22e-02

Pos logit contributions
Robert+0.013
 Robert+0.012
ados+0.011
Rober+0.011
iable+0.011
Neg logit contributions
ina-0.013
 roast-0.012
ies-0.012
aa-0.012
ie-0.012
Token or
Token ID393
Feature activation-3.44e-02

Pos logit contributions
Robert+0.020
 Robert+0.018
Rober+0.017
iable+0.017
jected+0.017
Neg logit contributions
 roast-0.020
ies-0.020
ina-0.020
ie-0.019
 polar-0.019
Tokennam
Token ID7402
Feature activation-1.39e-01

Pos logit contributions
Robert+0.047
Rober+0.040
jected+0.040
 Robert+0.040
iable+0.039
Neg logit contributions
 roast-0.067
ies-0.066
ina-0.066
 scrub-0.065
 sleep-0.064
Tokenents
Token ID658
Feature activation+7.26e-03

Pos logit contributions
Robert+0.196
 Robert+0.177
Rober+0.165
iable+0.163
jected+0.163
Neg logit contributions
ina-0.258
ies-0.258
 roast-0.254
ie-0.252
aa-0.239
Token that
Token ID326
Feature activation+7.10e-02

Pos logit contributions
ina+0.008
ies+0.008
ie+0.008
 roast+0.008
 sleep+0.007
Neg logit contributions
Robert-0.017
Rober-0.015
 Robert-0.015
 Kyle-0.015
jected-0.014
Token spark
Token ID9009
Feature activation+1.75e-02

Pos logit contributions
ina+0.091
 roast+0.085
ie+0.085
ies+0.084
 sleep+0.081
Neg logit contributions
Robert-0.150
Rober-0.134
ados-0.131
 Robert-0.131
jected-0.130
Tokenled
Token ID992
Feature activation-3.07e-03

Pos logit contributions
ies+0.028
ina+0.028
ie+0.028
 roast+0.026
aa+0.025
Neg logit contributions
Robert-0.031
 Robert-0.027
Rober-0.027
iable-0.026
Terry-0.026
Token in
Token ID287
Feature activation+1.98e-02

Pos logit contributions
Robert+0.007
Rober+0.007
iable+0.007
jected+0.007
Mic+0.006
Neg logit contributions
ies-0.003
ie-0.003
ina-0.003
 sleep-0.003
 scrub-0.003
Token and
Token ID290
Feature activation+1.84e-03

Pos logit contributions
Robert+0.133
Rober+0.123
 Robert+0.119
iable+0.117
jected+0.117
Neg logit contributions
ies-0.072
ina-0.071
ie-0.068
 roast-0.064
 camp-0.060
Token lots
Token ID6041
Feature activation-3.17e-02

Pos logit contributions
 roast+0.002
ina+0.002
ies+0.002
 polar+0.002
 sleep+0.002
Neg logit contributions
Robert-0.004
jected-0.003
Rober-0.003
iable-0.003
ados-0.003
Token of
Token ID286
Feature activation+1.79e-03

Pos logit contributions
Robert+0.082
Rober+0.077
 Robert+0.075
iable+0.075
jected+0.075
Neg logit contributions
ies-0.023
ie-0.023
ina-0.022
 roast-0.021
 sleep-0.021
Token shiny
Token ID22441
Feature activation-5.56e-03

Pos logit contributions
ies+0.002
 roast+0.002
ie+0.002
ina+0.002
 polar+0.002
Neg logit contributions
Robert-0.004
 Robert-0.003
jected-0.003
iable-0.003
Rober-0.003
Token or
Token ID393
Feature activation-2.84e-02

Pos logit contributions
Robert+0.010
 Robert+0.008
jected+0.008
Rober+0.008
iable+0.008
Neg logit contributions
ies-0.009
ie-0.009
ina-0.009
 roast-0.009
 polar-0.009
Tokennam
Token ID7402
Feature activation-1.38e-01

Pos logit contributions
Robert+0.059
jected+0.056
Rober+0.054
ados+0.053
iable+0.052
Neg logit contributions
ies-0.034
 roast-0.034
 polar-0.034
ina-0.032
 sleep-0.032
Tokenents
Token ID658
Feature activation+1.23e-04

Pos logit contributions
Robert+0.192
 Robert+0.171
Rober+0.161
jected+0.158
iable+0.158
Neg logit contributions
ina-0.263
ies-0.262
 roast-0.259
ie-0.256
 polar-0.247
Token.
Token ID13
Feature activation+2.88e-03

Pos logit contributions
ies+0.000
ie+0.000
ina+0.000
 roast+0.000
 polar+0.000
Neg logit contributions
Robert-0.000
Rober-0.000
 Robert-0.000
jected-0.000
ados-0.000
Token L
Token ID406
Feature activation+2.10e-02

Pos logit contributions
 roast+0.004
ies+0.004
ie+0.004
ina+0.003
 polar+0.003
Neg logit contributions
Robert-0.006
 Robert-0.005
 Kyle-0.005
Rober-0.005
ados-0.005
Tokenila
Token ID10102
Feature activation+2.31e-02

Pos logit contributions
 roast+0.025
 polar+0.024
 sleep+0.023
 camp+0.023
ies+0.022
Neg logit contributions
Robert-0.044
 Robert-0.040
iable-0.040
Rober-0.040
 Kyle-0.039
Token wanted
Token ID2227
Feature activation-2.17e-02

Pos logit contributions
ina+0.024
 roast+0.024
ies+0.023
ie+0.023
 polar+0.022
Neg logit contributions
Robert-0.052
 Robert-0.048
ados-0.047
Rober-0.047
iable-0.046
Token It
Token ID632
Feature activation+1.64e-02

Pos logit contributions
Robert+0.004
 Robert+0.004
iable+0.004
Rober+0.004
jected+0.004
Neg logit contributions
 roast-0.005
ina-0.004
 sleep-0.004
 polar-0.004
ies-0.004
Token was
Token ID373
Feature activation+7.08e-04

Pos logit contributions
aa+0.028
iona+0.027
ies+0.026
ucks+0.026
ina+0.026
Neg logit contributions
jected-0.023
Robert-0.020
 Robert-0.020
 thirteen-0.019
aw-0.018
Token the
Token ID262
Feature activation-5.34e-03

Pos logit contributions
ies+0.001
ie+0.001
ina+0.001
aa+0.001
ucks+0.001
Neg logit contributions
Robert-0.001
 Robert-0.001
 Jerry-0.001
 thirteen-0.001
 twelve-0.001
Token deepest
Token ID25420
Feature activation+1.75e-02

Pos logit contributions
Robert+0.011
ados+0.010
 Robert+0.010
iable+0.010
Rober+0.010
Neg logit contributions
 roast-0.007
ina-0.007
 polar-0.006
ies-0.006
 camp-0.006
Token sea
Token ID5417
Feature activation-2.42e-02

Pos logit contributions
ina+0.024
 roast+0.023
ies+0.022
 scrub+0.022
ie+0.022
Neg logit contributions
Robert-0.032
 Robert-0.030
 thirteen-0.028
 Kyle-0.028
ados-0.028
Token that
Token ID326
Feature activation+7.46e-02

Pos logit contributions
Robert+0.045
 Robert+0.041
ados+0.039
iable+0.039
Rober+0.039
Neg logit contributions
 roast-0.034
ina-0.033
ies-0.032
ie-0.032
 polar-0.032
Token anyone
Token ID2687
Feature activation-2.81e-03

Pos logit contributions
 roast+0.084
ina+0.083
ies+0.081
ie+0.080
 polar+0.079
Neg logit contributions
Robert-0.156
 Robert-0.147
jected-0.139
ados-0.139
Rober-0.138
Token had
Token ID550
Feature activation-2.16e-02

Pos logit contributions
Robert+0.004
 Robert+0.003
jected+0.003
aw+0.003
iable+0.003
Neg logit contributions
 roast-0.005
ucks-0.005
imi-0.005
 polar-0.005
 camp-0.005
Token ever
Token ID1683
Feature activation-4.59e-02

Pos logit contributions
Robert+0.035
 Robert+0.031
Rober+0.029
iable+0.029
jected+0.029
Neg logit contributions
 roast-0.036
ina-0.036
ies-0.035
ie-0.035
 polar-0.034
Token seen
Token ID1775
Feature activation-1.22e-02

Pos logit contributions
Robert+0.079
 Robert+0.072
iable+0.069
jected+0.068
Terry+0.067
Neg logit contributions
ina-0.068
 roast-0.067
aa-0.064
ie-0.063
ies-0.063
Token.
Token ID13
Feature activation-9.71e-03

Pos logit contributions
Robert+0.025
 Robert+0.023
Rober+0.022
iable+0.022
ados+0.022
Neg logit contributions
ina-0.015
 roast-0.015
ie-0.015
ies-0.015
 sleep-0.014
Token to
Token ID284
Feature activation+1.62e-02

Pos logit contributions
ies+0.049
ie+0.048
 roast+0.046
 polar+0.045
ina+0.044
Neg logit contributions
Robert-0.111
Rober-0.104
jected-0.103
iable-0.098
 thirteen-0.098
Token help
Token ID1037
Feature activation+3.70e-02

Pos logit contributions
ina+0.020
ies+0.019
ucks+0.018
aa+0.018
 roast+0.018
Neg logit contributions
Robert-0.031
 Jerry-0.029
 Robert-0.029
iable-0.029
Terry-0.027
Token any
Token ID597
Feature activation+6.85e-03

Pos logit contributions
 roast+0.060
ina+0.059
ies+0.058
ie+0.056
 polar+0.056
Neg logit contributions
Robert-0.061
 Robert-0.056
ados-0.053
iable-0.053
 Jerry-0.052
Token harmless
Token ID23585
Feature activation+1.88e-02

Pos logit contributions
 roast+0.011
ina+0.011
ies+0.010
ie+0.010
 polar+0.010
Neg logit contributions
Robert-0.012
 Robert-0.011
ados-0.010
iable-0.010
Rober-0.010
Token creatures
Token ID8109
Feature activation-3.81e-03

Pos logit contributions
ies+0.024
ie+0.023
ina+0.023
 roast+0.023
 polar+0.022
Neg logit contributions
Robert-0.040
 Robert-0.036
Rober-0.035
jected-0.034
iable-0.034
Token that
Token ID326
Feature activation+7.65e-02

Pos logit contributions
Robert+0.008
 Robert+0.007
Rober+0.007
ados+0.007
jected+0.007
Neg logit contributions
 roast-0.005
ina-0.005
ie-0.005
ies-0.005
 sleep-0.005
Token he
Token ID339
Feature activation+6.55e-03

Pos logit contributions
ina+0.086
 roast+0.086
ie+0.085
ies+0.084
 sleep+0.081
Neg logit contributions
Robert-0.168
Rober-0.152
 Robert-0.151
ados-0.148
jected-0.147
Token found
Token ID1043
Feature activation-3.29e-03

Pos logit contributions
 roast+0.010
ina+0.009
 polar+0.009
ies+0.009
ucks+0.009
Neg logit contributions
Robert-0.011
jected-0.011
iable-0.011
 Robert-0.011
 Jerry-0.010
Token.
Token ID13
Feature activation+3.25e-03

Pos logit contributions
Robert+0.007
Rober+0.007
 Robert+0.006
iable+0.006
jected+0.006
Neg logit contributions
ie-0.004
ies-0.004
ina-0.004
 sleep-0.004
 polar-0.004
Token<|endoftext|>
Token ID50256
Feature activation+4.45e-02

Pos logit contributions
 roast+0.005
ina+0.005
ies+0.005
ie+0.005
 polar+0.005
Neg logit contributions
Robert-0.005
 Robert-0.005
Rober-0.005
iable-0.005
ados-0.005
TokenOnce
Token ID7454
Feature activation+2.48e-02

Pos logit contributions
 roast+0.063
ies+0.063
ina+0.063
ie+0.061
 polar+0.060
Neg logit contributions
Robert-0.083
 Robert-0.076
Rober-0.072
 Kyle-0.071
 Jerry-0.071
Token.
Token ID13
Feature activation-8.81e-03

Pos logit contributions
Robert+0.018
Rober+0.016
 Robert+0.016
iable+0.016
ados+0.015
Neg logit contributions
ina-0.010
 roast-0.010
ie-0.010
ies-0.010
 sleep-0.009
Token Then
Token ID3244
Feature activation+4.46e-03

Pos logit contributions
Robert+0.016
iable+0.016
 thirteen+0.016
jected+0.016
 eighteen+0.016
Neg logit contributions
 sleep-0.012
 roast-0.011
 scrub-0.011
ina-0.011
 camp-0.010
Token he
Token ID339
Feature activation-2.19e-02

Pos logit contributions
 sleep+0.005
ina+0.005
 roast+0.005
ies+0.005
 work+0.005
Neg logit contributions
Robert-0.009
Rober-0.008
 thirteen-0.008
jected-0.008
iable-0.008
Token wrote
Token ID2630
Feature activation-2.94e-02

Pos logit contributions
Robert+0.042
 Robert+0.039
iable+0.037
jected+0.037
Rober+0.037
Neg logit contributions
 roast-0.029
ina-0.028
ies-0.027
 polar-0.027
ie-0.027
Token his
Token ID465
Feature activation-9.36e-03

Pos logit contributions
Robert+0.059
jected+0.054
ados+0.054
Rober+0.054
iable+0.052
Neg logit contributions
ina-0.035
ies-0.034
ie-0.033
 roast-0.032
 scrub-0.031
Token name
Token ID1438
Feature activation+7.37e-02

Pos logit contributions
Robert+0.025
 Robert+0.023
Rober+0.022
iable+0.022
ados+0.022
Neg logit contributions
ina-0.006
 roast-0.006
ies-0.006
 sleep-0.006
ie-0.006
Token inside
Token ID2641
Feature activation+2.69e-02

Pos logit contributions
ina+0.080
ie+0.079
ies+0.070
 sleep+0.069
 roast+0.068
Neg logit contributions
Robert-0.160
Rober-0.150
Terry-0.144
ados-0.144
iable-0.143
Token the
Token ID262
Feature activation+5.84e-03

Pos logit contributions
ie+0.034
ina+0.034
 roast+0.034
ies+0.033
 sleep+0.033
Neg logit contributions
Robert-0.054
jected-0.049
Rober-0.048
 Robert-0.048
iable-0.047
Token circle
Token ID9197
Feature activation+2.50e-02

Pos logit contributions
ina+0.007
 roast+0.007
 sleep+0.007
 work+0.007
 design+0.007
Neg logit contributions
Robert-0.012
Rober-0.011
 Robert-0.011
ados-0.011
iable-0.011
Token.
Token ID13
Feature activation+1.36e-03

Pos logit contributions
ina+0.028
ie+0.027
ies+0.026
 roast+0.026
 sleep+0.026
Neg logit contributions
Robert-0.057
Rober-0.054
iable-0.051
 Robert-0.051
jected-0.050
Token
Token ID198
Feature activation-2.68e-03

Pos logit contributions
ina+0.002
 sleep+0.002
 roast+0.002
 scrub+0.002
 camp+0.002
Neg logit contributions
Robert-0.003
 thirteen-0.002
iable-0.002
ados-0.002
 eighteen-0.002
Token little
Token ID1310
Feature activation+3.89e-02

Pos logit contributions
 roast+0.001
ina+0.000
ies+0.000
ie+0.000
 polar+0.000
Neg logit contributions
Robert-0.001
 Robert-0.001
Rober-0.001
iable-0.001
ados-0.001
Token girl
Token ID2576
Feature activation+9.28e-03

Pos logit contributions
 roast+0.041
ina+0.039
ies+0.037
 polar+0.036
 scrub+0.036
Neg logit contributions
Robert-0.087
 Robert-0.081
ados-0.078
Rober-0.078
 Kyle-0.077
Token.
Token ID13
Feature activation-6.18e-03

Pos logit contributions
 roast+0.014
ina+0.013
ies+0.013
 polar+0.013
 camp+0.013
Neg logit contributions
Robert-0.016
 Robert-0.015
ados-0.014
iable-0.014
jected-0.014
Token "
Token ID366
Feature activation-2.79e-02

Pos logit contributions
Robert+0.013
iable+0.012
jected+0.012
 thirteen+0.012
 eighteen+0.012
Neg logit contributions
 Ch-0.007
 roast-0.007
ina-0.007
aa-0.007
 sleep-0.007
TokenMe
Token ID5308
Feature activation-4.98e-02

Pos logit contributions
Robert+0.047
 Robert+0.043
ados+0.042
iable+0.041
Rober+0.041
Neg logit contributions
 roast-0.044
ina-0.044
ie-0.041
ies-0.041
 scrub-0.041
Token too
Token ID1165
Feature activation+8.11e-02

Pos logit contributions
Robert+0.083
 Robert+0.077
iable+0.073
ados+0.072
Rober+0.072
Neg logit contributions
 roast-0.079
ina-0.077
 polar-0.076
 scrub-0.075
ie-0.075
Token!"
Token ID2474
Feature activation-3.59e-02

Pos logit contributions
 roast+0.127
 polar+0.120
ina+0.120
ie+0.117
ies+0.116
Neg logit contributions
Robert-0.140
 Robert-0.131
Rober-0.124
jected-0.119
 Jerry-0.119
Token bark
Token ID21405
Feature activation+4.47e-02

Pos logit contributions
Robert+0.076
iable+0.070
 thirteen+0.070
Rober+0.069
 Robert+0.068
Neg logit contributions
 roast-0.042
ina-0.041
 sleep-0.041
ies-0.039
ie-0.039
Tokened
Token ID276
Feature activation-3.58e-02

Pos logit contributions
ina+0.078
aa+0.078
ie+0.077
ies+0.077
 Ch+0.075
Neg logit contributions
Robert-0.069
ados-0.059
iable-0.059
 Robert-0.059
Rober-0.057
Token the
Token ID262
Feature activation-3.41e-03

Pos logit contributions
Robert+0.076
iable+0.068
jected+0.067
 Robert+0.066
ados+0.066
Neg logit contributions
ie-0.043
ies-0.043
 sleep-0.042
ina-0.041
 roast-0.041
Token dog
Token ID3290
Feature activation+3.21e-03

Pos logit contributions
Robert+0.007
 Robert+0.006
ados+0.006
iable+0.006
Rober+0.006
Neg logit contributions
 roast-0.004
ina-0.004
ies-0.004
ie-0.004
 polar-0.004
Token time
Token ID640
Feature activation+4.04e-03

Pos logit contributions
Robert+0.050
 Robert+0.047
 Jerry+0.044
Rober+0.043
iable+0.042
Neg logit contributions
ina-0.046
ies-0.043
 polar-0.043
 Ch-0.042
ie-0.042
Token.
Token ID13
Feature activation+1.95e-02

Pos logit contributions
ina+0.006
 roast+0.006
ies+0.005
ie+0.005
 polar+0.005
Neg logit contributions
Robert-0.008
 Robert-0.007
ados-0.007
Rober-0.007
iable-0.007
Token
Token ID198
Feature activation+8.16e-03

Pos logit contributions
 roast+0.027
ina+0.027
ies+0.026
ie+0.026
 polar+0.026
Neg logit contributions
Robert-0.037
 Robert-0.034
iable-0.033
Rober-0.033
ados-0.032
Token
Token ID198
Feature activation+2.68e-03

Pos logit contributions
ies+0.015
ina+0.015
ie+0.014
 roast+0.014
 polar+0.013
Neg logit contributions
Robert-0.013
 Jerry-0.011
 Robert-0.011
Terry-0.010
Rober-0.010
TokenFrom
Token ID4863
Feature activation-5.36e-02

Pos logit contributions
 roast+0.005
ina+0.004
 scrub+0.004
ie+0.004
 polar+0.004
Neg logit contributions
Robert-0.004
 Robert-0.004
ados-0.004
 Kyle-0.004
iable-0.004
Token that
Token ID326
Feature activation+1.07e-01

Pos logit contributions
Robert+0.089
 Robert+0.081
iable+0.077
ados+0.076
Rober+0.076
Neg logit contributions
 roast-0.087
ina-0.086
ies-0.085
ie-0.083
 polar-0.083
Token day
Token ID1110
Feature activation+6.08e-02

Pos logit contributions
 roast+0.081
ies+0.079
 polar+0.078
ina+0.077
aa+0.070
Neg logit contributions
Robert-0.266
 Robert-0.252
jected-0.244
 Jerry-0.241
iable-0.239
Token on
Token ID319
Feature activation+2.33e-03

Pos logit contributions
 roast+0.072
aa+0.071
ies+0.070
ie+0.070
ina+0.070
Neg logit contributions
Robert-0.128
 Robert-0.117
Rober-0.115
iable-0.113
 thirteen-0.110
Token,
Token ID11
Feature activation+2.43e-02

Pos logit contributions
ie+0.003
 roast+0.003
ies+0.003
ina+0.003
 camp+0.003
Neg logit contributions
Robert-0.005
iable-0.004
Rober-0.004
 Robert-0.004
jected-0.004
Token Kitty
Token ID21168
Feature activation+5.56e-02

Pos logit contributions
 roast+0.036
ies+0.035
ina+0.035
ie+0.035
 camp+0.034
Neg logit contributions
Robert-0.044
 Robert-0.040
iable-0.039
Rober-0.038
jected-0.038
Token was
Token ID373
Feature activation+1.35e-02

Pos logit contributions
 roast+0.075
ina+0.073
ies+0.072
 polar+0.071
ie+0.070
Neg logit contributions
Robert-0.105
 Robert-0.097
jected-0.093
ados-0.093
iable-0.092
Token she
Token ID673
Feature activation+6.60e-03

Pos logit contributions
Robert+0.031
 Robert+0.028
Rober+0.028
ados+0.027
iable+0.027
Neg logit contributions
 roast-0.020
ina-0.020
ies-0.019
ie-0.019
 polar-0.019
Token really
Token ID1107
Feature activation+3.76e-02

Pos logit contributions
 roast+0.008
ina+0.008
ies+0.007
 polar+0.007
ie+0.007
Neg logit contributions
Robert-0.014
 Robert-0.013
Rober-0.012
iable-0.012
jected-0.012
Token liked
Token ID8288
Feature activation-2.08e-02

Pos logit contributions
 roast+0.042
ina+0.041
ies+0.040
ie+0.039
 polar+0.039
Neg logit contributions
Robert-0.081
 Robert-0.075
Rober-0.072
iable-0.072
ados-0.072
Token playing
Token ID2712
Feature activation+3.61e-02

Pos logit contributions
Robert+0.040
 Robert+0.037
Rober+0.035
iable+0.035
jected+0.035
Neg logit contributions
 roast-0.028
ina-0.028
ies-0.027
ie-0.027
 polar-0.026
Token with
Token ID351
Feature activation-2.68e-02

Pos logit contributions
 roast+0.048
ina+0.048
ie+0.046
ies+0.046
 sleep+0.046
Neg logit contributions
Robert-0.071
 Robert-0.065
Rober-0.062
jected-0.062
iable-0.062
Token it
Token ID340
Feature activation+1.74e-02

Pos logit contributions
Robert+0.051
jected+0.046
 Robert+0.046
Rober+0.046
iable+0.045
Neg logit contributions
 roast-0.037
ie-0.037
ina-0.037
ies-0.037
 polar-0.036
Token.
Token ID13
Feature activation+7.66e-04

Pos logit contributions
ie+0.021
ina+0.021
ies+0.021
 roast+0.020
 sleep+0.020
Neg logit contributions
Robert-0.037
 Robert-0.033
Rober-0.033
ados-0.032
iable-0.032
Token One
Token ID1881
Feature activation+6.81e-02

Pos logit contributions
 roast+0.001
ina+0.001
ie+0.001
ies+0.001
 polar+0.001
Neg logit contributions
Robert-0.001
 Robert-0.001
iable-0.001
jected-0.001
ados-0.001
Token day
Token ID1110
Feature activation+9.61e-03

Pos logit contributions
 roast+0.065
ucks+0.062
 polar+0.059
ina+0.058
ies+0.057
Neg logit contributions
Robert-0.146
 Robert-0.141
 Jerry-0.135
jected-0.134
iable-0.131
Token,
Token ID11
Feature activation-1.57e-02

Pos logit contributions
ies+0.011
ina+0.011
 roast+0.010
ie+0.010
 camp+0.010
Neg logit contributions
Robert-0.021
jected-0.020
iable-0.019
 thirteen-0.019
Rober-0.019
Token when
Token ID618
Feature activation+2.18e-02

Pos logit contributions
Robert+0.030
jected+0.029
 thirteen+0.028
iable+0.027
Rober+0.027
Neg logit contributions
ina-0.021
 roast-0.021
ies-0.021
ie-0.021
 camp-0.020
Token very
Token ID845
Feature activation-1.47e-03

Pos logit contributions
Robert+0.042
 Robert+0.040
 Jerry+0.038
Rober+0.035
Terry+0.035
Neg logit contributions
ina-0.053
ie-0.052
 roast-0.051
 scrub-0.051
ies-0.050
Token happy
Token ID3772
Feature activation-3.82e-02

Pos logit contributions
Robert+0.002
 Robert+0.002
Rober+0.002
 Jerry+0.002
Terry+0.002
Neg logit contributions
ina-0.003
 roast-0.002
ie-0.002
 scrub-0.002
 ig-0.002
Token living
Token ID2877
Feature activation+2.71e-02

Pos logit contributions
Robert+0.062
 Robert+0.059
ados+0.056
 Jerry+0.055
 Kyle+0.053
Neg logit contributions
 roast-0.061
 polar-0.058
ina-0.057
 scrub-0.056
aa-0.056
Token on
Token ID319
Feature activation-8.07e-03

Pos logit contributions
 roast+0.044
ina+0.043
 polar+0.042
ie+0.041
aa+0.041
Neg logit contributions
Robert-0.045
 Robert-0.041
ados-0.039
Rober-0.038
jected-0.037
Token the
Token ID262
Feature activation-5.22e-03

Pos logit contributions
Robert+0.015
 Robert+0.013
jected+0.013
iable+0.013
ados+0.013
Neg logit contributions
 roast-0.012
ina-0.011
ies-0.011
 camp-0.011
 sleep-0.011
Token farm
Token ID5318
Feature activation+3.07e-02

Pos logit contributions
Robert+0.012
 Robert+0.011
ados+0.011
Rober+0.011
iable+0.011
Neg logit contributions
ina-0.005
 roast-0.005
ies-0.005
ie-0.005
 polar-0.005
Token.
Token ID13
Feature activation+4.61e-03

Pos logit contributions
 roast+0.039
ina+0.038
ies+0.038
ie+0.037
 sleep+0.036
Neg logit contributions
Robert-0.063
 Robert-0.057
Rober-0.056
iable-0.055
ados-0.055
Token
Token ID198
Feature activation-1.26e-02

Pos logit contributions
ies+0.008
ina+0.008
ie+0.008
 scrub+0.007
 roast+0.007
Neg logit contributions
Robert-0.008
 Robert-0.007
 Jerry-0.007
 Kyle-0.006
Rober-0.006
Token
Token ID198
Feature activation-1.66e-02

Pos logit contributions
Robert+0.014
 Robert+0.011
Terry+0.010
 Jerry+0.010
Rober+0.010
Neg logit contributions
ies-0.029
ina-0.028
 polar-0.028
 roast-0.028
aa-0.027
TokenEvery
Token ID6109
Feature activation+6.38e-02

Pos logit contributions
Robert+0.025
 Robert+0.022
Rober+0.021
Terry+0.020
jected+0.020
Neg logit contributions
ies-0.030
ina-0.030
 roast-0.029
ie-0.029
 polar-0.029
Token day
Token ID1110
Feature activation+2.16e-02

Pos logit contributions
ies+0.071
ina+0.067
 scrub+0.067
 polar+0.063
 roast+0.063
Neg logit contributions
Robert-0.132
 Robert-0.125
 Jerry-0.119
Terry-0.119
jected-0.118
Token she
Token ID673
Feature activation+1.32e-02

Pos logit contributions
ina+0.010
 roast+0.010
ies+0.009
ie+0.009
 scrub+0.009
Neg logit contributions
Robert-0.016
ados-0.014
 Robert-0.014
Rober-0.014
jected-0.014
Token smiled
Token ID13541
Feature activation-3.60e-02

Pos logit contributions
 roast+0.016
 polar+0.015
ies+0.015
 camp+0.015
ie+0.015
Neg logit contributions
Robert-0.027
 Robert-0.025
iable-0.024
jected-0.024
 Kyle-0.024
Token at
Token ID379
Feature activation-4.95e-04

Pos logit contributions
Robert+0.078
iable+0.070
ados+0.070
 Robert+0.070
Rober+0.069
Neg logit contributions
ina-0.045
ies-0.042
ie-0.040
 roast-0.039
 sleep-0.038
Token John
Token ID1757
Feature activation-1.59e-02

Pos logit contributions
jected+0.001
Robert+0.001
 thirteen+0.001
 seventeen+0.001
 eighteen+0.001
Neg logit contributions
ie-0.001
 work-0.001
ina-0.001
ies-0.001
 sleep-0.001
Token every
Token ID790
Feature activation+6.49e-02

Pos logit contributions
Robert+0.033
 Robert+0.030
Rober+0.030
ados+0.029
iable+0.029
Neg logit contributions
ina-0.019
 roast-0.019
ies-0.019
ie-0.019
 sleep-0.018
Token time
Token ID640
Feature activation+1.08e-02

Pos logit contributions
 roast+0.057
ina+0.055
ies+0.055
 polar+0.052
ie+0.051
Neg logit contributions
Robert-0.156
 Robert-0.147
Rober-0.140
jected-0.140
 Kyle-0.139
Token he
Token ID339
Feature activation+3.03e-03

Pos logit contributions
ies+0.014
ina+0.013
ie+0.013
 sleep+0.012
 camp+0.012
Neg logit contributions
Robert-0.022
jected-0.021
Rober-0.020
Mic-0.020
iable-0.019
Token came
Token ID1625
Feature activation-3.66e-03

Pos logit contributions
 roast+0.004
ina+0.003
ies+0.003
 polar+0.003
ie+0.003
Neg logit contributions
Robert-0.006
 Robert-0.006
iable-0.006
jected-0.006
Rober-0.005
Token to
Token ID284
Feature activation+1.09e-03

Pos logit contributions
Robert+0.008
jected+0.007
ados+0.007
 Robert+0.007
Rober+0.007
Neg logit contributions
ina-0.005
ies-0.004
ie-0.004
 sleep-0.004
 roast-0.004
Token school
Token ID1524
Feature activation-5.21e-02

Pos logit contributions
 sleep+0.001
 roast+0.001
ina+0.001
 camp+0.001
 work+0.001
Neg logit contributions
Robert-0.002
jected-0.002
ados-0.002
 thirteen-0.002
iable-0.002
Token.
Token ID13
Feature activation-2.98e-04

Pos logit contributions
Robert+0.114
 Robert+0.104
ados+0.104
jected+0.103
Rober+0.103
Neg logit contributions
ina-0.059
ies-0.056
ie-0.055
 sleep-0.055
 roast-0.054
Token.
Token ID13
Feature activation+8.63e-03

Pos logit contributions
Robert+0.009
 Robert+0.008
ados+0.008
iable+0.008
Rober+0.008
Neg logit contributions
 roast-0.007
ina-0.007
ies-0.007
 polar-0.007
ie-0.007
Token<|endoftext|>
Token ID50256
Feature activation+5.38e-02

Pos logit contributions
 roast+0.010
ina+0.010
 Ch+0.009
 polar+0.009
ie+0.009
Neg logit contributions
Robert-0.018
iable-0.016
Rober-0.016
 thirteen-0.016
 Robert-0.016
TokenOnce
Token ID7454
Feature activation+3.61e-02

Pos logit contributions
 roast+0.060
ina+0.060
ies+0.058
ie+0.058
 polar+0.056
Neg logit contributions
Robert-0.115
 Robert-0.106
iable-0.103
ados-0.103
Rober-0.102
Token there
Token ID612
Feature activation+1.81e-02

Pos logit contributions
 roast+0.039
 polar+0.034
 scrub+0.033
ina+0.033
 sleep+0.031
Neg logit contributions
Robert-0.081
 Robert-0.077
 Kyle-0.073
 Jerry-0.073
Rober-0.073
Token was
Token ID373
Feature activation+9.80e-03

Pos logit contributions
 roast+0.020
ina+0.019
ies+0.018
aa+0.018
 polar+0.017
Neg logit contributions
Robert-0.039
 Robert-0.038
 Jerry-0.036
 Kyle-0.035
Rober-0.035
Token a
Token ID257
Feature activation+1.10e-02

Pos logit contributions
 roast+0.018
ina+0.017
ies+0.017
ie+0.017
 polar+0.017
Neg logit contributions
Robert-0.015
 Robert-0.013
Rober-0.012
iable-0.012
ados-0.012
Token boy
Token ID2933
Feature activation-4.99e-03

Pos logit contributions
ina+0.017
ie+0.017
ies+0.017
 roast+0.017
ines+0.016
Neg logit contributions
Robert-0.018
 Robert-0.017
Rober-0.016
 Jerry-0.015
iable-0.015
Token called
Token ID1444
Feature activation+5.44e-02

Pos logit contributions
Robert+0.009
 Jerry+0.009
 Robert+0.009
jected+0.009
aw+0.008
Neg logit contributions
 roast-0.006
 camp-0.006
ies-0.006
ina-0.006
 polar-0.005
Token Billy
Token ID15890
Feature activation-5.83e-03

Pos logit contributions
 roast+0.073
 polar+0.071
 Ch+0.070
 sleep+0.069
 camp+0.068
Neg logit contributions
Robert-0.109
jected-0.105
Rober-0.102
iable-0.101
ados-0.098
Token who
Token ID508
Feature activation+3.92e-02

Pos logit contributions
Robert+0.009
 Robert+0.008
 Jerry+0.007
jected+0.007
iable+0.007
Neg logit contributions
 roast-0.010
ies-0.010
 camp-0.010
ina-0.010
 polar-0.009
Token was
Token ID373
Feature activation-1.66e-03

Pos logit contributions
ucks+0.057
ies+0.056
 roast+0.053
ina+0.053
aa+0.052
Neg logit contributions
Robert-0.070
 Robert-0.068
 Jerry-0.064
jected-0.062
iable-0.061
Token excited
Token ID6568
Feature activation-3.54e-02

Pos logit contributions
ina+0.027
 roast+0.027
ies+0.026
 sleep+0.026
ie+0.025
Neg logit contributions
Robert-0.052
ados-0.049
 Robert-0.048
iable-0.047
Rober-0.046
Token about
Token ID546
Feature activation-1.60e-03

Pos logit contributions
Robert+0.069
 Robert+0.063
Rober+0.061
iable+0.061
ados+0.061
Neg logit contributions
ina-0.047
 roast-0.046
ies-0.046
ie-0.046
 sleep-0.044
Token her
Token ID607
Feature activation-7.77e-03

Pos logit contributions
Robert+0.003
 Robert+0.003
Rober+0.003
iable+0.003
jected+0.003
Neg logit contributions
 roast-0.002
ina-0.002
ies-0.002
ie-0.002
 polar-0.002
Token adventure
Token ID8855
Feature activation+8.00e-03

Pos logit contributions
Robert+0.014
 Robert+0.014
Rober+0.013
ados+0.013
 Kyle+0.013
Neg logit contributions
ina-0.010
 roast-0.010
ucks-0.009
aa-0.009
ie-0.009
Token that
Token ID326
Feature activation+7.25e-02

Pos logit contributions
ina+0.009
ie+0.009
ies+0.008
 sleep+0.008
 camp+0.008
Neg logit contributions
Robert-0.018
Rober-0.016
 eighteen-0.016
ados-0.016
 thirteen-0.016
Token she
Token ID673
Feature activation+7.67e-03

Pos logit contributions
ina+0.108
ie+0.103
 roast+0.103
ies+0.102
 sleep+0.100
Neg logit contributions
Robert-0.135
ados-0.118
 Robert-0.118
Rober-0.118
iable-0.118
Token wanted
Token ID2227
Feature activation+1.26e-04

Pos logit contributions
 roast+0.010
ina+0.010
ies+0.010
ie+0.009
 polar+0.009
Neg logit contributions
Robert-0.015
 Robert-0.014
Rober-0.013
iable-0.013
jected-0.013
Token to
Token ID284
Feature activation-8.13e-03

Pos logit contributions
ina+0.000
ie+0.000
 sleep+0.000
ies+0.000
 roast+0.000
Neg logit contributions
Robert-0.000
jected-0.000
Rober-0.000
iable-0.000
ados-0.000
Token do
Token ID466
Feature activation+4.95e-04

Pos logit contributions
Robert+0.019
 Robert+0.018
Rober+0.017
iable+0.017
ados+0.017
Neg logit contributions
ina-0.008
 roast-0.008
ies-0.008
ie-0.007
 polar-0.007
Token it
Token ID340
Feature activation-2.39e-02

Pos logit contributions
ina+0.001
 roast+0.001
ies+0.001
ie+0.001
 sleep+0.001
Neg logit contributions
Robert-0.001
 Robert-0.001
jected-0.001
Rober-0.001
ados-0.001
Token again
Token ID757
Feature activation-8.89e-03

Pos logit contributions
Robert+0.048
 Robert+0.043
Rober+0.042
jected+0.042
ados+0.042
Neg logit contributions
ina-0.032
ie-0.031
ies-0.031
 roast-0.031
 sleep-0.030
Token a
Token ID257
Feature activation+7.01e-03

Pos logit contributions
Robert+0.011
 Robert+0.010
jected+0.009
ados+0.009
Rober+0.009
Neg logit contributions
 roast-0.010
 sleep-0.009
 scrub-0.009
ina-0.009
 camp-0.009
Token closer
Token ID5699
Feature activation+3.75e-02

Pos logit contributions
ina+0.009
 roast+0.009
ies+0.009
ie+0.009
 polar+0.009
Neg logit contributions
Robert-0.014
 Robert-0.013
iable-0.012
Rober-0.012
ados-0.012
Token look
Token ID804
Feature activation+6.44e-03

Pos logit contributions
ina+0.052
 roast+0.052
 polar+0.050
ies+0.049
 scrub+0.049
Neg logit contributions
Robert-0.066
 Robert-0.062
 Jerry-0.059
iable-0.058
 Kyle-0.058
Token,
Token ID11
Feature activation-1.03e-02

Pos logit contributions
ie+0.008
ies+0.008
ina+0.007
 roast+0.007
 sleep+0.007
Neg logit contributions
Robert-0.014
 Robert-0.013
Rober-0.012
ados-0.012
 Kyle-0.012
Token but
Token ID475
Feature activation-1.54e-03

Pos logit contributions
Robert+0.021
jected+0.019
Rober+0.019
 Robert+0.019
ados+0.019
Neg logit contributions
 roast-0.013
ina-0.013
ies-0.012
 sleep-0.012
 scrub-0.012
Token his
Token ID465
Feature activation-3.08e-02

Pos logit contributions
Robert+0.003
jected+0.003
Rober+0.003
ados+0.003
iable+0.003
Neg logit contributions
 roast-0.002
ina-0.002
ie-0.002
ies-0.002
 sleep-0.002
Token dad
Token ID9955
Feature activation-1.15e-02

Pos logit contributions
Robert+0.064
 Robert+0.059
Rober+0.057
iable+0.057
ados+0.057
Neg logit contributions
 roast-0.037
ina-0.037
ies-0.036
ie-0.035
 polar-0.035
Token said
Token ID531
Feature activation+3.53e-02

Pos logit contributions
Robert+0.026
 Robert+0.024
iable+0.023
Rober+0.023
ados+0.023
Neg logit contributions
 roast-0.012
ina-0.012
ies-0.011
ie-0.011
 polar-0.011
Token no
Token ID645
Feature activation-2.46e-02

Pos logit contributions
ina+0.044
ie+0.044
ies+0.043
 roast+0.043
 scrub+0.042
Neg logit contributions
Robert-0.071
Rober-0.064
jected-0.064
ados-0.063
Mic-0.063
Token.
Token ID13
Feature activation+7.87e-03

Pos logit contributions
Robert+0.041
 Robert+0.039
iable+0.038
ados+0.036
 Jerry+0.036
Neg logit contributions
 roast-0.039
 polar-0.036
ina-0.036
 scrub-0.035
 camp-0.035
Token
Token ID220
Feature activation+2.66e-02

Pos logit contributions
 roast+0.010
 polar+0.010
 Ch+0.009
 camp+0.009
ina+0.009
Neg logit contributions
Robert-0.015
jected-0.015
iable-0.014
ados-0.014
 thirteen-0.013
TokenThe
Token ID464
Feature activation-1.79e-03

Pos logit contributions
Robert+0.029
 Robert+0.027
Rober+0.026
ados+0.026
iable+0.026
Neg logit contributions
 roast-0.020
ina-0.020
ies-0.019
ie-0.019
 polar-0.019
Token pretty
Token ID2495
Feature activation+7.03e-03

Pos logit contributions
Robert+0.004
 Robert+0.003
Rober+0.003
ados+0.003
jected+0.003
Neg logit contributions
ina-0.002
 roast-0.002
ies-0.002
ie-0.002
 scrub-0.002
Token frog
Token ID21264
Feature activation+5.09e-02

Pos logit contributions
 roast+0.010
ina+0.010
 scrub+0.009
aa+0.009
 polar+0.009
Neg logit contributions
Robert-0.013
 Robert-0.012
ados-0.012
 Jerry-0.012
 Kyle-0.011
Token looked
Token ID3114
Feature activation+5.14e-03

Pos logit contributions
 roast+0.065
ina+0.063
ies+0.061
 polar+0.061
 camp+0.059
Neg logit contributions
Robert-0.100
 Robert-0.094
jected-0.089
iable-0.088
Rober-0.088
Token at
Token ID379
Feature activation-3.69e-02

Pos logit contributions
ies+0.007
ie+0.007
ina+0.007
 roast+0.007
 polar+0.007
Neg logit contributions
Robert-0.010
 Robert-0.009
ados-0.009
Rober-0.009
jected-0.009
Token him
Token ID683
Feature activation-7.57e-03

Pos logit contributions
Robert+0.071
jected+0.064
Rober+0.064
iable+0.064
 thirteen+0.062
Neg logit contributions
ie-0.054
ina-0.050
ies-0.049
 polar-0.049
 sleep-0.049
Token and
Token ID290
Feature activation-2.02e-02

Pos logit contributions
Robert+0.017
 Robert+0.015
Rober+0.015
iable+0.015
ados+0.015
Neg logit contributions
 roast-0.008
ina-0.008
ies-0.008
ie-0.008
 sleep-0.008
Token said
Token ID531
Feature activation+2.87e-02

Pos logit contributions
Robert+0.046
 Robert+0.042
Rober+0.041
ados+0.041
iable+0.041
Neg logit contributions
 roast-0.020
ina-0.020
ies-0.020
ie-0.019
 polar-0.019
Token,
Token ID11
Feature activation-1.08e-02

Pos logit contributions
ie+0.022
ies+0.021
 Ch+0.021
ina+0.018
 polar+0.018
Neg logit contributions
Robert-0.074
jected-0.069
Rober-0.067
handed-0.067
Mic-0.067
Token "
Token ID366
Feature activation-3.13e-02

Pos logit contributions
Robert+0.022
jected+0.019
iable+0.019
 Robert+0.019
ados+0.019
Neg logit contributions
 roast-0.014
ina-0.014
ies-0.013
 polar-0.013
 scrub-0.013
TokenI
Token ID40
Feature activation+7.22e-03

Pos logit contributions
Robert+0.056
 Robert+0.051
ados+0.050
Rober+0.049
iable+0.049
Neg logit contributions
 roast-0.046
ina-0.046
ie-0.045
ies-0.044
 polar-0.044
Token again
Token ID757
Feature activation+3.03e-03

Pos logit contributions
Robert+0.034
 Robert+0.031
Rober+0.031
Terry+0.030
ados+0.030
Neg logit contributions
ie-0.016
ies-0.015
ina-0.015
 roast-0.014
 camp-0.014
Token!"
Token ID2474
Feature activation-4.05e-02

Pos logit contributions
 roast+0.004
ina+0.004
ies+0.004
ie+0.004
 polar+0.003
Neg logit contributions
Robert-0.006
 Robert-0.006
Rober-0.005
iable-0.005
ados-0.005
Token
Token ID220
Feature activation+8.75e-03

Pos logit contributions
Robert+0.075
iable+0.067
Rober+0.067
 thirteen+0.065
 Robert+0.065
Neg logit contributions
 roast-0.060
 sleep-0.059
 scrub-0.055
 camp-0.055
 Ch-0.054
Token
Token ID198
Feature activation-1.28e-02

Pos logit contributions
 roast+0.012
ina+0.012
ies+0.012
ie+0.011
 polar+0.011
Neg logit contributions
Robert-0.017
 Robert-0.016
Rober-0.015
iable-0.015
ados-0.015
Token
Token ID198
Feature activation-1.29e-02

Pos logit contributions
Robert+0.024
 Robert+0.021
Rober+0.020
jected+0.020
iable+0.020
Neg logit contributions
ies-0.020
ina-0.020
 roast-0.019
ie-0.019
 polar-0.018
TokenBut
Token ID1537
Feature activation-1.87e-02

Pos logit contributions
Robert+0.018
ados+0.018
 Robert+0.018
 Kyle+0.016
 Jerry+0.016
Neg logit contributions
 roast-0.023
 scrub-0.022
 sleep-0.022
ina-0.021
 camp-0.021
Token the
Token ID262
Feature activation-4.85e-03

Pos logit contributions
Robert+0.042
Rober+0.039
iable+0.038
ados+0.038
Terry+0.037
Neg logit contributions
 roast-0.021
 sleep-0.020
 polar-0.019
 camp-0.019
 Ch-0.019
Token bad
Token ID2089
Feature activation-7.65e-03

Pos logit contributions
Robert+0.009
 Robert+0.008
jected+0.008
Rober+0.008
ados+0.008
Neg logit contributions
ina-0.007
ies-0.007
 roast-0.007
aa-0.007
ie-0.007
Token bear
Token ID6842
Feature activation+7.03e-02

Pos logit contributions
 Robert+0.013
 Jerry+0.012
Robert+0.012
ados+0.012
 av+0.011
Neg logit contributions
ucks-0.011
ina-0.011
 roast-0.010
ili-0.010
 scrub-0.010
Token just
Token ID655
Feature activation+1.88e-02

Pos logit contributions
ie+0.064
ina+0.063
ies+0.062
 roast+0.061
 scrub+0.058
Neg logit contributions
Robert-0.168
 Robert-0.154
ados-0.153
Rober-0.151
 Kyle-0.148
Token laughed
Token ID13818
Feature activation-2.71e-02

Pos logit contributions
 roast+0.024
ina+0.024
ies+0.023
ie+0.023
 polar+0.022
Neg logit contributions
Robert-0.038
 Robert-0.035
Rober-0.034
ados-0.034
iable-0.033
Token me
Token ID502
Feature activation+4.43e-02

Pos logit contributions
Robert+0.146
jected+0.132
Rober+0.132
 Robert+0.130
 thirteen+0.126
Neg logit contributions
ie-0.088
ies-0.085
ina-0.082
aa-0.080
 roast-0.078
Token the
Token ID262
Feature activation-7.85e-03

Pos logit contributions
 roast+0.059
ie+0.059
ies+0.058
aa+0.056
 sleep+0.056
Neg logit contributions
Robert-0.086
jected-0.078
 Robert-0.078
Rober-0.077
Terry-0.074
Token orange
Token ID10912
Feature activation+3.42e-02

Pos logit contributions
Robert+0.017
Rober+0.015
jected+0.015
iable+0.015
 Robert+0.015
Neg logit contributions
 roast-0.009
 polar-0.009
 camp-0.009
 ig-0.009
 sleep-0.009
Token car
Token ID1097
Feature activation-3.64e-02

Pos logit contributions
 roast+0.044
ie+0.042
ies+0.042
ina+0.042
 polar+0.041
Neg logit contributions
Robert-0.071
Rober-0.064
 Robert-0.063
jected-0.062
Terry-0.062
Token!"
Token ID2474
Feature activation-5.14e-02

Pos logit contributions
Robert+0.090
Rober+0.081
Terry+0.081
 Robert+0.081
jected+0.080
Neg logit contributions
ies-0.034
ie-0.033
 roast-0.029
ina-0.029
 sleep-0.029
Token Sam
Token ID3409
Feature activation-3.47e-02

Pos logit contributions
Robert+0.090
 Robert+0.080
Rober+0.078
iable+0.077
jected+0.077
Neg logit contributions
 roast-0.080
ina-0.079
ies-0.078
ie-0.077
 polar-0.075
Token says
Token ID1139
Feature activation+9.42e-04

Pos logit contributions
Robert+0.078
 Robert+0.073
Rober+0.070
iable+0.070
ados+0.069
Neg logit contributions
 roast-0.036
ina-0.036
ies-0.034
 polar-0.034
ie-0.033
Token.
Token ID13
Feature activation-1.11e-02

Pos logit contributions
ies+0.001
 scrub+0.001
 sleep+0.001
ie+0.001
ina+0.001
Neg logit contributions
Robert-0.002
Rober-0.002
iable-0.002
Terry-0.002
jected-0.002
Token He
Token ID679
Feature activation-2.58e-03

Pos logit contributions
Robert+0.016
 Robert+0.014
Rober+0.013
ados+0.013
iable+0.013
Neg logit contributions
 roast-0.021
ina-0.020
ies-0.020
ie-0.020
 polar-0.020
Token tries
Token ID8404
Feature activation+1.29e-03

Pos logit contributions
Robert+0.005
 Robert+0.004
Rober+0.004
iable+0.004
ados+0.004
Neg logit contributions
 roast-0.004
ina-0.004
ies-0.004
ie-0.004
 polar-0.004
Token to
Token ID284
Feature activation-2.39e-02

Pos logit contributions
 scrub+0.001
ina+0.001
ies+0.001
 sleep+0.001
 roast+0.001
Neg logit contributions
Robert-0.003
jected-0.003
ados-0.003
Rober-0.003
 Robert-0.003
Token before
Token ID878
Feature activation+8.35e-03

Pos logit contributions
 roast+0.002
ina+0.002
ies+0.002
ie+0.002
 camp+0.002
Neg logit contributions
Robert-0.003
Rober-0.003
ados-0.003
iable-0.003
 Robert-0.003
Token they
Token ID484
Feature activation-3.95e-02

Pos logit contributions
 roast+0.012
ina+0.012
ies+0.012
ie+0.011
 polar+0.011
Neg logit contributions
Robert-0.016
 Robert-0.014
ados-0.014
iable-0.014
Rober-0.014
Token could
Token ID714
Feature activation+1.80e-02

Pos logit contributions
Robert+0.096
ados+0.090
 Robert+0.087
Rober+0.086
 thirteen+0.084
Neg logit contributions
 roast-0.036
ie-0.036
 scrub-0.034
 sleep-0.034
ina-0.033
Token escape
Token ID6654
Feature activation+5.70e-03

Pos logit contributions
 roast+0.021
 sleep+0.020
 camp+0.018
ina+0.018
 scrub+0.018
Neg logit contributions
Robert-0.040
ados-0.037
jected-0.036
 Robert-0.036
 thirteen-0.035
Token,
Token ID11
Feature activation-8.29e-03

Pos logit contributions
ies+0.007
ina+0.007
 roast+0.007
ie+0.007
 camp+0.007
Neg logit contributions
Robert-0.012
jected-0.011
Rober-0.011
ados-0.011
 Robert-0.010
Token the
Token ID262
Feature activation-1.24e-02

Pos logit contributions
Robert+0.017
jected+0.016
iable+0.015
ados+0.015
Rober+0.015
Neg logit contributions
 roast-0.011
 camp-0.010
ina-0.010
ies-0.010
 sleep-0.010
Token police
Token ID1644
Feature activation-4.90e-02

Pos logit contributions
Robert+0.022
iable+0.021
 Robert+0.020
ados+0.020
Terry+0.019
Neg logit contributions
 polar-0.019
 sleep-0.019
 camp-0.019
 roast-0.019
 ig-0.018
Token came
Token ID1625
Feature activation-1.64e-02

Pos logit contributions
Robert+0.104
ados+0.096
Rober+0.095
 Robert+0.094
jected+0.093
Neg logit contributions
ies-0.057
ina-0.056
ie-0.056
 roast-0.055
 polar-0.055
Token and
Token ID290
Feature activation-1.73e-02

Pos logit contributions
Robert+0.036
 Robert+0.033
ados+0.033
iable+0.032
Rober+0.032
Neg logit contributions
ina-0.019
ies-0.019
 roast-0.018
ie-0.018
 sleep-0.017
Token stopped
Token ID5025
Feature activation-3.17e-02

Pos logit contributions
Robert+0.037
 Robert+0.034
ados+0.034
Rober+0.033
iable+0.033
Neg logit contributions
 roast-0.020
ina-0.019
ies-0.019
ie-0.019
 polar-0.019
Token them
Token ID606
Feature activation-2.88e-02

Pos logit contributions
Robert+0.057
 Robert+0.053
ados+0.050
Rober+0.050
iable+0.050
Neg logit contributions
 roast-0.046
ina-0.046
ies-0.045
ie-0.044
 polar-0.043
Token We
Token ID775
Feature activation-3.01e-02

Pos logit contributions
 roast+0.023
ina+0.021
 polar+0.021
 sleep+0.020
ies+0.020
Neg logit contributions
Robert-0.026
iable-0.023
 Robert-0.023
Rober-0.023
ados-0.022
Token wanted
Token ID2227
Feature activation-8.34e-04

Pos logit contributions
Robert+0.050
 Robert+0.046
iable+0.046
jected+0.044
Rober+0.044
Neg logit contributions
 roast-0.046
ina-0.046
 polar-0.045
ie-0.045
 camp-0.044
Token to
Token ID284
Feature activation-4.84e-04

Pos logit contributions
Robert+0.002
jected+0.002
Rober+0.002
iable+0.002
iece+0.002
Neg logit contributions
 roast-0.001
 sleep-0.001
 camp-0.001
ies-0.001
 work-0.001
Token make
Token ID787
Feature activation+3.72e-02

Pos logit contributions
Robert+0.001
 Robert+0.001
 Kyle+0.001
 Jerry+0.001
iable+0.001
Neg logit contributions
ina-0.000
ies-0.000
ie-0.000
aa-0.000
 polar-0.000
Token a
Token ID257
Feature activation-4.29e-03

Pos logit contributions
 roast+0.057
 sleep+0.055
ies+0.055
ie+0.055
 camp+0.055
Neg logit contributions
Robert-0.065
jected-0.060
Rober-0.058
 Robert-0.057
iable-0.056
Token menu
Token ID6859
Feature activation-9.07e-02

Pos logit contributions
Robert+0.008
 Robert+0.007
Rober+0.007
ados+0.007
iable+0.007
Neg logit contributions
 roast-0.006
ina-0.006
ies-0.006
ie-0.006
 polar-0.006
Token with
Token ID351
Feature activation-1.68e-02

Pos logit contributions
Robert+0.198
 Robert+0.182
ados+0.179
Rober+0.178
jected+0.177
Neg logit contributions
 roast-0.102
ies-0.100
ina-0.098
ie-0.096
 sleep-0.096
Token healthy
Token ID5448
Feature activation-1.30e-02

Pos logit contributions
Robert+0.032
jected+0.032
Rober+0.030
iece+0.030
iable+0.029
Neg logit contributions
 roast-0.023
 camp-0.022
ies-0.022
 sleep-0.021
ie-0.021
Token food
Token ID2057
Feature activation-1.87e-02

Pos logit contributions
Robert+0.024
iable+0.022
jected+0.022
 Robert+0.022
Rober+0.022
Neg logit contributions
ies-0.019
 roast-0.019
ie-0.018
 sleep-0.018
 polar-0.018
Token,
Token ID11
Feature activation+7.63e-03

Pos logit contributions
Robert+0.041
 Robert+0.037
Rober+0.037
jected+0.037
iable+0.036
Neg logit contributions
 roast-0.021
ies-0.021
ina-0.020
ie-0.019
 sleep-0.019
Token but
Token ID475
Feature activation+2.34e-02

Pos logit contributions
 roast+0.009
 sleep+0.008
ies+0.008
ina+0.008
 scrub+0.008
Neg logit contributions
Robert-0.016
jected-0.015
 Robert-0.015
Rober-0.015
ados-0.015
Token.
Token ID13
Feature activation-5.88e-04

Pos logit contributions
Robert+0.000
Rober+0.000
 Robert+0.000
jected+0.000
iable+0.000
Neg logit contributions
ies-0.000
ie-0.000
ina-0.000
 roast-0.000
 sleep-0.000
Token They
Token ID1119
Feature activation+5.41e-03

Pos logit contributions
Robert+0.001
 Robert+0.001
 Jerry+0.001
 Kyle+0.001
 Terry+0.001
Neg logit contributions
ie-0.001
 polar-0.001
ies-0.001
ina-0.001
 scrub-0.001
Token liked
Token ID8288
Feature activation-8.97e-03

Pos logit contributions
ucks+0.007
ina+0.007
 roast+0.007
imi+0.007
ies+0.007
Neg logit contributions
Robert-0.009
 Robert-0.009
 Jerry-0.008
 Kyle-0.008
iable-0.008
Token to
Token ID284
Feature activation+5.79e-03

Pos logit contributions
Robert+0.015
 Robert+0.014
ados+0.014
 Jerry+0.013
 Kyle+0.013
Neg logit contributions
ina-0.014
 roast-0.014
ie-0.013
ies-0.013
 polar-0.013
Token make
Token ID787
Feature activation+3.63e-02

Pos logit contributions
ina+0.008
ies+0.007
aa+0.007
ie+0.007
 Chick+0.007
Neg logit contributions
Robert-0.011
 Robert-0.011
 Jerry-0.010
 Kyle-0.010
iable-0.010
Token sand
Token ID6450
Feature activation-8.38e-02

Pos logit contributions
ina+0.069
 roast+0.067
ie+0.065
aa+0.065
 polar+0.064
Neg logit contributions
Robert-0.048
 Robert-0.043
ados-0.042
iable-0.041
 Kyle-0.040
Token castles
Token ID49203
Feature activation-6.65e-02

Pos logit contributions
Robert+0.134
 Robert+0.121
ados+0.117
iable+0.115
Rober+0.114
Neg logit contributions
 roast-0.136
ina-0.136
ie-0.131
ies-0.130
 polar-0.130
Token and
Token ID290
Feature activation-9.98e-04

Pos logit contributions
Robert+0.175
jected+0.162
 Robert+0.162
Rober+0.161
ados+0.153
Neg logit contributions
ies-0.066
ie-0.054
 roast-0.053
ina-0.051
 sleep-0.051
Token dig
Token ID3100
Feature activation+5.14e-02

Pos logit contributions
Robert+0.002
 Robert+0.002
 thirteen+0.002
iable+0.002
ados+0.002
Neg logit contributions
ina-0.001
aa-0.001
ie-0.001
 roast-0.001
ies-0.001
Token holes
Token ID10421
Feature activation-1.60e-02

Pos logit contributions
ies+0.069
ie+0.064
 roast+0.063
ina+0.061
 camp+0.060
Neg logit contributions
Robert-0.112
 Robert-0.102
iable-0.100
Rober-0.099
jected-0.096
Token.
Token ID13
Feature activation+2.21e-04

Pos logit contributions
Robert+0.037
 Robert+0.034
Rober+0.033
iable+0.033
Terry+0.032
Neg logit contributions
ies-0.018
ie-0.018
ina-0.018
 roast-0.017
 scrub-0.016
Token bright
Token ID6016
Feature activation+1.21e-02

Pos logit contributions
Robert+0.003
 Robert+0.002
Rober+0.002
ados+0.002
iable+0.002
Neg logit contributions
 roast-0.002
ina-0.002
ies-0.002
ie-0.002
 polar-0.002
Token.
Token ID13
Feature activation+1.15e-02

Pos logit contributions
ies+0.013
ina+0.013
ie+0.013
 sleep+0.012
 roast+0.012
Neg logit contributions
Robert-0.028
iable-0.025
Rober-0.025
Terry-0.025
 Robert-0.025
Token It
Token ID632
Feature activation+1.93e-02

Pos logit contributions
 roast+0.019
ina+0.019
ies+0.018
ie+0.018
 polar+0.018
Neg logit contributions
Robert-0.019
 Robert-0.017
Rober-0.016
ados-0.016
iable-0.016
Token has
Token ID468
Feature activation-2.64e-02

Pos logit contributions
ina+0.025
 roast+0.025
ies+0.025
 polar+0.024
ie+0.024
Neg logit contributions
Robert-0.037
 Robert-0.034
jected-0.033
iable-0.033
 thirteen-0.033
Token new
Token ID649
Feature activation-3.39e-02

Pos logit contributions
Robert+0.053
Rober+0.048
iable+0.048
 Robert+0.046
jected+0.046
Neg logit contributions
 roast-0.037
 sleep-0.035
 camp-0.035
 ig-0.035
 polar-0.034
Token books
Token ID3835
Feature activation-9.22e-02

Pos logit contributions
Robert+0.061
 Robert+0.057
ados+0.055
Rober+0.053
 Kyle+0.053
Neg logit contributions
 roast-0.049
ina-0.048
ie-0.046
ies-0.046
 polar-0.045
Token and
Token ID290
Feature activation+1.07e-02

Pos logit contributions
Robert+0.218
Rober+0.203
ados+0.203
 Robert+0.198
Terry+0.197
Neg logit contributions
ina-0.089
 sleep-0.087
ies-0.082
ie-0.082
 roast-0.081
Token toys
Token ID14958
Feature activation-5.57e-02

Pos logit contributions
 roast+0.015
 sleep+0.015
ies+0.015
 polar+0.014
 camp+0.014
Neg logit contributions
Robert-0.021
Rober-0.019
jected-0.018
iable-0.018
 Robert-0.018
Token and
Token ID290
Feature activation+1.24e-02

Pos logit contributions
Robert+0.134
Rober+0.124
 Robert+0.122
Terry+0.120
jected+0.118
Neg logit contributions
ies-0.054
 sleep-0.052
ina-0.052
ie-0.049
 roast-0.049
Token a
Token ID257
Feature activation+3.73e-02

Pos logit contributions
 roast+0.018
ies+0.017
 sleep+0.017
 polar+0.017
 camp+0.017
Neg logit contributions
Robert-0.024
jected-0.021
Rober-0.021
 Robert-0.021
iable-0.021
Token big
Token ID1263
Feature activation+9.70e-03

Pos logit contributions
 roast+0.048
 polar+0.046
ies+0.046
ina+0.046
 sleep+0.045
Neg logit contributions
Robert-0.075
 Robert-0.069
jected-0.068
iable-0.067
ados-0.067
Tokenily
Token ID813
Feature activation+8.65e-03

Pos logit contributions
Robert+0.033
 Robert+0.029
Rober+0.028
ados+0.027
iable+0.027
Neg logit contributions
 roast-0.050
ina-0.050
ies-0.049
ie-0.048
 polar-0.048
Token and
Token ID290
Feature activation-1.71e-02

Pos logit contributions
 roast+0.012
ina+0.011
 polar+0.011
ies+0.011
 camp+0.011
Neg logit contributions
Robert-0.016
 Robert-0.015
jected-0.014
Rober-0.014
iable-0.014
Token the
Token ID262
Feature activation+1.06e-02

Pos logit contributions
Robert+0.030
jected+0.026
iable+0.026
 Robert+0.026
Rober+0.025
Neg logit contributions
ina-0.027
ies-0.027
ie-0.027
 roast-0.026
 sleep-0.026
Token witch
Token ID16365
Feature activation+3.38e-02

Pos logit contributions
 roast+0.014
ina+0.013
ies+0.013
ie+0.013
 scrub+0.013
Neg logit contributions
Robert-0.021
 Robert-0.019
Rober-0.018
ados-0.018
 Kyle-0.018
Token played
Token ID2826
Feature activation+4.23e-02

Pos logit contributions
 roast+0.045
ina+0.045
ies+0.043
 polar+0.043
ie+0.042
Neg logit contributions
Robert-0.064
 Robert-0.059
iable-0.056
Rober-0.056
jected-0.056
Token games
Token ID1830
Feature activation-9.01e-02

Pos logit contributions
 roast+0.065
ina+0.065
ies+0.063
ie+0.063
 polar+0.062
Neg logit contributions
Robert-0.073
 Robert-0.067
Rober-0.064
ados-0.063
iable-0.062
Token,
Token ID11
Feature activation-3.49e-03

Pos logit contributions
Robert+0.193
ados+0.175
 Robert+0.175
Rober+0.175
iable+0.175
Neg logit contributions
ies-0.107
ina-0.105
ie-0.104
 sleep-0.104
 roast-0.102
Token ran
Token ID4966
Feature activation-3.09e-02

Pos logit contributions
Robert+0.007
 Robert+0.007
Rober+0.007
ados+0.007
iable+0.007
Neg logit contributions
 roast-0.004
ina-0.004
ies-0.004
ie-0.004
 polar-0.004
Token around
Token ID1088
Feature activation+3.44e-02

Pos logit contributions
Robert+0.070
iable+0.065
jected+0.065
ados+0.064
 Robert+0.063
Neg logit contributions
ies-0.032
 sleep-0.031
ina-0.031
 camp-0.031
ie-0.031
Token,
Token ID11
Feature activation-1.67e-02

Pos logit contributions
 roast+0.049
ina+0.049
ies+0.048
ie+0.047
 polar+0.046
Neg logit contributions
Robert-0.064
 Robert-0.058
Rober-0.056
iable-0.056
ados-0.056
Token and
Token ID290
Feature activation-1.84e-02

Pos logit contributions
Robert+0.037
 Robert+0.034
ados+0.033
Rober+0.033
iable+0.033
Neg logit contributions
 roast-0.018
ina-0.018
ies-0.017
ie-0.017
 scrub-0.016
Token twins
Token ID20345
Feature activation-1.86e-03

Pos logit contributions
Robert+0.039
 Robert+0.036
Rober+0.035
ados+0.035
iable+0.034
Neg logit contributions
 roast-0.025
ina-0.024
ies-0.024
ie-0.024
 polar-0.023
Token who
Token ID508
Feature activation+5.78e-02

Pos logit contributions
Robert+0.004
 Robert+0.004
ados+0.004
Rober+0.003
iable+0.003
Neg logit contributions
ina-0.002
 roast-0.002
ies-0.002
ie-0.002
 sleep-0.002
Token loved
Token ID6151
Feature activation+1.58e-02

Pos logit contributions
 roast+0.068
ies+0.068
ie+0.067
ina+0.066
 polar+0.064
Neg logit contributions
Robert-0.118
 Robert-0.111
Rober-0.104
 Jerry-0.103
 Kyle-0.103
Token to
Token ID284
Feature activation+2.10e-02

Pos logit contributions
ina+0.024
 roast+0.024
ies+0.023
ie+0.023
 polar+0.022
Neg logit contributions
Robert-0.027
 Robert-0.025
ados-0.025
 Jerry-0.024
Rober-0.023
Token play
Token ID711
Feature activation+5.22e-02

Pos logit contributions
ina+0.015
ies+0.015
ie+0.014
 roast+0.014
aa+0.013
Neg logit contributions
Robert-0.052
 Robert-0.050
 Jerry-0.048
 Kyle-0.048
iable-0.047
Token games
Token ID1830
Feature activation-8.34e-02

Pos logit contributions
 roast+0.073
ina+0.072
ies+0.071
ie+0.070
 polar+0.068
Neg logit contributions
Robert-0.100
 Robert-0.091
Rober-0.087
iable-0.087
jected-0.086
Token.
Token ID13
Feature activation-1.50e-03

Pos logit contributions
Robert+0.193
Rober+0.178
 Robert+0.177
iable+0.176
ados+0.174
Neg logit contributions
ies-0.083
ina-0.083
 sleep-0.081
ie-0.080
 roast-0.080
Token One
Token ID1881
Feature activation+7.99e-02

Pos logit contributions
Robert+0.002
 Robert+0.002
 Kyle+0.002
 Jerry+0.002
Rober+0.002
Neg logit contributions
ies-0.002
ina-0.002
 roast-0.002
ie-0.002
 polar-0.002
Token day
Token ID1110
Feature activation+1.72e-02

Pos logit contributions
 roast+0.080
 polar+0.078
 Chick+0.077
 scrub+0.077
ucks+0.074
Neg logit contributions
Robert-0.161
 Robert-0.156
 Jerry-0.152
 Kyle-0.147
jected-0.145
Token,
Token ID11
Feature activation-7.06e-03

Pos logit contributions
ies+0.024
 roast+0.023
ina+0.023
ie+0.023
 polar+0.022
Neg logit contributions
Robert-0.033
 Robert-0.030
jected-0.030
Rober-0.030
iable-0.030
Token they
Token ID484
Feature activation-2.80e-02

Pos logit contributions
Robert+0.013
 Robert+0.012
Rober+0.011
ados+0.011
iable+0.011
Neg logit contributions
 roast-0.010
ina-0.010
ies-0.010
ie-0.010
 polar-0.010