TOP ACTIVATIONS
MAX = 4.339

her mom my watched in amaz ement as the machine flew
soon nothing but a small spe ck in the sky .
she had with her or nam ents . <|endoftext|> Once upon
the rest of the or nam ents onto the tree .
away , a bright blue spe ck in the sky .
eddy bear and watched in amaz ement as it shrunk an
around stopped and watched in amaz ement . They were so
calmed down and watched in amaz ement as the rainbow melted
the zipper and gasped with amaz ement at all the treasures
time playing with her or nam ents and making her special
Tim watched them with pure amaz ement , never t iring
friends stopped and watched in amaz ement . The dog too
Wow ," Emily gasped in amaz ement . She realized that
Sarah watched in amaz ement as the water became
were filled with wonder and amaz ement . They thanked the
they both looked around in amaz ement . The lake was
seen ! She gasped in amaz ement , and her tears
Lily stopped and stared in amaz ement . The bush was
it often and watched in amaz ement whenever the door opened
take one of the or nam ents outside for a walk

MIN ACTIVATIONS
MIN = -4.352

put on their p aj amas . They said good night
put on their p aj amas and get into their beds
put on your p aj amas ." Tim and
put on their p aj amas first . They do what
put on their p aj amas . They hug their mom
put on their p aj amas . They hug their mom
them towels and p aj amas . They give them a
puts on her p aj amas . They are tight and
put on your p aj amas ." L ily
They were wearing p aj amas . And they were not
put on their p aj amas . They climbed into their
put on their p aj amas . They each pick a
put on her p aj amas . Mom my read her
put on their p aj amas . Their mom tucked them
put on their p aj amas . They get into their
put on your p aj amas . OK ?"
on their warm p aj amas and crawl into their sleeping
pair of matching p aj amas with com ets on them
put on their p aj amas . They climbed into their
put on their p aj amas . They hugged their mom

INTERVAL 2.166 - 4.339
CONTAINS 0.093%

He looked at it with amaz ement and said , "
. He always used the loop to lead them back home
feel calm ", or " Sm ile and let the sadness
One day , Zig gy 's friend , a
had a big , bus hy tail and sharp teeth .

INTERVAL -0.007 - 2.166
CONTAINS 48.298%

, but it was hard to drink as his throat was
mom hugged them and said , " I know you want
The goat quickly ran out of the shed and back to
and fast . One day a man told the
She took the frame and put it up on

INTERVAL -2.179 - -0.007
CONTAINS 51.512%

night , car . I love you ." And they both
's words . <|endoftext|> Once upon a time , there was
- years old . One day , Sally went to the
seeing all the people go hungry . She had an idea
3 year old named Tommy wanted to open it , but

INTERVAL -4.352 - -2.179
CONTAINS 0.097%

label that said " del iver to Mr . Smith ".
Then she went to the kitchen to get a snack .
They could see it sailing away in the distance . They
and said , " Go away ! Anna is mine now
!" Anna said . " But can you number the flowers
Token her
Token ID607
Feature activation+8.93e-01

Pos logit contributions
Just+0.003
ager+0.003
age+0.003
P+0.003
sy+0.003
Neg logit contributions
 theirs-0.003
rings-0.003
 wow-0.002
 what-0.002
 are-0.002
Token mom
Token ID1995
Feature activation+8.12e-01

Pos logit contributions
 theirs+0.082
rings+0.069
 what+0.064
 are+0.060
 wow+0.060
Neg logit contributions
Just-0.087
ager-0.081
age-0.081
P-0.078
bes-0.076
Tokenmy
Token ID1820
Feature activation+7.28e-01

Pos logit contributions
 theirs+0.077
rings+0.065
 what+0.061
 are+0.058
 wow+0.057
Neg logit contributions
Just-0.076
ager-0.071
age-0.071
P-0.068
bes-0.067
Token watched
Token ID7342
Feature activation-3.86e-01

Pos logit contributions
 theirs+0.070
rings+0.060
 what+0.056
 are+0.053
 wow+0.052
Neg logit contributions
Just-0.068
ager-0.062
age-0.062
P-0.061
bes-0.059
Token in
Token ID287
Feature activation+4.32e-02

Pos logit contributions
Just+0.043
age+0.040
ager+0.040
bes+0.039
P+0.039
Neg logit contributions
 theirs-0.029
rings-0.024
 what-0.020
 wow-0.020
 are-0.019
Token amaz
Token ID40642
Feature activation+4.23e+00

Pos logit contributions
 theirs+0.003
rings+0.003
 wow+0.002
nam+0.002
 what+0.002
Neg logit contributions
Just-0.005
ager-0.004
bes-0.004
age-0.004
rd-0.004
Tokenement
Token ID972
Feature activation+7.19e-01

Pos logit contributions
 theirs+0.424
rings+0.365
 what+0.325
nam+0.323
 are+0.318
Neg logit contributions
Just-0.375
ager-0.346
age-0.337
P-0.331
ivering-0.323
Token as
Token ID355
Feature activation+2.32e+00

Pos logit contributions
 theirs+0.069
rings+0.058
 what+0.053
 wow+0.051
 are+0.051
Neg logit contributions
Just-0.067
age-0.062
ager-0.061
P-0.059
bes-0.059
Token the
Token ID262
Feature activation+3.45e-01

Pos logit contributions
 theirs+0.153
rings+0.128
ours+0.098
 wow+0.097
 are+0.095
Neg logit contributions
Just-0.262
ager-0.246
age-0.241
Lu-0.240
P-0.240
Token machine
Token ID4572
Feature activation+7.18e-01

Pos logit contributions
 theirs+0.032
rings+0.027
 what+0.026
 wow+0.024
 are+0.024
Neg logit contributions
Just-0.033
age-0.030
ager-0.030
P-0.029
bes-0.029
Token flew
Token ID13112
Feature activation+1.37e+00

Pos logit contributions
 theirs+0.068
rings+0.057
 what+0.053
 are+0.050
 wow+0.050
Neg logit contributions
Just-0.068
ager-0.063
age-0.063
P-0.061
bes-0.060
Token soon
Token ID2582
Feature activation-1.52e+00

Pos logit contributions
Just+0.027
age+0.026
ager+0.025
ivering+0.024
sy+0.024
Neg logit contributions
 theirs-0.027
rings-0.023
 what-0.020
 wow-0.020
 are-0.020
Token nothing
Token ID2147
Feature activation-7.74e-01

Pos logit contributions
Just+0.137
age+0.130
ager+0.124
ivering+0.121
bes+0.119
Neg logit contributions
 theirs-0.149
rings-0.128
 what-0.114
nam-0.113
 wow-0.112
Token but
Token ID475
Feature activation-9.64e-01

Pos logit contributions
Just+0.079
ager+0.074
age+0.073
P+0.070
bes+0.069
Neg logit contributions
 theirs-0.067
rings-0.057
 what-0.051
 wow-0.048
 are-0.048
Token a
Token ID257
Feature activation+1.31e-02

Pos logit contributions
Just+0.105
ager+0.098
age+0.095
sy+0.091
bes+0.089
Neg logit contributions
 theirs-0.071
rings-0.064
nam-0.053
ours-0.048
angles-0.046
Token small
Token ID1402
Feature activation-1.94e-01

Pos logit contributions
 theirs+0.001
rings+0.001
 what+0.001
 wow+0.001
 are+0.001
Neg logit contributions
Just-0.001
age-0.001
ager-0.001
bes-0.001
P-0.001
Token spe
Token ID693
Feature activation+4.14e+00

Pos logit contributions
Just+0.017
age+0.015
ager+0.015
P+0.015
bes+0.014
Neg logit contributions
 theirs-0.020
rings-0.017
 what-0.016
 wow-0.015
 are-0.015
Tokenck
Token ID694
Feature activation+7.45e-01

Pos logit contributions
 theirs+0.305
rings+0.235
 what+0.210
 wow+0.194
 are+0.190
Neg logit contributions
Just-0.475
age-0.443
ager-0.443
P-0.437
amas-0.437
Token in
Token ID287
Feature activation-4.55e-01

Pos logit contributions
 theirs+0.073
rings+0.062
 what+0.058
 are+0.056
 wow+0.055
Neg logit contributions
Just-0.068
ager-0.062
age-0.062
bes-0.061
P-0.060
Token the
Token ID262
Feature activation-1.77e-01

Pos logit contributions
Just+0.052
P+0.050
age+0.049
ager+0.048
Now+0.048
Neg logit contributions
 theirs-0.028
rings-0.028
ours-0.021
nam-0.020
 wow-0.019
Token sky
Token ID6766
Feature activation+4.04e-01

Pos logit contributions
Just+0.016
ager+0.015
age+0.014
bes+0.014
P+0.014
Neg logit contributions
 theirs-0.017
rings-0.015
 what-0.014
 are-0.014
 wow-0.013
Token.
Token ID13
Feature activation+1.69e-01

Pos logit contributions
 theirs+0.041
rings+0.035
 what+0.032
nam+0.031
 wow+0.031
Neg logit contributions
Just-0.036
age-0.033
ager-0.033
P-0.031
bes-0.031
Token she
Token ID673
Feature activation+4.53e-02

Pos logit contributions
 theirs+0.014
rings+0.011
 what+0.009
 wow+0.009
nam+0.009
Neg logit contributions
Just-0.020
ager-0.019
age-0.019
bes-0.018
P-0.018
Token had
Token ID550
Feature activation+3.95e-01

Pos logit contributions
 theirs+0.003
 what+0.003
rings+0.003
 are+0.003
 wow+0.003
Neg logit contributions
Just-0.005
age-0.005
amas-0.005
ivering-0.005
bes-0.005
Token with
Token ID351
Feature activation+3.78e-02

Pos logit contributions
 theirs+0.035
 what+0.029
rings+0.028
 are+0.026
 their+0.025
Neg logit contributions
Just-0.039
age-0.038
oster-0.038
ivering-0.038
amas-0.037
Token her
Token ID607
Feature activation+4.57e-01

Pos logit contributions
 theirs+0.002
rings+0.002
 wow+0.002
ours+0.002
 are+0.001
Neg logit contributions
Just-0.004
bes-0.004
age-0.004
ager-0.004
P-0.004
Token or
Token ID393
Feature activation+3.55e-01

Pos logit contributions
 theirs+0.042
rings+0.035
 what+0.032
 wow+0.030
 are+0.030
Neg logit contributions
Just-0.045
age-0.042
ager-0.042
P-0.040
bes-0.040
Tokennam
Token ID7402
Feature activation+4.13e+00

Pos logit contributions
 theirs+0.026
rings+0.021
 wow+0.018
 what+0.018
 are+0.017
Neg logit contributions
Just-0.039
ager-0.037
age-0.037
P-0.036
bes-0.036
Tokenents
Token ID658
Feature activation+2.83e+00

Pos logit contributions
 theirs+0.212
rings+0.148
 what+0.127
 wow+0.113
 are+0.109
Neg logit contributions
Just-0.571
age-0.543
ager-0.540
P-0.528
bes-0.522
Token.
Token ID13
Feature activation+3.68e-01

Pos logit contributions
 theirs+0.277
rings+0.237
 wow+0.218
nam+0.215
 what+0.215
Neg logit contributions
Just-0.236
age-0.234
ager-0.219
sy-0.210
bes-0.209
Token<|endoftext|>
Token ID50256
Feature activation+1.21e+00

Pos logit contributions
 theirs+0.036
rings+0.031
 what+0.028
 wow+0.027
 are+0.027
Neg logit contributions
Just-0.034
age-0.031
ager-0.031
P-0.030
bes-0.029
TokenOnce
Token ID7454
Feature activation+1.11e+00

Pos logit contributions
 theirs+0.100
 what+0.082
rings+0.082
 are+0.081
 their+0.072
Neg logit contributions
Just-0.125
ager-0.118
age-0.116
ivering-0.114
bes-0.111
Token upon
Token ID2402
Feature activation-2.87e-02

Pos logit contributions
 theirs+0.102
rings+0.090
 wow+0.084
nam+0.080
 flashes+0.075
Neg logit contributions
Just-0.091
 year-0.088
P-0.085
eh-0.083
Lu-0.082
Token the
Token ID262
Feature activation+4.91e-02

Pos logit contributions
 theirs+0.019
rings+0.018
 wow+0.014
nam+0.014
ours+0.013
Neg logit contributions
Just-0.036
age-0.035
ager-0.034
sy-0.033
bes-0.033
Token rest
Token ID1334
Feature activation-6.10e-02

Pos logit contributions
 theirs+0.005
rings+0.004
 what+0.004
 wow+0.004
 are+0.003
Neg logit contributions
Just-0.005
age-0.004
ager-0.004
P-0.004
bes-0.004
Token of
Token ID286
Feature activation+1.24e+00

Pos logit contributions
Just+0.006
age+0.006
ager+0.006
P+0.006
bes+0.006
Neg logit contributions
 theirs-0.005
rings-0.004
 what-0.004
 are-0.004
 wow-0.004
Token the
Token ID262
Feature activation+1.39e-01

Pos logit contributions
 theirs+0.073
rings+0.070
 wow+0.052
 are+0.049
ours+0.048
Neg logit contributions
Just-0.137
bes-0.135
P-0.130
zer-0.130
ager-0.130
Token or
Token ID393
Feature activation+1.50e-01

Pos logit contributions
 theirs+0.013
rings+0.011
 what+0.010
 are+0.010
nam+0.010
Neg logit contributions
Just-0.014
age-0.012
ager-0.012
P-0.012
bes-0.012
Tokennam
Token ID7402
Feature activation+4.12e+00

Pos logit contributions
 theirs+0.012
rings+0.010
 wow+0.009
ours+0.008
 are+0.008
Neg logit contributions
Just-0.015
ager-0.014
age-0.014
P-0.013
fire-0.013
Tokenents
Token ID658
Feature activation+2.63e+00

Pos logit contributions
 theirs+0.223
rings+0.157
 what+0.140
 wow+0.130
 are+0.122
Neg logit contributions
Just-0.558
age-0.529
ager-0.526
P-0.514
ivering-0.507
Token onto
Token ID4291
Feature activation+7.43e-01

Pos logit contributions
 theirs+0.263
rings+0.226
 what+0.210
 wow+0.205
nam+0.202
Neg logit contributions
Just-0.225
age-0.215
ager-0.208
bes-0.197
sy-0.196
Token the
Token ID262
Feature activation+1.74e-01

Pos logit contributions
 theirs+0.044
rings+0.033
 what+0.028
 wow+0.025
 are+0.025
Neg logit contributions
Just-0.097
age-0.092
ager-0.092
P-0.090
bes-0.089
Token tree
Token ID5509
Feature activation+9.00e-01

Pos logit contributions
 theirs+0.016
rings+0.015
 what+0.014
nam+0.013
 are+0.013
Neg logit contributions
Just-0.016
ager-0.015
P-0.014
age-0.014
ivering-0.014
Token.
Token ID13
Feature activation+2.25e-02

Pos logit contributions
 theirs+0.085
rings+0.072
 what+0.067
 are+0.063
 wow+0.063
Neg logit contributions
Just-0.085
ager-0.079
age-0.078
P-0.076
bes-0.074
Token away
Token ID1497
Feature activation-1.86e+00

Pos logit contributions
 theirs+0.100
rings+0.087
 what+0.081
 wow+0.078
 are+0.077
Neg logit contributions
Just-0.077
age-0.071
ager-0.069
P-0.067
sy-0.065
Token,
Token ID11
Feature activation+2.56e-01

Pos logit contributions
Just+0.174
ager+0.163
age+0.163
P+0.159
bes+0.154
Neg logit contributions
 theirs-0.177
rings-0.150
 what-0.140
 wow-0.131
 are-0.131
Token a
Token ID257
Feature activation+7.06e-02

Pos logit contributions
 theirs+0.026
rings+0.022
 what+0.020
 are+0.019
 wow+0.019
Neg logit contributions
Just-0.023
age-0.021
ager-0.021
P-0.020
bes-0.020
Token bright
Token ID6016
Feature activation-1.77e-01

Pos logit contributions
 theirs+0.006
rings+0.005
 what+0.005
 wow+0.005
 are+0.005
Neg logit contributions
Just-0.007
ager-0.006
age-0.006
bes-0.006
P-0.006
Token blue
Token ID4171
Feature activation+1.29e-01

Pos logit contributions
Just+0.018
age+0.017
ager+0.017
P+0.016
bes+0.016
Neg logit contributions
 theirs-0.016
rings-0.013
 what-0.012
 wow-0.011
 are-0.011
Token spe
Token ID693
Feature activation+4.08e+00

Pos logit contributions
 theirs+0.013
rings+0.011
 what+0.010
 wow+0.009
 are+0.009
Neg logit contributions
Just-0.012
age-0.011
ager-0.011
P-0.011
bes-0.010
Tokenck
Token ID694
Feature activation+8.95e-01

Pos logit contributions
 theirs+0.328
rings+0.260
 what+0.232
 wow+0.217
 are+0.213
Neg logit contributions
Just-0.436
ager-0.403
amas-0.402
age-0.399
P-0.398
Token in
Token ID287
Feature activation-3.28e-01

Pos logit contributions
 theirs+0.092
rings+0.079
 what+0.073
 wow+0.070
 are+0.069
Neg logit contributions
Just-0.077
age-0.071
ager-0.071
P-0.068
ivering-0.066
Token the
Token ID262
Feature activation+6.37e-02

Pos logit contributions
Just+0.035
P+0.033
age+0.033
 entire+0.032
Now+0.032
Neg logit contributions
 theirs-0.022
rings-0.022
ours-0.017
nam-0.017
 maybe-0.017
Token sky
Token ID6766
Feature activation+4.90e-01

Pos logit contributions
 theirs+0.006
rings+0.005
 what+0.005
 are+0.005
 wow+0.005
Neg logit contributions
Just-0.006
ager-0.006
age-0.005
bes-0.005
P-0.005
Token.
Token ID13
Feature activation+1.76e-01

Pos logit contributions
 theirs+0.049
rings+0.042
 what+0.039
 wow+0.037
nam+0.037
Neg logit contributions
Just-0.044
age-0.041
ager-0.040
P-0.038
bes-0.038
Tokeneddy
Token ID21874
Feature activation-9.25e-01

Pos logit contributions
Just+0.051
ager+0.048
bes+0.045
age+0.044
P+0.043
Neg logit contributions
 theirs-0.066
rings-0.063
 what-0.053
 are-0.050
nam-0.049
Token bear
Token ID6842
Feature activation+1.63e-01

Pos logit contributions
Just+0.087
ager+0.077
P+0.073
ivering+0.072
Days+0.071
Neg logit contributions
 theirs-0.085
rings-0.082
 what-0.079
 are-0.074
 look-0.069
Token and
Token ID290
Feature activation-1.12e-01

Pos logit contributions
 theirs+0.015
rings+0.014
 what+0.013
 are+0.013
 wow+0.011
Neg logit contributions
Just-0.015
ager-0.014
P-0.014
age-0.013
ivering-0.013
Token watched
Token ID7342
Feature activation-1.00e+00

Pos logit contributions
Just+0.011
age+0.011
ager+0.010
bes+0.010
P+0.010
Neg logit contributions
 theirs-0.010
rings-0.008
 what-0.007
 wow-0.007
 are-0.006
Token in
Token ID287
Feature activation-2.05e-01

Pos logit contributions
Just+0.118
age+0.109
bes+0.107
ze+0.107
ager+0.107
Neg logit contributions
 theirs-0.066
rings-0.054
 are-0.044
 wow-0.043
nam-0.042
Token amaz
Token ID40642
Feature activation+4.06e+00

Pos logit contributions
Just+0.021
ager+0.020
bes+0.020
age+0.020
rd+0.019
Neg logit contributions
 theirs-0.015
rings-0.014
 wow-0.011
nam-0.011
ours-0.010
Tokenement
Token ID972
Feature activation+4.70e-01

Pos logit contributions
 theirs+0.396
rings+0.338
 what+0.306
nam+0.295
 are+0.294
Neg logit contributions
Just-0.374
ager-0.346
age-0.341
P-0.332
ivering-0.323
Token as
Token ID355
Feature activation+2.10e+00

Pos logit contributions
 theirs+0.047
rings+0.039
 what+0.036
 wow+0.036
 are+0.036
Neg logit contributions
Just-0.041
age-0.038
ager-0.037
bes-0.036
ivering-0.035
Token it
Token ID340
Feature activation+5.58e-01

Pos logit contributions
 theirs+0.139
rings+0.116
ours+0.093
 are+0.089
 wow+0.088
Neg logit contributions
Just-0.233
ager-0.216
Lu-0.213
sy-0.213
P-0.210
Token shrunk
Token ID38900
Feature activation-1.51e-01

Pos logit contributions
 theirs+0.052
rings+0.044
 what+0.041
 are+0.039
 wow+0.038
Neg logit contributions
Just-0.054
ager-0.050
age-0.050
P-0.048
bes-0.047
Token an
Token ID281
Feature activation+4.61e-02

Pos logit contributions
Just+0.014
ager+0.013
age+0.013
P+0.013
bes+0.013
Neg logit contributions
 theirs-0.015
rings-0.012
 what-0.012
 are-0.011
 wow-0.011
Token around
Token ID1088
Feature activation+1.10e+00

Pos logit contributions
Just+0.014
ager+0.013
age+0.013
P+0.013
sy+0.012
Neg logit contributions
 theirs-0.015
rings-0.012
 what-0.011
 wow-0.011
nam-0.010
Token stopped
Token ID5025
Feature activation+2.23e-01

Pos logit contributions
 theirs+0.075
rings+0.059
 wow+0.049
nam+0.048
 what+0.048
Neg logit contributions
Just-0.127
age-0.120
ager-0.120
P-0.117
bes-0.116
Token and
Token ID290
Feature activation+3.02e-01

Pos logit contributions
 theirs+0.023
rings+0.020
 wow+0.018
nam+0.018
 are+0.018
Neg logit contributions
Just-0.019
age-0.016
ivering-0.016
ager-0.016
P-0.015
Token watched
Token ID7342
Feature activation-1.06e+00

Pos logit contributions
 theirs+0.030
rings+0.024
 ours+0.022
ours+0.021
nam+0.021
Neg logit contributions
Just-0.026
age-0.025
ager-0.025
sy-0.023
ce-0.022
Token in
Token ID287
Feature activation-1.52e-01

Pos logit contributions
Just+0.120
age+0.111
ze+0.109
ager+0.108
bes+0.107
Neg logit contributions
 theirs-0.074
rings-0.061
nam-0.050
 are-0.049
ours-0.048
Token amaz
Token ID40642
Feature activation+4.04e+00

Pos logit contributions
Just+0.016
age+0.015
ager+0.015
 entire+0.015
bes+0.015
Neg logit contributions
 theirs-0.010
rings-0.010
ours-0.008
nam-0.007
 wow-0.007
Tokenement
Token ID972
Feature activation+4.88e-01

Pos logit contributions
 theirs+0.406
rings+0.351
 what+0.313
nam+0.309
 are+0.303
Neg logit contributions
Just-0.361
ager-0.333
age-0.324
P-0.320
ivering-0.311
Token.
Token ID13
Feature activation+1.83e-01

Pos logit contributions
 theirs+0.050
rings+0.042
nam+0.038
 what+0.038
 wow+0.038
Neg logit contributions
Just-0.042
age-0.038
ager-0.037
bes-0.035
ivering-0.035
Token They
Token ID1119
Feature activation+4.65e-02

Pos logit contributions
 theirs+0.017
rings+0.014
 what+0.013
 are+0.012
 wow+0.012
Neg logit contributions
Just-0.018
age-0.017
ager-0.017
P-0.016
bes-0.016
Token were
Token ID547
Feature activation+1.24e+00

Pos logit contributions
 theirs+0.004
rings+0.004
ours+0.003
 ours+0.003
 what+0.003
Neg logit contributions
Just-0.004
ager-0.004
age-0.004
sy-0.004
P-0.004
Token so
Token ID523
Feature activation+6.75e-01

Pos logit contributions
 theirs+0.116
rings+0.101
 what+0.088
nam+0.085
 wow+0.085
Neg logit contributions
Just-0.116
age-0.109
ager-0.107
sy-0.103
P-0.102
Token calmed
Token ID49566
Feature activation+6.60e-01

Pos logit contributions
Just+0.053
age+0.050
ager+0.050
P+0.048
bes+0.047
Neg logit contributions
 theirs-0.037
rings-0.030
 what-0.027
 wow-0.025
 are-0.025
Token down
Token ID866
Feature activation+9.03e-02

Pos logit contributions
 theirs+0.061
rings+0.052
 wow+0.047
nam+0.045
 what+0.044
Neg logit contributions
Just-0.059
age-0.055
ager-0.053
sy-0.051
ivering-0.050
Token and
Token ID290
Feature activation+2.76e-01

Pos logit contributions
 theirs+0.009
rings+0.008
 what+0.007
 wow+0.007
 are+0.007
Neg logit contributions
Just-0.008
age-0.007
ager-0.007
P-0.007
bes-0.007
Token watched
Token ID7342
Feature activation-1.08e+00

Pos logit contributions
 theirs+0.025
rings+0.021
 what+0.017
nam+0.017
 wow+0.017
Neg logit contributions
Just-0.026
ager-0.025
age-0.024
sy-0.023
ce-0.023
Token in
Token ID287
Feature activation-2.72e-01

Pos logit contributions
Just+0.120
age+0.109
ager+0.109
ze+0.107
bes+0.107
Neg logit contributions
 theirs-0.079
rings-0.068
nam-0.055
 are-0.053
 wow-0.052
Token amaz
Token ID40642
Feature activation+4.03e+00

Pos logit contributions
Just+0.030
ager+0.028
age+0.028
bes+0.027
zer+0.027
Neg logit contributions
 theirs-0.018
rings-0.017
nam-0.013
ours-0.012
 wow-0.012
Tokenement
Token ID972
Feature activation+5.15e-01

Pos logit contributions
 theirs+0.415
rings+0.363
nam+0.324
 what+0.320
 are+0.312
Neg logit contributions
Just-0.350
ager-0.322
age-0.309
P-0.305
ivering-0.298
Token as
Token ID355
Feature activation+2.14e+00

Pos logit contributions
 theirs+0.051
rings+0.043
nam+0.039
 wow+0.038
 what+0.038
Neg logit contributions
Just-0.046
age-0.042
ager-0.041
bes-0.039
ivering-0.039
Token the
Token ID262
Feature activation+3.87e-02

Pos logit contributions
 theirs+0.145
rings+0.141
ours+0.115
endant+0.103
nam+0.095
Neg logit contributions
Just-0.220
fire-0.208
ager-0.208
ce-0.203
Lu-0.200
Token rainbow
Token ID27223
Feature activation+1.86e+00

Pos logit contributions
 theirs+0.004
rings+0.003
 what+0.003
 wow+0.003
 are+0.003
Neg logit contributions
Just-0.004
ager-0.004
age-0.003
P-0.003
bes-0.003
Token melted
Token ID24178
Feature activation+3.02e-01

Pos logit contributions
 theirs+0.180
rings+0.152
 what+0.141
 wow+0.134
nam+0.133
Neg logit contributions
Just-0.170
age-0.160
ager-0.158
P-0.151
bes-0.150
Token the
Token ID262
Feature activation-1.22e-02

Pos logit contributions
 theirs+0.023
rings+0.021
 are+0.017
nam+0.017
 wow+0.016
Neg logit contributions
Just-0.034
ce-0.030
sy-0.030
ager-0.030
zer-0.029
Token zipper
Token ID48992
Feature activation+8.18e-01

Pos logit contributions
Just+0.001
age+0.001
ager+0.001
P+0.001
bes+0.001
Neg logit contributions
 theirs-0.001
rings-0.001
 what-0.001
 wow-0.001
 are-0.001
Token and
Token ID290
Feature activation+1.03e-01

Pos logit contributions
 theirs+0.089
rings+0.076
 what+0.072
 wow+0.069
 are+0.068
Neg logit contributions
Just-0.066
age-0.061
ager-0.060
P-0.057
bes-0.057
Token gasped
Token ID45236
Feature activation+5.16e-01

Pos logit contributions
 theirs+0.010
rings+0.008
 what+0.007
 are+0.007
 wow+0.007
Neg logit contributions
Just-0.010
ager-0.009
age-0.009
P-0.009
sy-0.009
Token with
Token ID351
Feature activation-1.16e-01

Pos logit contributions
 theirs+0.053
rings+0.045
 what+0.042
 wow+0.040
 are+0.040
Neg logit contributions
Just-0.045
age-0.042
ager-0.041
P-0.040
bes-0.039
Token amaz
Token ID40642
Feature activation+4.03e+00

Pos logit contributions
Just+0.009
ager+0.009
age+0.009
P+0.009
sy+0.008
Neg logit contributions
rings-0.011
 theirs-0.011
ours-0.009
nam-0.008
angles-0.008
Tokenement
Token ID972
Feature activation+4.36e-01

Pos logit contributions
 theirs+0.401
rings+0.346
 what+0.310
 are+0.302
nam+0.301
Neg logit contributions
Just-0.363
ager-0.334
age-0.328
P-0.319
ivering-0.314
Token at
Token ID379
Feature activation+1.41e+00

Pos logit contributions
 theirs+0.046
rings+0.039
 are+0.036
nam+0.036
 wow+0.035
Neg logit contributions
Just-0.035
age-0.032
ager-0.032
sy-0.030
ivering-0.030
Token all
Token ID477
Feature activation+1.46e+00

Pos logit contributions
 theirs+0.095
rings+0.086
nam+0.065
 wow+0.064
 are+0.064
Neg logit contributions
Just-0.151
ager-0.143
bes-0.141
zer-0.140
age-0.140
Token the
Token ID262
Feature activation+7.42e-02

Pos logit contributions
 theirs+0.103
rings+0.099
 wow+0.079
nam+0.078
 are+0.068
Neg logit contributions
Just-0.153
age-0.147
ager-0.147
sy-0.145
ce-0.142
Token treasures
Token ID29561
Feature activation+5.05e-01

Pos logit contributions
 theirs+0.007
rings+0.005
 what+0.005
 wow+0.005
 are+0.005
Neg logit contributions
Just-0.008
ager-0.007
age-0.007
P-0.007
bes-0.007
Token time
Token ID640
Feature activation+4.58e-02

Pos logit contributions
 theirs+0.038
rings+0.032
 what+0.030
 wow+0.029
 are+0.028
Neg logit contributions
Just-0.036
age-0.033
ager-0.033
P-0.032
bes-0.031
Token playing
Token ID2712
Feature activation-5.33e-01

Pos logit contributions
 theirs+0.004
rings+0.004
 what+0.003
 wow+0.003
 are+0.003
Neg logit contributions
Just-0.004
age-0.004
ager-0.004
P-0.004
bes-0.004
Token with
Token ID351
Feature activation-2.13e-01

Pos logit contributions
Just+0.044
ager+0.040
age+0.040
ivering+0.038
sy+0.036
Neg logit contributions
 theirs-0.058
 what-0.049
rings-0.048
 are-0.046
 their-0.046
Token her
Token ID607
Feature activation+3.44e-01

Pos logit contributions
Just+0.024
bes+0.023
P+0.023
age+0.023
ager+0.023
Neg logit contributions
 theirs-0.014
rings-0.012
 wow-0.009
ours-0.009
 are-0.009
Token or
Token ID393
Feature activation+1.54e-01

Pos logit contributions
 theirs+0.034
rings+0.029
 what+0.027
 wow+0.025
 are+0.025
Neg logit contributions
Just-0.032
age-0.029
ager-0.029
P-0.028
bes-0.028
Tokennam
Token ID7402
Feature activation+4.00e+00

Pos logit contributions
 theirs+0.013
rings+0.010
 wow+0.009
 are+0.009
 what+0.009
Neg logit contributions
Just-0.016
age-0.014
bes-0.014
P-0.014
ager-0.014
Tokenents
Token ID658
Feature activation+2.70e+00

Pos logit contributions
 theirs+0.227
rings+0.165
 what+0.146
 wow+0.133
 are+0.128
Neg logit contributions
Just-0.531
age-0.503
ager-0.501
P-0.490
bes-0.483
Token and
Token ID290
Feature activation-6.96e-02

Pos logit contributions
 theirs+0.273
rings+0.233
 what+0.218
 wow+0.213
nam+0.206
Neg logit contributions
Just-0.230
age-0.219
ager-0.213
P-0.202
bes-0.201
Token making
Token ID1642
Feature activation-1.04e+00

Pos logit contributions
Just+0.007
age+0.007
ager+0.006
P+0.006
bes+0.006
Neg logit contributions
 theirs-0.006
rings-0.005
 what-0.005
 wow-0.004
 are-0.004
Token her
Token ID607
Feature activation+2.03e-01

Pos logit contributions
Just+0.111
age+0.106
ager+0.105
bes+0.103
P+0.102
Neg logit contributions
 theirs-0.078
rings-0.066
 wow-0.055
 are-0.054
 what-0.053
Token special
Token ID2041
Feature activation-5.04e-02

Pos logit contributions
 theirs+0.018
rings+0.014
 wow+0.013
 what+0.013
ours+0.012
Neg logit contributions
age-0.019
Just-0.019
bes-0.018
ager-0.018
ze-0.018
Token Tim
Token ID5045
Feature activation+7.32e-01

Pos logit contributions
Just+0.006
age+0.005
ager+0.005
P+0.005
bes+0.005
Neg logit contributions
 theirs-0.002
rings-0.001
 what-0.001
 wow-0.001
 are-0.001
Token watched
Token ID7342
Feature activation-1.28e+00

Pos logit contributions
 theirs+0.038
 what+0.035
rings+0.032
 are+0.029
 Tom+0.028
Neg logit contributions
fire-0.088
bes-0.087
Just-0.086
oster-0.086
ager-0.085
Token them
Token ID606
Feature activation-3.25e-01

Pos logit contributions
Just+0.147
age+0.137
ager+0.134
P+0.131
bes+0.131
Neg logit contributions
 theirs-0.091
rings-0.076
 what-0.062
 wow-0.062
 are-0.061
Token with
Token ID351
Feature activation-1.94e-01

Pos logit contributions
Just+0.027
age+0.025
sy+0.024
ager+0.024
ivering+0.023
Neg logit contributions
 theirs-0.033
rings-0.029
nam-0.026
 wow-0.026
 what-0.025
Token pure
Token ID5899
Feature activation+9.18e-01

Pos logit contributions
ze+0.015
zer+0.015
Just+0.015
age+0.015
bes+0.015
Neg logit contributions
rings-0.017
 theirs-0.016
ours-0.015
angles-0.013
endant-0.013
Token amaz
Token ID40642
Feature activation+3.97e+00

Pos logit contributions
 theirs+0.078
rings+0.067
 what+0.059
 wow+0.057
nam+0.056
Neg logit contributions
Just-0.093
age-0.088
ager-0.086
P-0.084
bes-0.083
Tokenement
Token ID972
Feature activation+4.83e-01

Pos logit contributions
 theirs+0.340
rings+0.272
 what+0.259
 wow+0.237
 are+0.233
Neg logit contributions
Just-0.417
age-0.396
ager-0.391
P-0.381
bes-0.376
Token,
Token ID11
Feature activation+3.41e-01

Pos logit contributions
 theirs+0.047
rings+0.040
 what+0.037
 wow+0.036
nam+0.036
Neg logit contributions
Just-0.044
age-0.041
ager-0.040
bes-0.038
ivering-0.038
Token never
Token ID1239
Feature activation-7.06e-01

Pos logit contributions
 theirs+0.035
rings+0.030
 what+0.027
 are+0.026
nam+0.026
Neg logit contributions
Just-0.030
age-0.027
ager-0.026
bes-0.026
P-0.025
Token t
Token ID256
Feature activation-9.80e-01

Pos logit contributions
Just+0.054
age+0.048
ager+0.048
ivering+0.046
 seek+0.045
Neg logit contributions
 theirs-0.074
rings-0.063
angles-0.058
ours-0.057
 wow-0.056
Tokeniring
Token ID3428
Feature activation-2.66e-01

Pos logit contributions
Just+0.073
ager+0.067
age+0.066
P+0.063
bes+0.063
Neg logit contributions
 theirs-0.113
rings-0.100
 what-0.092
 are-0.088
 wow-0.087
Token friends
Token ID2460
Feature activation-6.31e-01

Pos logit contributions
 theirs+0.063
rings+0.053
 what+0.048
 wow+0.045
 are+0.045
Neg logit contributions
Just-0.073
age-0.068
ager-0.068
P-0.066
bes-0.065
Token stopped
Token ID5025
Feature activation+9.65e-02

Pos logit contributions
Just+0.067
age+0.063
ager+0.062
P+0.061
bes+0.060
Neg logit contributions
 theirs-0.052
rings-0.043
 what-0.040
 are-0.037
 wow-0.037
Token and
Token ID290
Feature activation-2.86e-01

Pos logit contributions
 theirs+0.009
rings+0.008
 what+0.007
 wow+0.007
 are+0.007
Neg logit contributions
Just-0.009
age-0.008
ager-0.008
P-0.008
ivering-0.008
Token watched
Token ID7342
Feature activation-1.26e+00

Pos logit contributions
Just+0.025
ager+0.023
age+0.022
P+0.022
sy+0.022
Neg logit contributions
 theirs-0.029
rings-0.025
 ours-0.021
 are-0.021
 what-0.020
Token in
Token ID287
Feature activation-3.73e-01

Pos logit contributions
Just+0.142
ager+0.130
age+0.130
bes+0.127
P+0.125
Neg logit contributions
 theirs-0.092
rings-0.078
 are-0.064
 what-0.063
 wow-0.063
Token amaz
Token ID40642
Feature activation+3.97e+00

Pos logit contributions
Just+0.040
ager+0.038
age+0.036
bes+0.036
rd+0.035
Neg logit contributions
 theirs-0.028
rings-0.026
nam-0.020
 wow-0.019
ours-0.018
Tokenement
Token ID972
Feature activation+2.78e-01

Pos logit contributions
 theirs+0.401
rings+0.353
nam+0.312
 what+0.310
 are+0.306
Neg logit contributions
Just-0.348
ager-0.321
age-0.305
P-0.304
ivering-0.293
Token.
Token ID13
Feature activation-3.43e-01

Pos logit contributions
 theirs+0.027
rings+0.022
 what+0.020
 wow+0.020
 are+0.020
Neg logit contributions
Just-0.026
age-0.023
ager-0.023
bes-0.022
ivering-0.022
Token The
Token ID383
Feature activation-4.01e-02

Pos logit contributions
Just+0.037
age+0.034
ager+0.034
P+0.033
bes+0.032
Neg logit contributions
 theirs-0.028
rings-0.023
 what-0.020
 are-0.020
 wow-0.019
Token dog
Token ID3290
Feature activation-1.83e-01

Pos logit contributions
Just+0.004
age+0.004
ager+0.004
P+0.003
bes+0.003
Neg logit contributions
 theirs-0.004
rings-0.003
 what-0.003
 wow-0.003
 are-0.003
Token too
Token ID1165
Feature activation+8.28e-01

Pos logit contributions
Just+0.018
age+0.017
P+0.017
ager+0.017
amas+0.016
Neg logit contributions
 theirs-0.016
rings-0.013
 what-0.013
 wow-0.012
 are-0.012
TokenWow
Token ID22017
Feature activation+1.26e+00

Pos logit contributions
age+0.003
Just+0.003
ager+0.003
ivering+0.003
bes+0.003
Neg logit contributions
 theirs-0.003
rings-0.003
 what-0.003
 wow-0.003
nam-0.002
Token,"
Token ID553
Feature activation+8.88e-01

Pos logit contributions
 theirs+0.144
rings+0.123
 what+0.110
nam+0.110
 wow+0.107
Neg logit contributions
Just-0.096
ager-0.088
age-0.087
P-0.084
sy-0.082
Token Emily
Token ID17608
Feature activation+4.46e-01

Pos logit contributions
 theirs+0.078
rings+0.063
 what+0.054
 wow+0.053
 are+0.052
Neg logit contributions
Just-0.093
ager-0.086
age-0.086
P-0.085
bes-0.082
Token gasped
Token ID45236
Feature activation+4.31e-01

Pos logit contributions
 theirs+0.029
rings+0.025
 what+0.023
 are+0.022
 wow+0.021
Neg logit contributions
Just-0.050
P-0.049
ivering-0.049
age-0.049
ager-0.047
Token in
Token ID287
Feature activation-4.16e-01

Pos logit contributions
 theirs+0.043
rings+0.037
 what+0.035
 wow+0.032
 are+0.032
Neg logit contributions
Just-0.038
age-0.036
ager-0.036
P-0.034
bes-0.034
Token amaz
Token ID40642
Feature activation+3.95e+00

Pos logit contributions
Just+0.047
ager+0.044
age+0.043
P+0.042
bes+0.041
Neg logit contributions
 theirs-0.032
rings-0.028
 what-0.022
nam-0.021
 wow-0.021
Tokenement
Token ID972
Feature activation+2.72e-01

Pos logit contributions
 theirs+0.385
rings+0.330
 what+0.298
 are+0.286
nam+0.286
Neg logit contributions
Just-0.366
ager-0.338
age-0.333
P-0.325
ivering-0.317
Token.
Token ID13
Feature activation+3.77e-01

Pos logit contributions
 theirs+0.027
rings+0.023
 what+0.021
 are+0.020
 wow+0.020
Neg logit contributions
Just-0.025
ager-0.023
age-0.023
P-0.022
bes-0.022
Token She
Token ID1375
Feature activation+8.41e-02

Pos logit contributions
 theirs+0.027
rings+0.022
 what+0.021
 wow+0.019
 maybe+0.018
Neg logit contributions
Just-0.042
ager-0.042
age-0.041
P-0.040
ivering-0.040
Token realized
Token ID6939
Feature activation+5.31e-01

Pos logit contributions
 theirs+0.006
 what+0.006
rings+0.006
 wow+0.005
 are+0.005
Neg logit contributions
age-0.008
P-0.008
ivering-0.008
Just-0.008
amas-0.008
Token that
Token ID326
Feature activation+5.42e-01

Pos logit contributions
 theirs+0.042
rings+0.035
 are+0.030
nam+0.029
ours+0.029
Neg logit contributions
Just-0.056
ager-0.049
P-0.049
age-0.048
bes-0.047
Token
Token ID198
Feature activation-3.09e-01

Pos logit contributions
 theirs+0.154
rings+0.132
 what+0.122
 wow+0.117
 are+0.116
Neg logit contributions
Just-0.135
age-0.125
ager-0.124
P-0.119
bes-0.118
Token
Token ID198
Feature activation-3.41e-01

Pos logit contributions
ager+0.033
age+0.032
ivering+0.032
bes+0.031
amas+0.031
Neg logit contributions
 theirs-0.021
 what-0.018
rings-0.017
 maybe-0.016
 Tom-0.016
TokenSarah
Token ID29284
Feature activation-2.30e-02

Pos logit contributions
amas+0.026
ager+0.026
bes+0.025
age+0.024
ivering+0.024
Neg logit contributions
 theirs-0.031
 what-0.028
rings-0.026
 their-0.026
 they-0.025
Token watched
Token ID7342
Feature activation-1.25e+00

Pos logit contributions
P+0.002
amas+0.002
bes+0.002
ager+0.002
Just+0.002
Neg logit contributions
 theirs-0.002
 what-0.001
rings-0.001
 are-0.001
 their-0.001
Token in
Token ID287
Feature activation-3.92e-01

Pos logit contributions
Just+0.137
age+0.125
ivering+0.121
ze+0.121
bes+0.121
Neg logit contributions
 theirs-0.098
rings-0.083
nam-0.068
 are-0.067
 wow-0.067
Token amaz
Token ID40642
Feature activation+3.95e+00

Pos logit contributions
Just+0.041
age+0.039
ivering+0.037
ager+0.037
bes+0.037
Neg logit contributions
 theirs-0.030
rings-0.026
nam-0.021
angles-0.020
 wow-0.019
Tokenement
Token ID972
Feature activation+3.57e-01

Pos logit contributions
 theirs+0.394
rings+0.341
 what+0.303
nam+0.299
 are+0.296
Neg logit contributions
Just-0.358
ager-0.327
age-0.320
P-0.314
ivering-0.308
Token as
Token ID355
Feature activation+1.90e+00

Pos logit contributions
 theirs+0.033
rings+0.027
 are+0.024
 wow+0.024
nam+0.024
Neg logit contributions
Just-0.035
age-0.031
ager-0.030
ivering-0.030
bes-0.029
Token the
Token ID262
Feature activation-3.61e-02

Pos logit contributions
 theirs+0.141
rings+0.125
ours+0.101
 ours+0.093
angles+0.093
Neg logit contributions
Just-0.200
Lu-0.186
Now-0.179
ce-0.176
B-0.175
Token water
Token ID1660
Feature activation-2.62e-01

Pos logit contributions
Just+0.003
ager+0.003
age+0.003
P+0.003
ivering+0.003
Neg logit contributions
 theirs-0.003
rings-0.003
 what-0.003
 wow-0.002
 are-0.002
Token became
Token ID2627
Feature activation+1.01e+00

Pos logit contributions
Just+0.025
ager+0.024
age+0.024
P+0.023
bes+0.023
Neg logit contributions
 theirs-0.023
rings-0.020
 what-0.019
 are-0.018
 wow-0.017
Token were
Token ID547
Feature activation+1.17e+00

Pos logit contributions
Just+0.094
age+0.087
ager+0.087
P+0.084
bes+0.083
Neg logit contributions
 theirs-0.080
rings-0.067
 what-0.061
 wow-0.057
 are-0.057
Token filled
Token ID5901
Feature activation+8.58e-01

Pos logit contributions
 theirs+0.108
rings+0.092
 what+0.083
 wow+0.079
 are+0.079
Neg logit contributions
Just-0.112
age-0.105
ager-0.104
P-0.100
bes-0.099
Token with
Token ID351
Feature activation-1.97e-01

Pos logit contributions
 theirs+0.092
 what+0.076
 their+0.073
rings+0.071
 are+0.068
Neg logit contributions
Just-0.074
age-0.069
ivering-0.067
ager-0.065
P-0.064
Token wonder
Token ID4240
Feature activation+2.41e+00

Pos logit contributions
age+0.015
Just+0.015
ager+0.015
sy+0.014
 entire+0.014
Neg logit contributions
 theirs-0.018
rings-0.018
ours-0.015
 wow-0.014
angles-0.014
Token and
Token ID290
Feature activation+7.32e-02

Pos logit contributions
 theirs+0.236
rings+0.208
nam+0.184
 wow+0.182
ours+0.176
Neg logit contributions
Just-0.200
age-0.185
ager-0.182
sy-0.172
bes-0.171
Token amaz
Token ID40642
Feature activation+3.95e+00

Pos logit contributions
 theirs+0.007
rings+0.006
ours+0.005
nam+0.005
 wow+0.005
Neg logit contributions
Just-0.007
age-0.006
ager-0.006
sy-0.006
fire-0.006
Tokenement
Token ID972
Feature activation+3.64e-01

Pos logit contributions
 theirs+0.382
rings+0.329
 what+0.296
 are+0.285
nam+0.284
Neg logit contributions
Just-0.366
ager-0.338
age-0.334
P-0.321
ivering-0.315
Token.
Token ID13
Feature activation+9.71e-02

Pos logit contributions
 theirs+0.036
rings+0.030
nam+0.028
 are+0.027
 wow+0.027
Neg logit contributions
Just-0.032
age-0.030
ager-0.029
sy-0.028
ivering-0.027
Token They
Token ID1119
Feature activation+1.89e-02

Pos logit contributions
 theirs+0.008
rings+0.007
 what+0.006
 are+0.006
nam+0.006
Neg logit contributions
Just-0.010
age-0.009
ager-0.009
P-0.009
bes-0.009
Token thanked
Token ID26280
Feature activation+6.82e-01

Pos logit contributions
 theirs+0.002
rings+0.002
 what+0.001
ours+0.001
 wow+0.001
Neg logit contributions
Just-0.002
ager-0.002
age-0.002
sy-0.002
P-0.002
Token the
Token ID262
Feature activation-7.09e-02

Pos logit contributions
 theirs+0.040
rings+0.035
ours+0.026
nam+0.026
 wow+0.025
Neg logit contributions
Just-0.082
ager-0.078
age-0.076
P-0.075
ce-0.074
Token they
Token ID484
Feature activation-1.75e-01

Pos logit contributions
Just+0.015
ager+0.013
age+0.013
bes+0.013
sy+0.013
Neg logit contributions
 theirs-0.012
rings-0.011
 what-0.009
 wow-0.009
 are-0.009
Token both
Token ID1111
Feature activation+5.76e-01

Pos logit contributions
Just+0.016
ager+0.015
age+0.015
P+0.014
sy+0.014
Neg logit contributions
 theirs-0.017
rings-0.014
 what-0.012
 wow-0.012
nam-0.012
Token looked
Token ID3114
Feature activation-1.22e-01

Pos logit contributions
 theirs+0.055
rings+0.047
 what+0.043
 wow+0.041
nam+0.040
Neg logit contributions
Just-0.053
ager-0.050
age-0.049
P-0.047
sy-0.047
Token around
Token ID1088
Feature activation+9.23e-01

Pos logit contributions
Just+0.011
ager+0.010
sy+0.010
age+0.009
ivering+0.009
Neg logit contributions
 theirs-0.011
rings-0.011
nam-0.008
 wow-0.008
 are-0.008
Token in
Token ID287
Feature activation-3.10e-01

Pos logit contributions
 theirs+0.097
rings+0.087
 what+0.075
 wow+0.075
nam+0.074
Neg logit contributions
Just-0.077
ager-0.068
age-0.066
P-0.065
bes-0.063
Token amaz
Token ID40642
Feature activation+3.95e+00

Pos logit contributions
Just+0.034
rd+0.031
ager+0.031
 entire+0.031
P+0.031
Neg logit contributions
rings-0.021
 theirs-0.020
nam-0.015
ours-0.014
 wow-0.014
Tokenement
Token ID972
Feature activation+2.47e-01

Pos logit contributions
 theirs+0.402
rings+0.351
nam+0.313
 what+0.313
 are+0.305
Neg logit contributions
Just-0.342
ager-0.315
age-0.303
P-0.300
ivering-0.290
Token.
Token ID13
Feature activation-1.32e-01

Pos logit contributions
 theirs+0.024
rings+0.020
 what+0.019
 wow+0.018
 are+0.018
Neg logit contributions
Just-0.023
ager-0.021
age-0.021
P-0.020
bes-0.020
Token The
Token ID383
Feature activation-7.60e-02

Pos logit contributions
Just+0.014
age+0.013
ager+0.013
P+0.012
bes+0.012
Neg logit contributions
 theirs-0.011
rings-0.009
 what-0.008
 wow-0.008
 are-0.008
Token lake
Token ID13546
Feature activation+2.58e-01

Pos logit contributions
Just+0.007
age+0.007
ager+0.007
P+0.006
bes+0.006
Neg logit contributions
 theirs-0.007
rings-0.006
 what-0.006
 wow-0.006
 are-0.005
Token was
Token ID373
Feature activation-3.90e-01

Pos logit contributions
 theirs+0.028
rings+0.025
 what+0.023
 wow+0.022
 are+0.022
Neg logit contributions
Just-0.020
age-0.019
ager-0.019
P-0.018
bes-0.017
Token seen
Token ID1775
Feature activation+7.48e-02

Pos logit contributions
Just+0.027
ager+0.025
age+0.025
P+0.024
bes+0.024
Neg logit contributions
 theirs-0.027
rings-0.023
 what-0.021
 wow-0.020
 are-0.020
Token!
Token ID0
Feature activation-1.33e-01

Pos logit contributions
 theirs+0.007
rings+0.006
 what+0.005
 are+0.005
 wow+0.005
Neg logit contributions
Just-0.007
ager-0.007
age-0.007
P-0.007
bes-0.006
Token She
Token ID1375
Feature activation-3.28e-02

Pos logit contributions
Just+0.013
age+0.012
ager+0.012
P+0.012
bes+0.012
Neg logit contributions
 theirs-0.012
rings-0.010
 what-0.009
 wow-0.009
 are-0.009
Token gasped
Token ID45236
Feature activation+3.60e-01

Pos logit contributions
Just+0.003
age+0.003
ager+0.003
ivering+0.003
P+0.003
Neg logit contributions
 theirs-0.003
rings-0.003
 what-0.003
 are-0.002
 wow-0.002
Token in
Token ID287
Feature activation-4.43e-01

Pos logit contributions
 theirs+0.039
rings+0.034
 what+0.032
 wow+0.030
 are+0.030
Neg logit contributions
Just-0.029
age-0.027
ager-0.027
P-0.026
bes-0.025
Token amaz
Token ID40642
Feature activation+3.95e+00

Pos logit contributions
Just+0.048
ager+0.045
age+0.044
P+0.044
bes+0.043
Neg logit contributions
 theirs-0.034
rings-0.030
ours-0.023
nam-0.022
 maybe-0.022
Tokenement
Token ID972
Feature activation+2.41e-01

Pos logit contributions
 theirs+0.396
rings+0.340
 what+0.305
nam+0.299
 are+0.297
Neg logit contributions
Just-0.353
ager-0.326
age-0.318
P-0.312
ivering-0.304
Token,
Token ID11
Feature activation+1.53e-01

Pos logit contributions
 theirs+0.022
rings+0.018
 what+0.017
 are+0.016
 wow+0.016
Neg logit contributions
Just-0.024
age-0.022
ager-0.022
ivering-0.020
bes-0.020
Token and
Token ID290
Feature activation-8.75e-02

Pos logit contributions
 theirs+0.015
rings+0.013
 what+0.012
 are+0.011
 wow+0.011
Neg logit contributions
Just-0.014
age-0.013
ager-0.013
P-0.012
bes-0.012
Token her
Token ID607
Feature activation+2.91e-02

Pos logit contributions
Just+0.009
ager+0.009
age+0.009
P+0.008
bes+0.008
Neg logit contributions
 theirs-0.007
rings-0.006
 what-0.005
 are-0.005
 wow-0.005
Token tears
Token ID10953
Feature activation+1.23e+00

Pos logit contributions
 theirs+0.003
rings+0.002
 what+0.002
 wow+0.002
 are+0.002
Neg logit contributions
Just-0.003
age-0.003
ager-0.003
P-0.003
bes-0.003
Token Lily
Token ID20037
Feature activation+3.93e-01

Pos logit contributions
 theirs+0.029
rings+0.023
ours+0.021
endant+0.021
aly+0.020
Neg logit contributions
Just-0.026
P-0.026
Lu-0.025
 seek-0.024
But-0.024
Token stopped
Token ID5025
Feature activation-3.46e-02

Pos logit contributions
 theirs+0.022
rings+0.021
 what+0.021
 are+0.019
 their+0.019
Neg logit contributions
age-0.044
Just-0.043
ager-0.042
ivering-0.042
amas-0.042
Token and
Token ID290
Feature activation+7.33e-02

Pos logit contributions
Just+0.003
age+0.003
P+0.003
ager+0.003
ivering+0.003
Neg logit contributions
 theirs-0.003
rings-0.003
 wow-0.003
 are-0.002
 what-0.002
Token stared
Token ID18484
Feature activation-1.03e+00

Pos logit contributions
 theirs+0.008
rings+0.007
 ours+0.006
 are+0.006
bars+0.006
Neg logit contributions
Just-0.006
ager-0.005
P-0.005
ce-0.005
bes-0.005
Token in
Token ID287
Feature activation-3.66e-01

Pos logit contributions
Just+0.099
age+0.089
ivering+0.088
P+0.088
ager+0.087
Neg logit contributions
 theirs-0.096
rings-0.081
 are-0.073
 wow-0.071
nam-0.069
Token amaz
Token ID40642
Feature activation+3.95e+00

Pos logit contributions
Just+0.035
 entire+0.033
Lu+0.032
ager+0.032
P+0.032
Neg logit contributions
 theirs-0.029
rings-0.028
angles-0.022
ours-0.021
bars-0.021
Tokenement
Token ID972
Feature activation+4.70e-01

Pos logit contributions
 theirs+0.392
rings+0.335
 what+0.302
 are+0.294
nam+0.293
Neg logit contributions
Just-0.360
ager-0.330
age-0.325
P-0.321
ivering-0.312
Token.
Token ID13
Feature activation-3.16e-02

Pos logit contributions
 theirs+0.048
rings+0.040
 are+0.038
 wow+0.037
 what+0.037
Neg logit contributions
Just-0.041
age-0.036
ager-0.036
ivering-0.035
bes-0.034
Token The
Token ID383
Feature activation-2.38e-02

Pos logit contributions
Just+0.003
age+0.003
ager+0.003
bes+0.003
P+0.003
Neg logit contributions
 theirs-0.003
rings-0.002
 what-0.002
 are-0.002
 wow-0.002
Token bush
Token ID24484
Feature activation-2.87e-03

Pos logit contributions
ager+0.002
Just+0.002
age+0.002
bes+0.002
oster+0.002
Neg logit contributions
 theirs-0.002
 what-0.002
rings-0.002
 are-0.002
 look-0.001
Token was
Token ID373
Feature activation-2.51e-01

Pos logit contributions
Just+0.000
ager+0.000
age+0.000
P+0.000
bes+0.000
Neg logit contributions
 theirs-0.000
rings-0.000
 what-0.000
 are-0.000
 wow-0.000
Token it
Token ID340
Feature activation+3.85e-01

Pos logit contributions
Just+0.033
age+0.031
ager+0.031
P+0.031
ivering+0.030
Neg logit contributions
 theirs-0.012
rings-0.008
 what-0.007
 wow-0.006
 are-0.006
Token often
Token ID1690
Feature activation-1.07e-02

Pos logit contributions
 theirs+0.023
 what+0.019
rings+0.017
 are+0.016
 their+0.015
Neg logit contributions
Just-0.048
ivering-0.046
P-0.045
ager-0.045
bes-0.045
Token and
Token ID290
Feature activation+2.79e-01

Pos logit contributions
Just+0.001
ager+0.001
age+0.001
P+0.001
ivering+0.001
Neg logit contributions
 theirs-0.001
rings-0.001
 what-0.001
 are-0.001
 wow-0.001
Token watched
Token ID7342
Feature activation-1.21e+00

Pos logit contributions
 theirs+0.028
rings+0.024
 what+0.022
 wow+0.021
 are+0.021
Neg logit contributions
Just-0.025
age-0.023
ager-0.023
P-0.022
bes-0.021
Token in
Token ID287
Feature activation-2.86e-01

Pos logit contributions
Just+0.140
age+0.131
ager+0.129
ze+0.127
bes+0.126
Neg logit contributions
 theirs-0.079
rings-0.069
nam-0.054
 are-0.053
 wow-0.052
Token amaz
Token ID40642
Feature activation+3.95e+00

Pos logit contributions
Just+0.027
age+0.026
 entire+0.026
 year+0.025
ager+0.025
Neg logit contributions
rings-0.022
 theirs-0.021
ours-0.017
 wow-0.017
nam-0.016
Tokenement
Token ID972
Feature activation+3.10e-01

Pos logit contributions
 theirs+0.390
rings+0.338
 what+0.301
nam+0.297
 are+0.292
Neg logit contributions
Just-0.358
ager-0.331
age-0.324
P-0.318
ivering-0.309
Token whenever
Token ID8797
Feature activation+1.41e+00

Pos logit contributions
 theirs+0.031
rings+0.026
 what+0.023
 wow+0.023
nam+0.023
Neg logit contributions
Just-0.028
age-0.025
ager-0.025
bes-0.024
ivering-0.023
Token the
Token ID262
Feature activation+7.26e-02

Pos logit contributions
 theirs+0.105
rings+0.091
ours+0.079
endant+0.072
 ours+0.070
Neg logit contributions
Just-0.148
ager-0.139
P-0.137
 seek-0.136
fire-0.133
Token door
Token ID3420
Feature activation-6.47e-01

Pos logit contributions
 theirs+0.007
 what+0.006
rings+0.006
 are+0.005
nam+0.005
Neg logit contributions
Just-0.007
age-0.006
ager-0.006
P-0.006
bes-0.006
Token opened
Token ID4721
Feature activation+3.97e-01

Pos logit contributions
Just+0.051
age+0.047
ager+0.046
bes+0.043
P+0.043
Neg logit contributions
 theirs-0.072
rings-0.061
 what-0.057
 wow-0.056
nam-0.056
Token take
Token ID1011
Feature activation-1.79e-02

Pos logit contributions
 theirs+0.036
rings+0.029
 what+0.027
 are+0.026
 wow+0.024
Neg logit contributions
Just-0.062
ager-0.057
age-0.057
P-0.057
ivering-0.056
Token one
Token ID530
Feature activation+9.32e-02

Pos logit contributions
Just+0.002
age+0.002
ager+0.002
P+0.002
bes+0.002
Neg logit contributions
 theirs-0.001
rings-0.001
 what-0.001
 wow-0.001
 are-0.001
Token of
Token ID286
Feature activation+1.13e+00

Pos logit contributions
 theirs+0.008
rings+0.007
 what+0.006
 are+0.006
 wow+0.006
Neg logit contributions
Just-0.009
ager-0.009
age-0.009
bes-0.008
P-0.008
Token the
Token ID262
Feature activation-2.27e-02

Pos logit contributions
 theirs+0.072
rings+0.065
 wow+0.051
 are+0.048
 what+0.048
Neg logit contributions
Just-0.132
age-0.125
ager-0.125
P-0.123
bes-0.120
Token or
Token ID393
Feature activation+3.21e-02

Pos logit contributions
Just+0.002
age+0.002
ager+0.002
P+0.002
bes+0.002
Neg logit contributions
 theirs-0.002
rings-0.002
 what-0.002
 wow-0.002
 are-0.002
Tokennam
Token ID7402
Feature activation+3.94e+00

Pos logit contributions
 theirs+0.002
rings+0.002
 wow+0.001
 are+0.001
ours+0.001
Neg logit contributions
Just-0.004
age-0.004
ager-0.004
P-0.004
bes-0.003
Tokenents
Token ID658
Feature activation+2.59e+00

Pos logit contributions
 theirs+0.209
rings+0.145
 what+0.128
 wow+0.117
 are+0.111
Neg logit contributions
Just-0.540
age-0.512
ager-0.509
P-0.498
ivering-0.491
Token outside
Token ID2354
Feature activation-1.49e-01

Pos logit contributions
 theirs+0.251
rings+0.217
 wow+0.200
 what+0.197
nam+0.195
Neg logit contributions
Just-0.220
age-0.217
ager-0.204
sy-0.194
P-0.193
Token for
Token ID329
Feature activation-1.22e-01

Pos logit contributions
Just+0.014
age+0.013
ager+0.013
P+0.012
bes+0.012
Neg logit contributions
 theirs-0.014
rings-0.012
 what-0.011
 wow-0.011
 are-0.010
Token a
Token ID257
Feature activation+1.94e-01

Pos logit contributions
Just+0.015
age+0.014
ager+0.014
P+0.014
bes+0.013
Neg logit contributions
 theirs-0.008
rings-0.007
 what-0.006
 wow-0.005
 are-0.005
Token walk
Token ID2513
Feature activation+7.98e-01

Pos logit contributions
 theirs+0.018
rings+0.016
 what+0.015
 wow+0.014
nam+0.014
Neg logit contributions
Just-0.018
age-0.016
bes-0.016
ager-0.016
ivering-0.016
Token put
Token ID1234
Feature activation-1.16e+00

Pos logit contributions
Just+0.029
age+0.027
ager+0.027
bes+0.026
P+0.026
Neg logit contributions
 theirs-0.031
rings-0.027
 what-0.024
 wow-0.023
 are-0.023
Token on
Token ID319
Feature activation-1.33e-02

Pos logit contributions
P+0.124
Just+0.121
bes+0.118
ers+0.116
zer+0.116
Neg logit contributions
 theirs-0.076
rings-0.070
 wow-0.053
nam-0.052
 expect-0.050
Token their
Token ID511
Feature activation-6.06e-01

Pos logit contributions
Just+0.002
bes+0.002
P+0.002
zer+0.002
ze+0.002
Neg logit contributions
 theirs-0.001
rings-0.001
 wow-0.000
 are-0.000
 what-0.000
Token p
Token ID279
Feature activation-7.68e-01

Pos logit contributions
Just+0.067
age+0.064
ager+0.062
ivering+0.061
sy+0.059
Neg logit contributions
 theirs-0.049
rings-0.039
 what-0.037
 are-0.034
 wow-0.034
Tokenaj
Token ID1228
Feature activation-2.69e+00

Pos logit contributions
Just+0.054
ager+0.049
age+0.048
P+0.046
bes+0.045
Neg logit contributions
 theirs-0.091
rings-0.081
 what-0.076
 wow-0.072
 are-0.072
Tokenamas
Token ID17485
Feature activation-4.35e+00

Pos logit contributions
ager+0.125
Just+0.111
eh+0.107
oster+0.099
P+0.098
Neg logit contributions
 theirs-0.340
rings-0.339
 are-0.306
 what-0.300
 eyes-0.299
Token.
Token ID13
Feature activation-3.03e-03

Pos logit contributions
Just+0.430
ager+0.402
age+0.395
P+0.395
bes+0.381
Neg logit contributions
 theirs-0.397
rings-0.331
 what-0.307
 are-0.289
 wow-0.280
Token They
Token ID1119
Feature activation-3.04e-01

Pos logit contributions
Just+0.000
age+0.000
bes+0.000
amas+0.000
P+0.000
Neg logit contributions
 theirs-0.000
rings-0.000
nam-0.000
 wow-0.000
 are-0.000
Token said
Token ID531
Feature activation-2.00e-01

Pos logit contributions
Just+0.026
ager+0.024
age+0.024
P+0.023
sy+0.023
Neg logit contributions
 theirs-0.032
rings-0.027
 what-0.025
 wow-0.024
 ours-0.023
Token good
Token ID922
Feature activation-1.78e+00

Pos logit contributions
Just+0.018
ze+0.017
age+0.016
ager+0.016
bes+0.016
Neg logit contributions
 theirs-0.018
rings-0.016
nam-0.014
 ours-0.013
angles-0.013
Token night
Token ID1755
Feature activation-1.18e+00

Pos logit contributions
Just+0.154
age+0.147
ager+0.146
P+0.139
bes+0.131
Neg logit contributions
 theirs-0.182
rings-0.154
nam-0.140
 what-0.140
 wow-0.137
Token put
Token ID1234
Feature activation-1.22e+00

Pos logit contributions
Just+0.039
ager+0.038
age+0.038
sy+0.038
bes+0.037
Neg logit contributions
 theirs-0.032
rings-0.024
 wow-0.020
 what-0.020
nam-0.019
Token on
Token ID319
Feature activation-4.43e-03

Pos logit contributions
P+0.124
bes+0.116
ers+0.116
Just+0.114
sy+0.114
Neg logit contributions
 theirs-0.085
rings-0.080
 wow-0.068
 expect-0.063
nam-0.057
Token their
Token ID511
Feature activation-5.92e-01

Pos logit contributions
Just+0.001
P+0.001
bes+0.001
ager+0.001
zer+0.001
Neg logit contributions
 theirs-0.000
rings-0.000
 wow-0.000
 maybe-0.000
 what-0.000
Token p
Token ID279
Feature activation-7.32e-01

Pos logit contributions
Just+0.064
age+0.062
ager+0.061
ivering+0.058
sy+0.058
Neg logit contributions
 theirs-0.048
rings-0.040
 what-0.037
nam-0.035
 are-0.035
Tokenaj
Token ID1228
Feature activation-2.62e+00

Pos logit contributions
Just+0.046
ager+0.042
age+0.041
P+0.039
ivering+0.038
Neg logit contributions
 theirs-0.091
rings-0.082
 what-0.077
 wow-0.073
 are-0.073
Tokenamas
Token ID17485
Feature activation-4.30e+00

Pos logit contributions
ager+0.131
Just+0.114
eh+0.113
mer+0.104
P+0.103
Neg logit contributions
rings-0.323
 theirs-0.317
 are-0.299
 what-0.294
 eyes-0.288
Token and
Token ID290
Feature activation-3.67e-01

Pos logit contributions
Just+0.404
ager+0.377
P+0.374
age+0.366
bes+0.357
Neg logit contributions
 theirs-0.414
rings-0.349
 what-0.329
 are-0.314
 wow-0.299
Token get
Token ID651
Feature activation-3.57e-01

Pos logit contributions
Just+0.033
age+0.031
bes+0.031
P+0.031
ager+0.030
Neg logit contributions
 theirs-0.034
rings-0.028
 wow-0.025
 what-0.024
nam-0.023
Token into
Token ID656
Feature activation-5.37e-01

Pos logit contributions
Just+0.035
P+0.034
sy+0.032
age+0.032
ze+0.032
Neg logit contributions
 theirs-0.029
rings-0.025
 wow-0.024
 Sof-0.020
 are-0.020
Token their
Token ID511
Feature activation-5.76e-01

Pos logit contributions
Just+0.063
bes+0.061
P+0.059
ce+0.059
amas+0.057
Neg logit contributions
 theirs-0.033
rings-0.031
 wow-0.024
nam-0.021
 are-0.019
Token beds
Token ID20237
Feature activation-3.92e-02

Pos logit contributions
Just+0.044
ager+0.040
age+0.040
P+0.038
ivering+0.037
Neg logit contributions
 theirs-0.065
rings-0.057
 what-0.054
 are-0.052
 wow-0.051
Token put
Token ID1234
Feature activation-1.20e+00

Pos logit contributions
Just+0.017
age+0.016
ager+0.016
bes+0.015
P+0.015
Neg logit contributions
 theirs-0.013
rings-0.011
 what-0.009
 wow-0.009
nam-0.009
Token on
Token ID319
Feature activation+8.74e-03

Pos logit contributions
Just+0.130
age+0.123
P+0.122
ager+0.121
bes+0.119
Neg logit contributions
 theirs-0.092
rings-0.076
 what-0.065
 wow-0.065
 are-0.062
Token your
Token ID534
Feature activation-6.99e-01

Pos logit contributions
 theirs+0.001
rings+0.001
 what+0.000
 wow+0.000
 are+0.000
Neg logit contributions
Just-0.001
age-0.001
ager-0.001
bes-0.001
P-0.001
Token p
Token ID279
Feature activation-6.59e-01

Pos logit contributions
Just+0.079
ager+0.078
ivering+0.072
age+0.072
sy+0.072
Neg logit contributions
 theirs-0.051
rings-0.043
 what-0.041
 are-0.038
nam-0.038
Tokenaj
Token ID1228
Feature activation-2.64e+00

Pos logit contributions
Just+0.043
ager+0.039
age+0.038
P+0.036
ivering+0.034
Neg logit contributions
 theirs-0.082
rings-0.074
 what-0.069
 are-0.065
 wow-0.065
Tokenamas
Token ID17485
Feature activation-4.28e+00

Pos logit contributions
ager+0.148
Just+0.130
eh+0.123
P+0.123
oster+0.121
Neg logit contributions
rings-0.312
 theirs-0.310
 are-0.281
 what-0.278
 eyes-0.277
Token."
Token ID526
Feature activation-2.92e-01

Pos logit contributions
Just+0.429
ager+0.411
P+0.407
age+0.391
bes+0.390
Neg logit contributions
 theirs-0.386
rings-0.322
 what-0.302
 are-0.290
 their-0.272
Token
Token ID198
Feature activation-8.03e-01

Pos logit contributions
Just+0.033
ager+0.031
age+0.031
P+0.030
bes+0.029
Neg logit contributions
 theirs-0.023
rings-0.018
 what-0.017
 are-0.016
 wow-0.015
Token
Token ID198
Feature activation-8.19e-01

Pos logit contributions
ager+0.084
age+0.083
Just+0.082
ivering+0.081
bes+0.081
Neg logit contributions
 theirs-0.063
 what-0.052
 their-0.049
 are-0.047
 they-0.046
TokenTim
Token ID14967
Feature activation-6.40e-01

Pos logit contributions
age+0.057
amas+0.056
bes+0.055
lor+0.055
ager+0.054
Neg logit contributions
 theirs-0.092
 what-0.080
 their-0.079
 they-0.075
 are-0.075
Token and
Token ID290
Feature activation-2.14e-01

Pos logit contributions
Just+0.066
age+0.062
P+0.062
ager+0.061
ivering+0.060
Neg logit contributions
 theirs-0.052
rings-0.044
 what-0.043
 are-0.042
 Tom-0.038
Token put
Token ID1234
Feature activation-1.10e+00

Pos logit contributions
Just+0.011
age+0.011
ager+0.010
bes+0.010
P+0.010
Neg logit contributions
 theirs-0.009
rings-0.007
 what-0.006
 wow-0.006
 are-0.006
Token on
Token ID319
Feature activation+8.99e-02

Pos logit contributions
Just+0.119
P+0.115
age+0.114
bes+0.113
sy+0.112
Neg logit contributions
 theirs-0.080
rings-0.067
 wow-0.056
 what-0.054
 are-0.052
Token their
Token ID511
Feature activation-5.96e-01

Pos logit contributions
 theirs+0.005
rings+0.004
 wow+0.003
 what+0.003
nam+0.003
Neg logit contributions
Just-0.011
bes-0.011
P-0.011
age-0.011
zer-0.010
Token p
Token ID279
Feature activation-5.81e-01

Pos logit contributions
Just+0.069
ager+0.065
age+0.065
ivering+0.063
P+0.062
Neg logit contributions
 theirs-0.045
rings-0.035
 what-0.034
 are-0.033
 their-0.032
Tokenaj
Token ID1228
Feature activation-2.59e+00

Pos logit contributions
Just+0.041
ager+0.037
age+0.036
P+0.035
ivering+0.034
Neg logit contributions
 theirs-0.069
rings-0.062
 what-0.057
 are-0.054
 wow-0.054
Tokenamas
Token ID17485
Feature activation-4.28e+00

Pos logit contributions
ager+0.135
Just+0.120
eh+0.111
oster+0.107
P+0.104
Neg logit contributions
 theirs-0.314
rings-0.310
 are-0.283
 what-0.280
 eyes-0.277
Token first
Token ID717
Feature activation-1.23e+00

Pos logit contributions
Just+0.442
ager+0.417
P+0.407
age+0.405
bes+0.396
Neg logit contributions
 theirs-0.374
rings-0.306
 what-0.289
 are-0.270
 their-0.259
Token.
Token ID13
Feature activation-5.35e-02

Pos logit contributions
Just+0.118
ager+0.110
age+0.109
P+0.106
bes+0.103
Neg logit contributions
 theirs-0.115
rings-0.097
 what-0.090
 are-0.085
 wow-0.084
Token They
Token ID1119
Feature activation-5.24e-01

Pos logit contributions
Just+0.006
age+0.006
ager+0.006
P+0.006
bes+0.006
Neg logit contributions
 theirs-0.004
rings-0.003
 what-0.003
 wow-0.002
nam-0.002
Token do
Token ID466
Feature activation+3.90e-01

Pos logit contributions
Just+0.048
sy+0.048
ager+0.047
age+0.047
ce+0.045
Neg logit contributions
 theirs-0.048
rings-0.037
 wow-0.032
nam-0.031
 what-0.030
Token what
Token ID644
Feature activation-8.69e-01

Pos logit contributions
 theirs+0.038
rings+0.033
 what+0.029
 wow+0.028
nam+0.028
Neg logit contributions
Just-0.036
age-0.033
ager-0.033
bes-0.032
P-0.032
Token put
Token ID1234
Feature activation-1.14e+00

Pos logit contributions
Just+0.024
bes+0.022
age+0.022
ager+0.021
ze+0.021
Neg logit contributions
 theirs-0.022
rings-0.018
 what-0.015
 wow-0.015
ours-0.015
Token on
Token ID319
Feature activation+7.40e-02

Pos logit contributions
Just+0.121
P+0.120
bes+0.119
age+0.118
sy+0.117
Neg logit contributions
 theirs-0.078
rings-0.067
 wow-0.055
 what-0.051
nam-0.050
Token their
Token ID511
Feature activation-5.58e-01

Pos logit contributions
 theirs+0.004
rings+0.003
 wow+0.002
 what+0.002
nam+0.002
Neg logit contributions
Just-0.009
bes-0.009
ze-0.009
P-0.009
ce-0.009
Token p
Token ID279
Feature activation-6.66e-01

Pos logit contributions
Just+0.062
age+0.058
ager+0.057
ivering+0.056
P+0.054
Neg logit contributions
 theirs-0.045
rings-0.036
 what-0.034
 are-0.032
 their-0.032
Tokenaj
Token ID1228
Feature activation-2.56e+00

Pos logit contributions
Just+0.042
ager+0.038
age+0.037
P+0.036
ivering+0.034
Neg logit contributions
 theirs-0.084
rings-0.075
 what-0.070
 wow-0.067
 are-0.067
Tokenamas
Token ID17485
Feature activation-4.26e+00

Pos logit contributions
ager+0.116
Just+0.107
eh+0.104
P+0.095
oster+0.090
Neg logit contributions
 theirs-0.324
rings-0.317
 are-0.294
 what-0.288
 their-0.284
Token.
Token ID13
Feature activation-1.42e-01

Pos logit contributions
Just+0.438
ager+0.413
P+0.409
age+0.399
bes+0.392
Neg logit contributions
 theirs-0.373
rings-0.307
 what-0.289
 are-0.271
 their-0.260
Token They
Token ID1119
Feature activation-4.13e-01

Pos logit contributions
Just+0.016
age+0.015
ager+0.015
bes+0.014
P+0.014
Neg logit contributions
 theirs-0.011
rings-0.009
 what-0.008
 wow-0.007
nam-0.007
Token hug
Token ID16225
Feature activation+1.43e-01

Pos logit contributions
Just+0.040
age+0.039
ager+0.038
sy+0.038
bes+0.037
Neg logit contributions
 theirs-0.037
rings-0.029
nam-0.025
 what-0.024
 wow-0.024
Token their
Token ID511
Feature activation-5.78e-01

Pos logit contributions
 theirs+0.009
rings+0.007
 wow+0.005
 what+0.005
nam+0.005
Neg logit contributions
Just-0.018
age-0.017
ager-0.017
bes-0.016
P-0.016
Token mom
Token ID1995
Feature activation-3.24e-01

Pos logit contributions
Just+0.064
age+0.060
ager+0.059
P+0.058
ivering+0.057
Neg logit contributions
 theirs-0.047
rings-0.039
 what-0.036
 are-0.034
 wow-0.034
Token put
Token ID1234
Feature activation-1.12e+00

Pos logit contributions
bes+0.024
Just+0.023
age+0.023
ager+0.023
P+0.022
Neg logit contributions
 theirs-0.021
rings-0.019
ours-0.015
 wow-0.015
 what-0.015
Token on
Token ID319
Feature activation+8.52e-02

Pos logit contributions
P+0.116
ers+0.112
Just+0.108
bes+0.108
co+0.107
Neg logit contributions
 theirs-0.071
rings-0.068
 wow-0.056
 expect-0.052
 are-0.050
Token their
Token ID511
Feature activation-5.66e-01

Pos logit contributions
 theirs+0.005
rings+0.005
 maybe+0.004
 wow+0.004
 are+0.003
Neg logit contributions
Just-0.010
bes-0.009
P-0.009
zer-0.009
ze-0.009
Token p
Token ID279
Feature activation-6.88e-01

Pos logit contributions
Just+0.068
age+0.064
ager+0.063
ivering+0.063
P+0.061
Neg logit contributions
 theirs-0.042
rings-0.031
 what-0.029
 are-0.027
 their-0.027
Tokenaj
Token ID1228
Feature activation-2.53e+00

Pos logit contributions
Just+0.042
age+0.038
ager+0.037
P+0.035
bes+0.034
Neg logit contributions
 theirs-0.088
rings-0.078
 what-0.074
 wow-0.071
 are-0.071
Tokenamas
Token ID17485
Feature activation-4.23e+00

Pos logit contributions
ager+0.118
Just+0.116
eh+0.106
age+0.094
P+0.093
Neg logit contributions
 theirs-0.324
rings-0.306
 are-0.289
 what-0.282
 their-0.279
Token.
Token ID13
Feature activation-1.07e-03

Pos logit contributions
Just+0.450
ager+0.423
P+0.420
age+0.410
bes+0.403
Neg logit contributions
 theirs-0.358
rings-0.291
 what-0.273
 are-0.255
 their-0.248
Token They
Token ID1119
Feature activation-3.77e-01

Pos logit contributions
Just+0.000
age+0.000
P+0.000
bes+0.000
ager+0.000
Neg logit contributions
 theirs-0.000
rings-0.000
 what-0.000
 wow-0.000
nam-0.000
Token hug
Token ID16225
Feature activation+1.69e-01

Pos logit contributions
ager+0.036
age+0.036
sy+0.036
Just+0.036
oster+0.035
Neg logit contributions
 theirs-0.031
rings-0.026
nam-0.021
 wow-0.020
ours-0.020
Token their
Token ID511
Feature activation-5.75e-01

Pos logit contributions
 theirs+0.012
rings+0.009
 what+0.008
 wow+0.008
 are+0.007
Neg logit contributions
Just-0.020
age-0.019
ager-0.019
P-0.019
bes-0.018
Token mom
Token ID1995
Feature activation-3.02e-01

Pos logit contributions
Just+0.066
age+0.063
ager+0.061
ivering+0.060
P+0.060
Neg logit contributions
 theirs-0.045
rings-0.035
 what-0.034
 are-0.031
 their-0.031
Token them
Token ID606
Feature activation-5.99e-01

Pos logit contributions
 theirs+0.005
rings+0.004
 wow+0.004
nam+0.003
 what+0.003
Neg logit contributions
Just-0.010
age-0.010
P-0.010
ager-0.009
sy-0.009
Token towels
Token ID38494
Feature activation-1.78e+00

Pos logit contributions
Just+0.065
ager+0.061
age+0.061
P+0.061
sy+0.058
Neg logit contributions
 theirs-0.045
rings-0.039
 wow-0.033
 what-0.032
nam-0.031
Token and
Token ID290
Feature activation-3.56e-01

Pos logit contributions
Just+0.141
age+0.129
ager+0.129
P+0.124
bes+0.121
Neg logit contributions
 theirs-0.195
rings-0.169
 what-0.158
 are-0.151
 wow-0.151
Token p
Token ID279
Feature activation-7.08e-01

Pos logit contributions
Just+0.031
bes+0.029
age+0.028
P+0.028
ager+0.028
Neg logit contributions
 theirs-0.034
rings-0.030
 wow-0.026
 what-0.025
nam-0.024
Tokenaj
Token ID1228
Feature activation-2.58e+00

Pos logit contributions
Just+0.073
bes+0.072
co+0.071
amas+0.070
ivering+0.069
Neg logit contributions
 theirs-0.050
rings-0.041
 wow-0.040
nam-0.039
 maybe-0.037
Tokenamas
Token ID17485
Feature activation-4.22e+00

Pos logit contributions
eh+0.116
ager+0.112
Just+0.112
P+0.107
age+0.098
Neg logit contributions
 theirs-0.347
rings-0.321
 are-0.318
 what-0.308
 their-0.299
Token.
Token ID13
Feature activation-1.12e-01

Pos logit contributions
Just+0.393
ager+0.364
age+0.360
P+0.355
bes+0.343
Neg logit contributions
 theirs-0.411
rings-0.346
 what-0.324
 are-0.308
 wow-0.302
Token They
Token ID1119
Feature activation-2.38e-01

Pos logit contributions
Just+0.012
age+0.011
P+0.011
ager+0.011
bes+0.011
Neg logit contributions
 theirs-0.009
rings-0.008
 what-0.007
 wow-0.007
nam-0.007
Token give
Token ID1577
Feature activation+4.85e-02

Pos logit contributions
ager+0.024
Just+0.023
age+0.023
sy+0.023
bes+0.023
Neg logit contributions
 theirs-0.019
rings-0.016
nam-0.013
 wow-0.012
 what-0.012
Token them
Token ID606
Feature activation-6.14e-01

Pos logit contributions
 theirs+0.003
rings+0.002
 wow+0.002
 what+0.002
nam+0.002
Neg logit contributions
Just-0.006
age-0.006
P-0.005
ager-0.005
sy-0.005
Token a
Token ID257
Feature activation-2.97e-01

Pos logit contributions
Just+0.065
P+0.061
age+0.061
ager+0.061
sy+0.059
Neg logit contributions
 theirs-0.048
rings-0.041
 wow-0.035
 what-0.034
nam-0.034
Token puts
Token ID7584
Feature activation-2.97e-01

Pos logit contributions
 theirs+0.007
rings+0.006
 what+0.005
 are+0.005
 wow+0.005
Neg logit contributions
Just-0.010
age-0.010
ager-0.010
P-0.009
bes-0.009
Token on
Token ID319
Feature activation+4.14e-02

Pos logit contributions
P+0.024
Just+0.024
age+0.022
bes+0.021
ager+0.021
Neg logit contributions
 theirs-0.030
rings-0.026
 wow-0.024
 what-0.023
 are-0.023
Token her
Token ID607
Feature activation-2.43e-01

Pos logit contributions
 theirs+0.003
rings+0.002
 wow+0.002
 what+0.002
 are+0.002
Neg logit contributions
Just-0.005
P-0.005
bes-0.005
age-0.004
ager-0.004
Token p
Token ID279
Feature activation-6.90e-01

Pos logit contributions
Just+0.025
ager+0.024
age+0.024
ivering+0.023
sy+0.023
Neg logit contributions
 theirs-0.020
rings-0.017
 what-0.016
 are-0.015
nam-0.015
Tokenaj
Token ID1228
Feature activation-2.54e+00

Pos logit contributions
Just+0.043
ager+0.039
age+0.038
P+0.036
bes+0.035
Neg logit contributions
 theirs-0.087
rings-0.078
 what-0.073
 wow-0.070
 are-0.070
Tokenamas
Token ID17485
Feature activation-4.22e+00

Pos logit contributions
ager+0.125
mer+0.108
eh+0.108
oster+0.104
fire+0.100
Neg logit contributions
rings-0.313
 theirs-0.306
 what-0.285
 are-0.284
 eyes-0.277
Token.
Token ID13
Feature activation+1.20e-01

Pos logit contributions
Just+0.381
ager+0.360
P+0.349
age+0.348
bes+0.338
Neg logit contributions
 theirs-0.414
rings-0.354
 what-0.334
 are-0.316
 wow-0.306
Token They
Token ID1119
Feature activation-1.48e-01

Pos logit contributions
 theirs+0.010
rings+0.008
 what+0.007
 wow+0.007
nam+0.007
Neg logit contributions
Just-0.012
age-0.011
amas-0.011
bes-0.011
P-0.011
Token are
Token ID389
Feature activation+1.67e+00

Pos logit contributions
age+0.013
Just+0.012
sy+0.012
P+0.012
bes+0.012
Neg logit contributions
 theirs-0.015
rings-0.011
 wow-0.010
 what-0.010
nam-0.010
Token tight
Token ID5381
Feature activation+3.86e-02

Pos logit contributions
 theirs+0.147
rings+0.124
 what+0.112
 wow+0.107
 are+0.106
Neg logit contributions
Just-0.168
age-0.157
ager-0.155
P-0.152
bes-0.150
Token and
Token ID290
Feature activation-2.44e-01

Pos logit contributions
 theirs+0.004
rings+0.003
 what+0.003
 are+0.003
 their+0.003
Neg logit contributions
Just-0.004
ager-0.004
P-0.004
age-0.003
oster-0.003
Token put
Token ID1234
Feature activation-1.08e+00

Pos logit contributions
 theirs+0.001
rings+0.001
 what+0.001
 wow+0.001
 are+0.001
Neg logit contributions
Just-0.001
age-0.001
ager-0.001
bes-0.001
P-0.001
Token on
Token ID319
Feature activation+1.68e-01

Pos logit contributions
Just+0.128
P+0.123
age+0.122
ager+0.119
bes+0.118
Neg logit contributions
 theirs-0.069
rings-0.054
 wow-0.044
 what-0.043
nam-0.041
Token your
Token ID534
Feature activation-5.33e-01

Pos logit contributions
 theirs+0.014
rings+0.011
 what+0.010
 wow+0.009
 are+0.009
Neg logit contributions
Just-0.018
age-0.017
ager-0.016
P-0.016
bes-0.016
Token p
Token ID279
Feature activation-5.87e-01

Pos logit contributions
Just+0.057
ager+0.054
age+0.053
P+0.051
sy+0.050
Neg logit contributions
 theirs-0.045
rings-0.037
 what-0.035
 are-0.033
nam-0.032
Tokenaj
Token ID1228
Feature activation-2.49e+00

Pos logit contributions
Just+0.036
ager+0.032
age+0.032
P+0.030
bes+0.029
Neg logit contributions
 theirs-0.075
rings-0.067
 what-0.063
 wow-0.061
 are-0.061
Tokenamas
Token ID17485
Feature activation-4.21e+00

Pos logit contributions
ager+0.138
Just+0.125
eh+0.122
oster+0.115
P+0.114
Neg logit contributions
rings-0.294
 theirs-0.285
 are-0.265
 eyes-0.254
 look-0.253
Token."
Token ID526
Feature activation-1.36e-01

Pos logit contributions
Just+0.429
ager+0.408
P+0.405
bes+0.391
age+0.390
Neg logit contributions
 theirs-0.373
rings-0.304
 what-0.289
 are-0.278
 their-0.262
Token
Token ID198
Feature activation-4.32e-01

Pos logit contributions
Just+0.016
ager+0.015
age+0.015
P+0.015
bes+0.014
Neg logit contributions
 theirs-0.010
rings-0.008
 what-0.007
 are-0.006
 wow-0.006
Token
Token ID198
Feature activation-4.76e-01

Pos logit contributions
Just+0.041
ager+0.039
age+0.039
P+0.037
ivering+0.037
Neg logit contributions
 theirs-0.040
rings-0.033
 what-0.032
 are-0.030
 wow-0.029
TokenL
Token ID43
Feature activation+1.21e+00

Pos logit contributions
age+0.038
ager+0.036
lor+0.035
amas+0.034
unk+0.034
Neg logit contributions
 theirs-0.047
 what-0.043
 are-0.041
 their-0.041
nam-0.040
Tokenily
Token ID813
Feature activation+2.37e-01

Pos logit contributions
 theirs+0.113
rings+0.089
 what+0.088
 are+0.083
 wow+0.078
Neg logit contributions
Just-0.118
age-0.112
ager-0.108
P-0.105
bes-0.105
Token They
Token ID1119
Feature activation-1.20e-01

Pos logit contributions
 theirs+0.005
rings+0.004
 what+0.004
 wow+0.004
nam+0.004
Neg logit contributions
Just-0.006
age-0.005
ager-0.005
P-0.005
bes-0.005
Token were
Token ID547
Feature activation+9.19e-01

Pos logit contributions
Just+0.011
age+0.011
ager+0.011
sy+0.011
co+0.010
Neg logit contributions
 theirs-0.011
rings-0.009
 wow-0.008
 ours-0.008
ours-0.008
Token wearing
Token ID5762
Feature activation-7.83e-01

Pos logit contributions
 theirs+0.084
rings+0.076
 wow+0.069
 are+0.066
 what+0.066
Neg logit contributions
Just-0.080
age-0.074
bes-0.072
sy-0.072
ivering-0.072
Token p
Token ID279
Feature activation-6.30e-01

Pos logit contributions
bes+0.078
Just+0.073
ze+0.072
age+0.071
P+0.070
Neg logit contributions
 theirs-0.058
rings-0.053
ours-0.043
 wow-0.043
 maybe-0.041
Tokenaj
Token ID1228
Feature activation-2.51e+00

Pos logit contributions
Just+0.041
bes+0.036
ager+0.035
age+0.035
ivering+0.035
Neg logit contributions
 theirs-0.079
rings-0.068
 what-0.065
 wow-0.065
 are-0.064
Tokenamas
Token ID17485
Feature activation-4.19e+00

Pos logit contributions
ager+0.106
Just+0.097
eh+0.093
oster+0.092
age+0.092
Neg logit contributions
 theirs-0.332
rings-0.320
 are-0.307
 what-0.302
 wow-0.293
Token.
Token ID13
Feature activation+1.67e-02

Pos logit contributions
Just+0.404
ager+0.376
P+0.370
age+0.369
bes+0.352
Neg logit contributions
 theirs-0.395
rings-0.331
 what-0.312
 are-0.296
 wow-0.286
Token And
Token ID843
Feature activation+1.69e-02

Pos logit contributions
 theirs+0.002
rings+0.001
 what+0.001
 wow+0.001
nam+0.001
Neg logit contributions
Just-0.002
age-0.001
ager-0.001
P-0.001
bes-0.001
Token they
Token ID484
Feature activation-2.69e-01

Pos logit contributions
 theirs+0.001
rings+0.001
 wow+0.001
nam+0.001
ours+0.001
Neg logit contributions
Just-0.002
bes-0.002
ager-0.002
age-0.002
rd-0.002
Token were
Token ID547
Feature activation+8.89e-01

Pos logit contributions
Just+0.026
ager+0.025
age+0.025
sy+0.024
P+0.024
Neg logit contributions
 theirs-0.024
rings-0.020
 what-0.017
 wow-0.017
nam-0.016
Token not
Token ID407
Feature activation-1.20e+00

Pos logit contributions
 theirs+0.080
rings+0.067
 what+0.061
 wow+0.058
 are+0.058
Neg logit contributions
Just-0.089
age-0.083
ager-0.083
P-0.080
bes-0.079
Token put
Token ID1234
Feature activation-1.05e+00

Pos logit contributions
Just+0.012
age+0.012
bes+0.011
ager+0.011
P+0.011
Neg logit contributions
 theirs-0.013
rings-0.011
 what-0.010
 wow-0.010
 are-0.010
Token on
Token ID319
Feature activation+2.05e-01

Pos logit contributions
bes+0.112
age+0.111
Just+0.110
ers+0.110
P+0.109
Neg logit contributions
 theirs-0.065
rings-0.057
 wow-0.046
nam-0.043
 expect-0.041
Token their
Token ID511
Feature activation-3.48e-01

Pos logit contributions
 theirs+0.010
rings+0.008
 wow+0.005
 what+0.005
nam+0.005
Neg logit contributions
Just-0.027
bes-0.027
age-0.026
ze-0.026
zer-0.026
Token p
Token ID279
Feature activation-5.49e-01

Pos logit contributions
Just+0.036
ager+0.034
age+0.033
P+0.032
ivering+0.032
Neg logit contributions
 theirs-0.031
rings-0.025
 what-0.024
 are-0.023
 wow-0.022
Tokenaj
Token ID1228
Feature activation-2.58e+00

Pos logit contributions
Just+0.038
ager+0.035
age+0.033
P+0.033
ivering+0.031
Neg logit contributions
 theirs-0.066
rings-0.059
 what-0.055
 wow-0.052
 are-0.052
Tokenamas
Token ID17485
Feature activation-4.18e+00

Pos logit contributions
ager+0.134
Just+0.122
eh+0.114
P+0.113
oster+0.102
Neg logit contributions
 theirs-0.316
rings-0.314
 are-0.288
 what-0.279
 their-0.273
Token.
Token ID13
Feature activation+7.36e-02

Pos logit contributions
Just+0.414
ager+0.389
P+0.381
age+0.375
bes+0.366
Neg logit contributions
 theirs-0.382
rings-0.320
 what-0.299
 are-0.282
 their-0.269
Token They
Token ID1119
Feature activation-1.83e-01

Pos logit contributions
 theirs+0.006
rings+0.005
 wow+0.004
 what+0.004
nam+0.004
Neg logit contributions
Just-0.008
age-0.007
bes-0.007
P-0.007
amas-0.007
Token climbed
Token ID19952
Feature activation+4.69e-01

Pos logit contributions
Just+0.016
age+0.015
ager+0.015
sy+0.015
P+0.015
Neg logit contributions
 theirs-0.019
rings-0.016
 what-0.014
 wow-0.014
 ours-0.013
Token into
Token ID656
Feature activation-4.16e-01

Pos logit contributions
 theirs+0.047
rings+0.040
 what+0.037
 wow+0.035
 are+0.035
Neg logit contributions
Just-0.042
age-0.039
ager-0.039
P-0.037
bes-0.037
Token their
Token ID511
Feature activation-3.76e-01

Pos logit contributions
bes+0.044
Just+0.043
ce+0.041
Lu+0.041
co+0.040
Neg logit contributions
 theirs-0.029
rings-0.027
 wow-0.022
ours-0.018
nam-0.018
Token put
Token ID1234
Feature activation-1.09e+00

Pos logit contributions
bes+0.021
Just+0.021
age+0.020
ager+0.019
P+0.019
Neg logit contributions
 theirs-0.022
rings-0.018
 what-0.016
ours-0.016
 wow-0.016
Token on
Token ID319
Feature activation+1.10e-01

Pos logit contributions
P+0.111
ers+0.108
bes+0.107
sy+0.103
age+0.101
Neg logit contributions
 theirs-0.068
rings-0.065
 wow-0.057
 expect-0.053
bars-0.051
Token their
Token ID511
Feature activation-4.78e-01

Pos logit contributions
 theirs+0.006
rings+0.006
 expect+0.004
 wow+0.004
 maybe+0.004
Neg logit contributions
bes-0.013
P-0.012
Just-0.012
zer-0.012
ze-0.012
Token p
Token ID279
Feature activation-5.51e-01

Pos logit contributions
Just+0.053
ager+0.050
age+0.050
P+0.048
ivering+0.048
Neg logit contributions
 theirs-0.038
rings-0.031
 what-0.028
 are-0.026
 wow-0.026
Tokenaj
Token ID1228
Feature activation-2.60e+00

Pos logit contributions
Just+0.038
age+0.035
ager+0.034
bes+0.033
P+0.033
Neg logit contributions
 theirs-0.066
rings-0.057
 what-0.055
 wow-0.053
 are-0.052
Tokenamas
Token ID17485
Feature activation-4.17e+00

Pos logit contributions
ager+0.121
Just+0.112
oster+0.093
eh+0.092
P+0.088
Neg logit contributions
rings-0.337
 theirs-0.336
 are-0.303
 look-0.294
 what-0.293
Token.
Token ID13
Feature activation-1.50e-01

Pos logit contributions
Just+0.435
ager+0.409
P+0.403
age+0.397
bes+0.390
Neg logit contributions
 theirs-0.361
rings-0.300
 what-0.277
 are-0.261
 their-0.251
Token They
Token ID1119
Feature activation-4.01e-01

Pos logit contributions
Just+0.018
age+0.017
ager+0.017
P+0.016
bes+0.016
Neg logit contributions
 theirs-0.010
rings-0.008
 what-0.007
 wow-0.007
nam-0.007
Token each
Token ID1123
Feature activation-5.52e-01

Pos logit contributions
Just+0.037
sy+0.036
ager+0.036
age+0.035
bes+0.034
Neg logit contributions
 theirs-0.038
rings-0.029
 wow-0.025
 what-0.024
nam-0.024
Token pick
Token ID2298
Feature activation-9.30e-02

Pos logit contributions
Just+0.059
age+0.055
ager+0.055
P+0.053
bes+0.052
Neg logit contributions
 theirs-0.046
rings-0.038
 what-0.034
 wow-0.033
nam-0.031
Token a
Token ID257
Feature activation-2.31e-01

Pos logit contributions
P+0.007
Just+0.007
age+0.007
sy+0.007
ager+0.007
Neg logit contributions
 theirs-0.009
rings-0.008
nam-0.007
 wow-0.007
 what-0.007
Token put
Token ID1234
Feature activation-1.12e+00

Pos logit contributions
Just+0.015
age+0.014
ager+0.014
P+0.014
bes+0.014
Neg logit contributions
 theirs-0.015
rings-0.012
 what-0.011
 wow-0.011
 are-0.011
Token on
Token ID319
Feature activation+1.05e-01

Pos logit contributions
Just+0.131
P+0.127
age+0.125
bes+0.123
sy+0.119
Neg logit contributions
 theirs-0.073
rings-0.058
 wow-0.048
 what-0.046
 are-0.045
Token her
Token ID607
Feature activation-3.07e-01

Pos logit contributions
 theirs+0.007
rings+0.005
 what+0.004
 wow+0.004
 are+0.004
Neg logit contributions
Just-0.013
bes-0.012
P-0.012
age-0.012
ager-0.012
Token p
Token ID279
Feature activation-5.65e-01

Pos logit contributions
Just+0.034
ager+0.032
age+0.031
ivering+0.030
sy+0.030
Neg logit contributions
 theirs-0.024
rings-0.020
 what-0.019
 are-0.018
nam-0.018
Tokenaj
Token ID1228
Feature activation-2.55e+00

Pos logit contributions
Just+0.035
ager+0.032
age+0.031
P+0.030
bes+0.028
Neg logit contributions
 theirs-0.072
rings-0.064
 what-0.060
 wow-0.058
 are-0.057
Tokenamas
Token ID17485
Feature activation-4.17e+00

Pos logit contributions
ager+0.132
Just+0.117
eh+0.107
P+0.103
oster+0.100
Neg logit contributions
rings-0.311
 theirs-0.306
 are-0.277
 what-0.269
 eyes-0.269
Token.
Token ID13
Feature activation-2.18e-01

Pos logit contributions
Just+0.429
ager+0.408
P+0.396
age+0.393
bes+0.386
Neg logit contributions
 theirs-0.359
rings-0.302
 what-0.280
 are-0.260
 their-0.247
Token Mom
Token ID11254
Feature activation-1.85e-01

Pos logit contributions
Just+0.023
age+0.021
P+0.021
amas+0.021
bes+0.020
Neg logit contributions
 theirs-0.018
rings-0.015
 wow-0.013
 what-0.013
nam-0.013
Tokenmy
Token ID1820
Feature activation-2.49e-01

Pos logit contributions
Just+0.019
ager+0.017
age+0.017
P+0.017
bes+0.017
Neg logit contributions
 theirs-0.016
rings-0.014
 what-0.013
 are-0.012
 wow-0.012
Token read
Token ID1100
Feature activation+2.87e-01

Pos logit contributions
Just+0.026
P+0.025
ager+0.024
age+0.024
ivering+0.024
Neg logit contributions
 theirs-0.020
rings-0.017
 what-0.016
 are-0.015
 wow-0.014
Token her
Token ID607
Feature activation-3.20e-01

Pos logit contributions
 theirs+0.019
rings+0.016
 wow+0.013
nam+0.012
 what+0.012
Neg logit contributions
Just-0.033
age-0.031
P-0.031
bes-0.031
co-0.030
Token put
Token ID1234
Feature activation-1.10e+00

Pos logit contributions
Just+0.015
age+0.014
ager+0.013
bes+0.013
P+0.013
Neg logit contributions
 theirs-0.015
rings-0.013
 what-0.012
 wow-0.011
 are-0.011
Token on
Token ID319
Feature activation+1.46e-01

Pos logit contributions
Just+0.115
age+0.112
P+0.112
bes+0.109
sy+0.107
Neg logit contributions
 theirs-0.082
rings-0.069
 wow-0.059
 what-0.055
nam-0.054
Token their
Token ID511
Feature activation-4.78e-01

Pos logit contributions
 theirs+0.008
rings+0.006
 wow+0.004
 what+0.004
nam+0.004
Neg logit contributions
Just-0.019
bes-0.019
age-0.018
P-0.018
ze-0.018
Token p
Token ID279
Feature activation-6.30e-01

Pos logit contributions
Just+0.054
ager+0.052
age+0.051
ivering+0.049
P+0.049
Neg logit contributions
 theirs-0.036
rings-0.029
 what-0.028
 are-0.027
 their-0.026
Tokenaj
Token ID1228
Feature activation-2.51e+00

Pos logit contributions
Just+0.044
ager+0.042
age+0.039
P+0.039
sy+0.037
Neg logit contributions
 theirs-0.073
rings-0.066
 what-0.061
ours-0.058
 are-0.057
Tokenamas
Token ID17485
Feature activation-4.17e+00

Pos logit contributions
ager+0.137
Just+0.116
mer+0.113
eh+0.112
P+0.111
Neg logit contributions
rings-0.297
 theirs-0.293
 are-0.270
 what-0.267
 eyes-0.263
Token.
Token ID13
Feature activation+2.08e-04

Pos logit contributions
Just+0.425
ager+0.401
P+0.396
age+0.387
ivering+0.378
Neg logit contributions
 theirs-0.368
rings-0.306
 what-0.286
 are-0.269
 their-0.257
Token Their
Token ID5334
Feature activation-3.23e-01

Pos logit contributions
 theirs+0.000
rings+0.000
nam+0.000
 wow+0.000
 are+0.000
Neg logit contributions
Just-0.000
age-0.000
bes-0.000
amas-0.000
P-0.000
Token mom
Token ID1995
Feature activation+3.71e-02

Pos logit contributions
Just+0.038
ager+0.036
age+0.036
P+0.035
ivering+0.034
Neg logit contributions
 theirs-0.023
rings-0.019
 what-0.017
 are-0.016
 wow-0.015
Token tucked
Token ID29779
Feature activation+2.27e-01

Pos logit contributions
 theirs+0.003
rings+0.002
 what+0.002
 are+0.002
 wow+0.002
Neg logit contributions
Just-0.004
P-0.004
age-0.004
ager-0.004
ivering-0.004
Token them
Token ID606
Feature activation-5.51e-01

Pos logit contributions
 theirs+0.013
rings+0.011
 wow+0.009
 are+0.008
 what+0.008
Neg logit contributions
Just-0.028
P-0.027
age-0.026
ager-0.026
bes-0.026
Token put
Token ID1234
Feature activation-1.13e+00

Pos logit contributions
Just+0.024
bes+0.023
age+0.023
ager+0.022
ze+0.022
Neg logit contributions
 theirs-0.021
rings-0.018
 what-0.015
 wow-0.015
ours-0.015
Token on
Token ID319
Feature activation+1.03e-01

Pos logit contributions
Just+0.120
P+0.120
bes+0.119
age+0.118
co+0.118
Neg logit contributions
 theirs-0.073
rings-0.063
 wow-0.053
 what-0.049
nam-0.046
Token their
Token ID511
Feature activation-3.77e-01

Pos logit contributions
 theirs+0.006
rings+0.005
 wow+0.003
 maybe+0.003
 what+0.003
Neg logit contributions
Just-0.013
bes-0.013
P-0.012
co-0.012
ze-0.012
Token p
Token ID279
Feature activation-6.10e-01

Pos logit contributions
Just+0.040
age+0.037
ager+0.037
P+0.036
ivering+0.035
Neg logit contributions
 theirs-0.032
rings-0.026
 what-0.024
 are-0.023
 wow-0.023
Tokenaj
Token ID1228
Feature activation-2.51e+00

Pos logit contributions
Just+0.036
age+0.032
ager+0.032
P+0.030
bes+0.029
Neg logit contributions
 theirs-0.079
rings-0.071
 what-0.067
 wow-0.064
 are-0.064
Tokenamas
Token ID17485
Feature activation-4.16e+00

Pos logit contributions
ager+0.118
Just+0.109
eh+0.105
P+0.098
oster+0.088
Neg logit contributions
 theirs-0.326
rings-0.318
 are-0.298
 what-0.289
 their-0.285
Token.
Token ID13
Feature activation+9.05e-02

Pos logit contributions
Just+0.423
ager+0.399
P+0.391
age+0.386
bes+0.375
Neg logit contributions
 theirs-0.371
rings-0.306
 what-0.287
 are-0.269
 their-0.260
Token They
Token ID1119
Feature activation-1.61e-01

Pos logit contributions
 theirs+0.007
rings+0.007
nam+0.006
 what+0.006
 wow+0.005
Neg logit contributions
Just-0.010
age-0.009
bes-0.008
P-0.008
ager-0.008
Token get
Token ID651
Feature activation-2.78e-01

Pos logit contributions
age+0.015
Just+0.015
sy+0.015
ager+0.015
bes+0.014
Neg logit contributions
 theirs-0.014
rings-0.011
 wow-0.010
nam-0.010
 what-0.009
Token into
Token ID656
Feature activation-4.53e-01

Pos logit contributions
Just+0.024
P+0.022
age+0.022
sy+0.022
ze+0.021
Neg logit contributions
 theirs-0.026
rings-0.023
 wow-0.022
 what-0.019
 Sof-0.019
Token their
Token ID511
Feature activation-4.06e-01

Pos logit contributions
Just+0.040
bes+0.040
amas+0.037
ce+0.037
Now+0.037
Neg logit contributions
 theirs-0.039
rings-0.038
 wow-0.033
nam-0.028
angles-0.027
Token put
Token ID1234
Feature activation-1.04e+00

Pos logit contributions
Just+0.008
age+0.008
ager+0.008
P+0.007
bes+0.007
Neg logit contributions
 theirs-0.007
rings-0.005
 what-0.005
 wow-0.005
 are-0.005
Token on
Token ID319
Feature activation+1.32e-01

Pos logit contributions
Just+0.135
P+0.127
ager+0.127
age+0.127
bes+0.125
Neg logit contributions
 theirs-0.060
rings-0.045
 what-0.035
 wow-0.034
nam-0.032
Token your
Token ID534
Feature activation-5.04e-01

Pos logit contributions
 theirs+0.008
rings+0.007
 what+0.006
 wow+0.005
 are+0.005
Neg logit contributions
Just-0.017
age-0.016
ager-0.016
P-0.015
bes-0.015
Token p
Token ID279
Feature activation-5.97e-01

Pos logit contributions
Just+0.057
age+0.057
ager+0.057
lor+0.052
ivering+0.052
Neg logit contributions
 theirs-0.037
 their-0.029
 what-0.029
 are-0.028
 look-0.027
Tokenaj
Token ID1228
Feature activation-2.44e+00

Pos logit contributions
Just+0.043
ager+0.041
age+0.039
P+0.037
ivering+0.035
Neg logit contributions
 theirs-0.069
rings-0.062
 what-0.057
ours-0.056
 are-0.054
Tokenamas
Token ID17485
Feature activation-4.14e+00

Pos logit contributions
ager+0.143
Just+0.127
eh+0.127
age+0.113
oster+0.107
Neg logit contributions
 theirs-0.280
rings-0.267
 are-0.255
ours-0.251
 eyes-0.250
Token.
Token ID13
Feature activation+2.45e-01

Pos logit contributions
Just+0.451
ager+0.433
P+0.419
bes+0.411
age+0.411
Neg logit contributions
 theirs-0.339
rings-0.270
 what-0.262
 are-0.250
 their-0.233
Token OK
Token ID7477
Feature activation-1.25e+00

Pos logit contributions
 theirs+0.020
rings+0.017
 what+0.015
 wow+0.014
 are+0.014
Neg logit contributions
Just-0.026
ager-0.025
age-0.024
P-0.024
bes-0.023
Token?"
Token ID1701
Feature activation+1.82e-01

Pos logit contributions
Just+0.138
ager+0.132
age+0.128
bes+0.128
P+0.127
Neg logit contributions
 theirs-0.099
 what-0.082
rings-0.082
 are-0.074
 wow-0.068
Token
Token ID198
Feature activation-4.61e-01

Pos logit contributions
 theirs+0.019
rings+0.017
 what+0.015
 wow+0.015
 are+0.014
Neg logit contributions
Just-0.016
ager-0.014
age-0.014
P-0.014
bes-0.013
Token
Token ID198
Feature activation-4.96e-01

Pos logit contributions
Just+0.043
age+0.040
ager+0.040
P+0.038
bes+0.038
Neg logit contributions
 theirs-0.044
rings-0.037
 what-0.035
 are-0.033
 wow-0.033
Token on
Token ID319
Feature activation+4.46e-02

Pos logit contributions
P+0.089
Just+0.089
bes+0.089
age+0.087
sy+0.085
Neg logit contributions
 theirs-0.116
rings-0.107
 wow-0.096
 what-0.088
nam-0.087
Token their
Token ID511
Feature activation-3.06e-01

Pos logit contributions
 theirs+0.002
rings+0.002
nam+0.001
 wow+0.001
 maybe+0.001
Neg logit contributions
Just-0.006
bes-0.006
ager-0.006
P-0.006
age-0.006
Token warm
Token ID5814
Feature activation-8.51e-01

Pos logit contributions
Just+0.034
ager+0.033
age+0.033
ivering+0.031
P+0.031
Neg logit contributions
 theirs-0.024
rings-0.019
 what-0.018
 their-0.017
 are-0.017
Token p
Token ID279
Feature activation-6.36e-01

Pos logit contributions
Just+0.091
ager+0.089
P+0.082
ivering+0.081
age+0.081
Neg logit contributions
 theirs-0.071
rings-0.059
 what-0.056
 their-0.053
 are-0.052
Tokenaj
Token ID1228
Feature activation-2.56e+00

Pos logit contributions
Just+0.041
ager+0.037
age+0.036
P+0.035
bes+0.033
Neg logit contributions
 theirs-0.079
rings-0.071
 what-0.066
 are-0.063
 wow-0.063
Tokenamas
Token ID17485
Feature activation-4.14e+00

Pos logit contributions
ager+0.124
Just+0.115
eh+0.111
oster+0.100
P+0.098
Neg logit contributions
 theirs-0.326
rings-0.325
 are-0.301
 their-0.288
 eyes-0.287
Token and
Token ID290
Feature activation-4.13e-01

Pos logit contributions
Just+0.378
ager+0.354
P+0.346
age+0.343
bes+0.335
Neg logit contributions
 theirs-0.409
rings-0.347
 what-0.327
 are-0.312
 wow-0.297
Token crawl
Token ID27318
Feature activation+2.27e-01

Pos logit contributions
Just+0.036
age+0.034
bes+0.033
ager+0.033
P+0.032
Neg logit contributions
 theirs-0.040
rings-0.034
 wow-0.030
 what-0.029
nam-0.027
Token into
Token ID656
Feature activation-4.26e-01

Pos logit contributions
 theirs+0.022
rings+0.019
 what+0.018
 are+0.017
 wow+0.017
Neg logit contributions
Just-0.021
ager-0.019
age-0.019
P-0.018
bes-0.018
Token their
Token ID511
Feature activation-3.11e-01

Pos logit contributions
bes+0.042
Just+0.042
ce+0.040
Lu+0.040
P+0.039
Neg logit contributions
rings-0.030
 theirs-0.030
 wow-0.025
angles-0.021
endant-0.021
Token sleeping
Token ID11029
Feature activation-1.42e+00

Pos logit contributions
Just+0.031
ager+0.029
age+0.028
P+0.027
ivering+0.026
Neg logit contributions
 theirs-0.028
rings-0.024
 what-0.023
 are-0.022
 their-0.021
Token pair
Token ID5166
Feature activation-5.37e-01

Pos logit contributions
Just+0.012
age+0.011
ager+0.011
P+0.010
bes+0.010
Neg logit contributions
 theirs-0.010
rings-0.009
 what-0.008
 are-0.007
 wow-0.007
Token of
Token ID286
Feature activation+8.50e-01

Pos logit contributions
Just+0.048
age+0.046
ager+0.045
sy+0.041
bes+0.041
Neg logit contributions
 theirs-0.052
rings-0.044
nam-0.041
 what-0.040
 wow-0.039
Token matching
Token ID12336
Feature activation-5.00e-01

Pos logit contributions
 theirs+0.075
rings+0.063
 what+0.053
ours+0.053
 wow+0.052
Neg logit contributions
Just-0.083
ager-0.078
age-0.077
P-0.076
sy-0.073
Token p
Token ID279
Feature activation-5.37e-01

Pos logit contributions
Just+0.046
ager+0.044
age+0.043
bes+0.042
P+0.041
Neg logit contributions
 theirs-0.046
rings-0.038
 what-0.034
nam-0.034
 wow-0.034
Tokenaj
Token ID1228
Feature activation-2.51e+00

Pos logit contributions
Just+0.046
ager+0.043
age+0.043
bes+0.041
sy+0.041
Neg logit contributions
 theirs-0.055
rings-0.045
 what-0.043
nam-0.042
 wow-0.042
Tokenamas
Token ID17485
Feature activation-4.12e+00

Pos logit contributions
Just+0.122
ager+0.120
P+0.111
eh+0.111
oster+0.109
Neg logit contributions
 theirs-0.321
rings-0.317
 what-0.289
 are-0.283
 wow-0.279
Token with
Token ID351
Feature activation-4.81e-01

Pos logit contributions
Just+0.384
age+0.356
ager+0.356
P+0.343
bes+0.337
Neg logit contributions
 theirs-0.395
rings-0.335
 what-0.310
 wow-0.293
 are-0.292
Token com
Token ID401
Feature activation+9.95e-01

Pos logit contributions
Just+0.041
bes+0.041
ers+0.039
sy+0.039
ze+0.039
Neg logit contributions
 theirs-0.036
rings-0.031
ours-0.030
 wow-0.027
nam-0.026
Tokenets
Token ID1039
Feature activation+3.93e-01

Pos logit contributions
 theirs+0.106
rings+0.091
 what+0.085
 wow+0.082
 are+0.081
Neg logit contributions
Just-0.082
ager-0.076
age-0.076
P-0.072
bes-0.071
Token on
Token ID319
Feature activation+2.19e-01

Pos logit contributions
 theirs+0.040
rings+0.034
nam+0.032
 what+0.031
 wow+0.030
Neg logit contributions
Just-0.033
age-0.031
ager-0.030
bes-0.029
sy-0.028
Token them
Token ID606
Feature activation-4.92e-01

Pos logit contributions
 theirs+0.013
rings+0.010
 wow+0.008
nam+0.008
ours+0.008
Neg logit contributions
Just-0.027
bes-0.025
age-0.024
ce-0.024
ager-0.024
Token put
Token ID1234
Feature activation-1.02e+00

Pos logit contributions
Just+0.021
age+0.019
ager+0.019
bes+0.018
P+0.018
Neg logit contributions
 theirs-0.023
rings-0.020
 what-0.018
 wow-0.017
 are-0.017
Token on
Token ID319
Feature activation+2.16e-01

Pos logit contributions
Just+0.111
P+0.108
age+0.107
ager+0.105
bes+0.104
Neg logit contributions
 theirs-0.073
rings-0.061
 wow-0.051
 what-0.047
nam-0.047
Token their
Token ID511
Feature activation-3.83e-01

Pos logit contributions
 theirs+0.012
rings+0.010
 wow+0.007
 what+0.007
 are+0.007
Neg logit contributions
Just-0.027
bes-0.026
age-0.026
P-0.026
ager-0.025
Token p
Token ID279
Feature activation-5.73e-01

Pos logit contributions
Just+0.042
age+0.040
ager+0.040
P+0.038
ivering+0.038
Neg logit contributions
 theirs-0.031
rings-0.025
 what-0.024
 are-0.022
 wow-0.022
Tokenaj
Token ID1228
Feature activation-2.44e+00

Pos logit contributions
Just+0.040
ager+0.037
age+0.035
P+0.035
ivering+0.033
Neg logit contributions
 theirs-0.068
rings-0.061
 what-0.056
 wow-0.053
 are-0.053
Tokenamas
Token ID17485
Feature activation-4.12e+00

Pos logit contributions
ager+0.121
eh+0.113
P+0.110
Just+0.110
oster+0.103
Neg logit contributions
 theirs-0.295
rings-0.295
 what-0.268
 are-0.265
 wow-0.260
Token.
Token ID13
Feature activation+8.06e-02

Pos logit contributions
Just+0.411
ager+0.387
P+0.381
age+0.374
bes+0.365
Neg logit contributions
 theirs-0.371
rings-0.311
 what-0.290
 are-0.272
 wow-0.261
Token They
Token ID1119
Feature activation-1.49e-01

Pos logit contributions
 theirs+0.007
rings+0.006
 wow+0.005
nam+0.005
 are+0.005
Neg logit contributions
Just-0.009
age-0.008
bes-0.007
amas-0.007
ager-0.007
Token climbed
Token ID19952
Feature activation+4.69e-01

Pos logit contributions
Just+0.013
age+0.012
ager+0.012
P+0.012
sy+0.012
Neg logit contributions
 theirs-0.015
rings-0.013
 what-0.012
 wow-0.011
nam-0.011
Token into
Token ID656
Feature activation-4.24e-01

Pos logit contributions
 theirs+0.045
rings+0.038
 what+0.035
 are+0.033
 wow+0.033
Neg logit contributions
Just-0.045
ager-0.042
age-0.042
P-0.040
ivering-0.040
Token their
Token ID511
Feature activation-4.28e-01

Pos logit contributions
Just+0.046
bes+0.045
ce+0.043
Lu+0.043
amas+0.043
Neg logit contributions
 theirs-0.028
rings-0.026
 wow-0.022
ours-0.018
angles-0.017
Token put
Token ID1234
Feature activation-1.18e+00

Pos logit contributions
Just+0.045
age+0.043
bes+0.042
ager+0.041
P+0.040
Neg logit contributions
 theirs-0.048
rings-0.041
 what-0.036
 wow-0.035
 are-0.033
Token on
Token ID319
Feature activation+8.52e-02

Pos logit contributions
Just+0.124
P+0.123
bes+0.123
age+0.122
ers+0.121
Neg logit contributions
 theirs-0.075
rings-0.067
 wow-0.056
nam-0.051
 expect-0.049
Token their
Token ID511
Feature activation-3.71e-01

Pos logit contributions
 theirs+0.005
rings+0.004
 wow+0.003
 what+0.003
 are+0.003
Neg logit contributions
Just-0.011
bes-0.011
age-0.010
P-0.010
zer-0.010
Token p
Token ID279
Feature activation-7.07e-01

Pos logit contributions
Just+0.038
age+0.036
ager+0.036
P+0.035
ivering+0.034
Neg logit contributions
 theirs-0.032
rings-0.027
 what-0.024
 are-0.023
 wow-0.023
Tokenaj
Token ID1228
Feature activation-2.64e+00

Pos logit contributions
Just+0.045
ager+0.040
age+0.039
P+0.038
ivering+0.036
Neg logit contributions
 theirs-0.089
rings-0.080
 what-0.075
 wow-0.072
 are-0.072
Tokenamas
Token ID17485
Feature activation-4.11e+00

Pos logit contributions
ager+0.132
Just+0.123
eh+0.104
P+0.102
oster+0.095
Neg logit contributions
 theirs-0.340
rings-0.336
 are-0.310
 their-0.295
 what-0.294
Token.
Token ID13
Feature activation-2.22e-01

Pos logit contributions
Just+0.420
ager+0.397
P+0.389
age+0.384
ivering+0.372
Neg logit contributions
 theirs-0.364
rings-0.300
 what-0.280
 are-0.262
 their-0.253
Token They
Token ID1119
Feature activation-3.06e-01

Pos logit contributions
Just+0.023
age+0.021
bes+0.020
P+0.020
ager+0.020
Neg logit contributions
 theirs-0.019
rings-0.016
nam-0.014
 what-0.014
 wow-0.013
Token hugged
Token ID41130
Feature activation-2.97e-01

Pos logit contributions
Just+0.026
ager+0.025
age+0.024
P+0.024
sy+0.024
Neg logit contributions
 theirs-0.031
rings-0.026
 what-0.024
 wow-0.023
 ours-0.022
Token their
Token ID511
Feature activation-3.57e-01

Pos logit contributions
Just+0.033
age+0.031
co+0.030
bes+0.030
ze+0.029
Neg logit contributions
 theirs-0.021
rings-0.018
 wow-0.016
ours-0.015
 ours-0.014
Token mom
Token ID1995
Feature activation-1.22e-01

Pos logit contributions
Just+0.035
age+0.033
ager+0.033
P+0.031
bes+0.031
Neg logit contributions
 theirs-0.032
rings-0.027
 what-0.025
 wow-0.024
 are-0.023
Token He
Token ID679
Feature activation+1.01e-01

Pos logit contributions
 theirs+0.023
rings+0.019
 what+0.017
 are+0.016
 wow+0.016
Neg logit contributions
Just-0.034
ager-0.032
age-0.032
P-0.031
ivering-0.031
Token looked
Token ID3114
Feature activation-2.81e-01

Pos logit contributions
 theirs+0.008
rings+0.007
 what+0.007
 are+0.006
 wow+0.006
Neg logit contributions
Just-0.010
age-0.009
ivering-0.009
P-0.009
amas-0.009
Token at
Token ID379
Feature activation+1.20e+00

Pos logit contributions
Just+0.024
ager+0.021
age+0.021
sy+0.021
ivering+0.021
Neg logit contributions
 theirs-0.028
rings-0.025
 wow-0.021
 are-0.021
nam-0.021
Token it
Token ID340
Feature activation+2.25e-01

Pos logit contributions
 theirs+0.073
rings+0.060
 wow+0.048
ours+0.042
 are+0.041
Neg logit contributions
Just-0.143
ager-0.135
bes-0.133
age-0.133
zer-0.131
Token with
Token ID351
Feature activation-3.16e-01

Pos logit contributions
 theirs+0.023
rings+0.019
 what+0.018
 are+0.017
 wow+0.017
Neg logit contributions
Just-0.020
ager-0.019
age-0.019
P-0.018
bes-0.017
Token amaz
Token ID40642
Feature activation+3.79e+00

Pos logit contributions
Just+0.031
age+0.028
ager+0.027
ze+0.027
P+0.027
Neg logit contributions
 theirs-0.026
rings-0.025
ours-0.021
nam-0.019
angles-0.019
Tokenement
Token ID972
Feature activation+1.91e-01

Pos logit contributions
 theirs+0.354
rings+0.299
 what+0.274
 wow+0.261
 are+0.259
Neg logit contributions
Just-0.365
age-0.338
ager-0.338
P-0.326
bes-0.321
Token and
Token ID290
Feature activation+2.80e-02

Pos logit contributions
 theirs+0.020
rings+0.017
nam+0.015
 are+0.015
 wow+0.015
Neg logit contributions
Just-0.016
age-0.015
ager-0.014
bes-0.014
ivering-0.014
Token said
Token ID531
Feature activation-1.32e-02

Pos logit contributions
 theirs+0.003
rings+0.002
 what+0.002
 are+0.002
 wow+0.002
Neg logit contributions
Just-0.003
ager-0.002
age-0.002
bes-0.002
P-0.002
Token,
Token ID11
Feature activation+2.44e-01

Pos logit contributions
Just+0.001
age+0.001
ager+0.001
P+0.001
sy+0.001
Neg logit contributions
 theirs-0.001
rings-0.001
nam-0.001
 what-0.001
 are-0.001
Token "
Token ID366
Feature activation-2.36e-04

Pos logit contributions
 theirs+0.018
rings+0.014
 what+0.014
 wow+0.013
 are+0.012
Neg logit contributions
Just-0.027
ager-0.027
age-0.027
P-0.026
ivering-0.025
Token.
Token ID13
Feature activation+1.46e-01

Pos logit contributions
Just+0.015
age+0.014
ager+0.014
P+0.013
bes+0.013
Neg logit contributions
 theirs-0.015
rings-0.013
 what-0.012
 are-0.011
 wow-0.011
Token He
Token ID679
Feature activation+1.28e-01

Pos logit contributions
 theirs+0.014
rings+0.012
 what+0.011
nam+0.010
 wow+0.010
Neg logit contributions
Just-0.014
age-0.013
ager-0.013
P-0.012
bes-0.012
Token always
Token ID1464
Feature activation-8.12e-01

Pos logit contributions
 theirs+0.011
 what+0.009
 are+0.009
rings+0.008
 their+0.008
Neg logit contributions
Just-0.013
ivering-0.012
amas-0.012
age-0.012
P-0.012
Token used
Token ID973
Feature activation-5.55e-01

Pos logit contributions
Just+0.072
age+0.067
ager+0.067
P+0.064
bes+0.063
Neg logit contributions
 theirs-0.082
rings-0.070
 what-0.065
 wow-0.062
 are-0.061
Token the
Token ID262
Feature activation-1.41e-01

Pos logit contributions
Just+0.057
age+0.054
bes+0.052
ager+0.051
sy+0.051
Neg logit contributions
 theirs-0.041
rings-0.037
 wow-0.032
ours-0.032
nam-0.030
Token loop
Token ID9052
Feature activation+2.36e+00

Pos logit contributions
Just+0.012
age+0.011
ager+0.011
P+0.011
bes+0.011
Neg logit contributions
 theirs-0.014
rings-0.012
 what-0.012
 wow-0.011
 are-0.011
Token to
Token ID284
Feature activation+4.74e-01

Pos logit contributions
 theirs+0.217
rings+0.183
 what+0.169
 are+0.159
 wow+0.158
Neg logit contributions
Just-0.230
ager-0.214
age-0.211
P-0.208
bes-0.203
Token lead
Token ID1085
Feature activation+1.90e+00

Pos logit contributions
 theirs+0.042
rings+0.037
 wow+0.032
 what+0.031
ours+0.031
Neg logit contributions
Just-0.045
age-0.044
ager-0.042
bes-0.041
sy-0.040
Token them
Token ID606
Feature activation-3.59e-01

Pos logit contributions
 theirs+0.114
rings+0.085
 what+0.075
 are+0.066
 wow+0.065
Neg logit contributions
Just-0.247
ager-0.234
age-0.234
P-0.228
bes-0.226
Token back
Token ID736
Feature activation-3.00e-01

Pos logit contributions
Just+0.037
ager+0.034
age+0.034
P+0.033
bes+0.033
Neg logit contributions
 theirs-0.032
rings-0.026
 what-0.024
 are-0.023
 wow-0.022
Token home
Token ID1363
Feature activation-1.59e+00

Pos logit contributions
Just+0.034
ager+0.032
P+0.032
ivering+0.032
age+0.031
Neg logit contributions
 theirs-0.024
rings-0.018
 what-0.018
 their-0.016
 are-0.016
Token feel
Token ID1254
Feature activation+1.44e+00

Pos logit contributions
 theirs+0.055
rings+0.046
 what+0.040
 wow+0.038
 are+0.037
Neg logit contributions
Just-0.074
age-0.070
ager-0.069
P-0.067
bes-0.067
Token calm
Token ID9480
Feature activation+7.09e-01

Pos logit contributions
 theirs+0.123
rings+0.107
 wow+0.088
 what+0.088
nam+0.086
Neg logit contributions
Just-0.149
age-0.139
ager-0.137
P-0.135
ivering-0.133
Token",
Token ID1600
Feature activation+4.35e-01

Pos logit contributions
 theirs+0.068
rings+0.057
 what+0.054
 are+0.051
 wow+0.050
Neg logit contributions
Just-0.067
ager-0.063
age-0.061
P-0.061
bes-0.060
Token or
Token ID393
Feature activation+9.66e-02

Pos logit contributions
 theirs+0.031
rings+0.025
 what+0.022
 wow+0.021
 are+0.020
Neg logit contributions
Just-0.051
age-0.048
ager-0.048
P-0.046
bes-0.046
Token "
Token ID366
Feature activation-1.51e-02

Pos logit contributions
 theirs+0.007
rings+0.006
 wow+0.005
 are+0.005
 what+0.004
Neg logit contributions
Just-0.011
age-0.010
ager-0.010
P-0.010
bes-0.010
TokenSm
Token ID7556
Feature activation+2.32e+00

Pos logit contributions
Just+0.001
ager+0.001
age+0.001
bes+0.001
ivering+0.001
Neg logit contributions
 theirs-0.002
rings-0.001
 what-0.001
 are-0.001
nam-0.001
Tokenile
Token ID576
Feature activation+2.70e-01

Pos logit contributions
 theirs+0.265
rings+0.228
 what+0.218
 are+0.208
 wow+0.203
Neg logit contributions
Just-0.175
age-0.158
ager-0.154
bes-0.150
P-0.149
Token and
Token ID290
Feature activation+1.56e-02

Pos logit contributions
 theirs+0.023
rings+0.019
 what+0.019
 are+0.018
 wow+0.017
Neg logit contributions
Just-0.027
ager-0.025
P-0.025
age-0.025
bes-0.024
Token let
Token ID1309
Feature activation+3.24e-01

Pos logit contributions
 theirs+0.001
rings+0.001
 what+0.001
 wow+0.001
nam+0.001
Neg logit contributions
Just-0.002
age-0.002
ager-0.002
P-0.002
bes-0.002
Token the
Token ID262
Feature activation+1.31e-01

Pos logit contributions
 theirs+0.032
 what+0.028
 are+0.027
rings+0.026
 their+0.025
Neg logit contributions
Just-0.030
ager-0.027
bes-0.027
ivering-0.025
ider-0.025
Token sadness
Token ID25303
Feature activation+2.73e-01

Pos logit contributions
 theirs+0.012
rings+0.010
 what+0.010
 are+0.009
 wow+0.009
Neg logit contributions
Just-0.013
ager-0.012
age-0.012
bes-0.011
P-0.011
Token
Token ID198
Feature activation-6.41e-01

Pos logit contributions
Just+0.010
age+0.010
ager+0.009
bes+0.009
P+0.009
Neg logit contributions
 theirs-0.013
rings-0.011
nam-0.011
 what-0.010
 wow-0.010
Token
Token ID198
Feature activation-6.51e-01

Pos logit contributions
Just+0.056
age+0.052
ager+0.051
P+0.049
bes+0.048
Neg logit contributions
 theirs-0.065
rings-0.056
 what-0.052
 wow-0.050
 are-0.049
TokenOne
Token ID3198
Feature activation+1.09e-01

Pos logit contributions
Just+0.054
ager+0.051
age+0.050
ivering+0.049
bes+0.049
Neg logit contributions
 theirs-0.067
rings-0.057
 what-0.054
 are-0.052
 wow-0.052
Token day
Token ID1110
Feature activation-9.20e-01

Pos logit contributions
 theirs+0.011
 what+0.009
rings+0.009
 are+0.008
 their+0.008
Neg logit contributions
Just-0.010
bes-0.009
ager-0.009
age-0.009
amas-0.009
Token,
Token ID11
Feature activation+1.42e-02

Pos logit contributions
Just+0.086
age+0.080
ager+0.079
P+0.077
bes+0.075
Neg logit contributions
 theirs-0.088
rings-0.075
 what-0.068
 wow-0.065
nam-0.064
Token Zig
Token ID24992
Feature activation+2.34e+00

Pos logit contributions
 theirs+0.001
rings+0.001
ours+0.001
nam+0.001
 ours+0.001
Neg logit contributions
Just-0.001
P-0.001
age-0.001
ager-0.001
B-0.001
Tokengy
Token ID1360
Feature activation-1.82e+00

Pos logit contributions
 theirs+0.275
rings+0.254
 what+0.230
 are+0.216
 their+0.211
Neg logit contributions
Just-0.140
P-0.139
ager-0.138
Now-0.131
amas-0.128
Token's
Token ID338
Feature activation+6.91e-01

Pos logit contributions
Just+0.188
P+0.184
bes+0.181
ivering+0.181
amas+0.179
Neg logit contributions
 theirs-0.123
 are-0.114
 Tom-0.110
 they-0.106
 what-0.106
Token friend
Token ID1545
Feature activation-7.36e-01

Pos logit contributions
 theirs+0.070
rings+0.061
 what+0.058
 are+0.055
 wow+0.052
Neg logit contributions
Just-0.060
ager-0.056
bes-0.055
age-0.053
ivering-0.052
Token,
Token ID11
Feature activation+5.24e-02

Pos logit contributions
Just+0.082
ager+0.076
age+0.076
bes+0.075
ivering+0.073
Neg logit contributions
 theirs-0.058
rings-0.047
 what-0.046
 are-0.042
 wow-0.041
Token a
Token ID257
Feature activation-1.74e-01

Pos logit contributions
 theirs+0.004
rings+0.003
nam+0.003
ours+0.003
 wow+0.003
Neg logit contributions
Just-0.006
P-0.005
ager-0.005
age-0.005
sy-0.005
Token had
Token ID550
Feature activation-2.92e-01

Pos logit contributions
amas+0.011
ivering+0.010
Just+0.010
age+0.010
lor+0.010
Neg logit contributions
 theirs-0.006
 are-0.005
 what-0.005
 their-0.005
 they-0.004
Token a
Token ID257
Feature activation-2.80e-01

Pos logit contributions
Just+0.037
ager+0.036
age+0.035
ivering+0.035
bes+0.035
Neg logit contributions
 theirs-0.017
rings-0.013
 what-0.012
 are-0.011
 wow-0.010
Token big
Token ID1263
Feature activation-1.23e+00

Pos logit contributions
Just+0.032
ager+0.030
bes+0.029
age+0.029
ivering+0.029
Neg logit contributions
 theirs-0.020
rings-0.016
 what-0.016
 wow-0.014
 look-0.014
Token,
Token ID11
Feature activation+2.60e-02

Pos logit contributions
Just+0.124
ager+0.114
age+0.112
P+0.109
bes+0.108
Neg logit contributions
 theirs-0.110
rings-0.091
 what-0.086
 are-0.083
 wow-0.082
Token bus
Token ID1323
Feature activation+3.58e-01

Pos logit contributions
 theirs+0.002
rings+0.002
 what+0.002
 wow+0.001
 are+0.001
Neg logit contributions
Just-0.003
ager-0.003
age-0.003
P-0.003
bes-0.003
Tokenhy
Token ID12114
Feature activation+2.40e+00

Pos logit contributions
 theirs+0.029
rings+0.025
 what+0.023
 are+0.022
 wow+0.021
Neg logit contributions
Just-0.038
P-0.036
ager-0.035
ivering-0.035
bes-0.034
Token tail
Token ID7894
Feature activation-4.20e-01

Pos logit contributions
 theirs+0.247
rings+0.210
 what+0.205
 are+0.196
 wow+0.196
Neg logit contributions
Just-0.202
ager-0.189
sy-0.182
age-0.178
rd-0.175
Token and
Token ID290
Feature activation-1.76e-01

Pos logit contributions
Just+0.044
ager+0.042
P+0.042
amas+0.041
age+0.040
Neg logit contributions
 theirs-0.031
rings-0.027
 what-0.025
 are-0.023
 wow-0.022
Token sharp
Token ID7786
Feature activation-1.85e-01

Pos logit contributions
Just+0.019
ager+0.018
age+0.018
ivering+0.017
bes+0.017
Neg logit contributions
 theirs-0.014
rings-0.012
 what-0.011
 wow-0.010
nam-0.010
Token teeth
Token ID9941
Feature activation+5.28e-01

Pos logit contributions
Just+0.020
ager+0.019
P+0.019
age+0.019
ivering+0.018
Neg logit contributions
 theirs-0.015
rings-0.012
 what-0.011
 are-0.010
 wow-0.010
Token.
Token ID13
Feature activation-2.00e-01

Pos logit contributions
 theirs+0.050
rings+0.042
 what+0.039
 are+0.037
 wow+0.036
Neg logit contributions
Just-0.050
ager-0.047
age-0.047
P-0.045
bes-0.044
Token,
Token ID11
Feature activation+3.39e-01

Pos logit contributions
 theirs+0.102
rings+0.086
 what+0.081
 are+0.076
 wow+0.075
Neg logit contributions
Just-0.096
ager-0.089
age-0.088
P-0.086
bes-0.084
Token but
Token ID475
Feature activation-8.42e-01

Pos logit contributions
 theirs+0.031
rings+0.026
 what+0.025
 wow+0.023
nam+0.023
Neg logit contributions
Just-0.032
ager-0.032
age-0.031
P-0.031
ivering-0.029
Token it
Token ID340
Feature activation+2.89e-01

Pos logit contributions
Just+0.101
ager+0.093
age+0.092
P+0.090
bes+0.089
Neg logit contributions
 theirs-0.059
rings-0.048
 wow-0.038
 what-0.038
 are-0.037
Token was
Token ID373
Feature activation-1.55e-01

Pos logit contributions
 theirs+0.026
rings+0.022
 are+0.021
 what+0.021
 maybe+0.020
Neg logit contributions
Just-0.027
ager-0.026
age-0.024
P-0.024
bes-0.024
Token hard
Token ID1327
Feature activation+1.70e-02

Pos logit contributions
Just+0.015
age+0.014
ager+0.013
sy+0.013
ivering+0.013
Neg logit contributions
 theirs-0.014
rings-0.012
 wow-0.011
 what-0.011
 are-0.010
Token to
Token ID284
Feature activation+5.12e-01

Pos logit contributions
 theirs+0.002
rings+0.001
 what+0.001
 wow+0.001
nam+0.001
Neg logit contributions
Just-0.002
age-0.002
ager-0.002
P-0.001
bes-0.001
Token drink
Token ID4144
Feature activation-7.99e-01

Pos logit contributions
 theirs+0.043
rings+0.035
 what+0.032
 wow+0.030
 are+0.030
Neg logit contributions
Just-0.054
age-0.051
ager-0.051
P-0.049
bes-0.049
Token as
Token ID355
Feature activation+1.92e+00

Pos logit contributions
Just+0.073
age+0.069
ager+0.067
P+0.066
bes+0.065
Neg logit contributions
 theirs-0.076
rings-0.066
 what-0.059
 wow-0.058
nam-0.056
Token his
Token ID465
Feature activation+4.63e-01

Pos logit contributions
 theirs+0.153
rings+0.142
 wow+0.119
 are+0.114
 what+0.109
Neg logit contributions
Just-0.193
ager-0.174
P-0.172
sy-0.170
age-0.166
Token throat
Token ID13589
Feature activation-2.15e-01

Pos logit contributions
 theirs+0.037
rings+0.031
 what+0.029
 are+0.027
 their+0.026
Neg logit contributions
Just-0.050
ager-0.048
P-0.046
age-0.046
ivering-0.045
Token was
Token ID373
Feature activation-1.20e-01

Pos logit contributions
Just+0.021
ager+0.019
age+0.019
P+0.019
bes+0.018
Neg logit contributions
 theirs-0.020
rings-0.017
 what-0.016
 are-0.015
 wow-0.015
Token mom
Token ID1995
Feature activation-1.31e-01

Pos logit contributions
Just+0.090
age+0.084
ager+0.084
P+0.081
bes+0.081
Neg logit contributions
 theirs-0.067
rings-0.055
 what-0.049
 wow-0.046
 are-0.046
Token hugged
Token ID41130
Feature activation-3.46e-01

Pos logit contributions
Just+0.014
P+0.013
age+0.013
bes+0.013
amas+0.013
Neg logit contributions
 theirs-0.009
 what-0.009
 are-0.008
rings-0.008
 maybe-0.007
Token them
Token ID606
Feature activation-5.90e-01

Pos logit contributions
Just+0.037
P+0.036
age+0.034
B+0.034
co+0.034
Neg logit contributions
 theirs-0.024
rings-0.022
 wow-0.020
nam-0.018
endant-0.018
Token and
Token ID290
Feature activation-1.64e-01

Pos logit contributions
Just+0.050
age+0.046
ager+0.046
P+0.045
bes+0.044
Neg logit contributions
 theirs-0.062
rings-0.053
 what-0.051
 are-0.048
 wow-0.047
Token said
Token ID531
Feature activation-3.02e-01

Pos logit contributions
Just+0.014
ager+0.013
P+0.012
bes+0.012
age+0.012
Neg logit contributions
 theirs-0.017
rings-0.015
 wow-0.012
 ours-0.012
nam-0.012
Token,
Token ID11
Feature activation+4.46e-02

Pos logit contributions
Just+0.029
age+0.025
ze+0.024
ager+0.024
ce+0.024
Neg logit contributions
 theirs-0.028
rings-0.024
nam-0.021
 ours-0.020
angles-0.020
Token "
Token ID366
Feature activation-2.36e-01

Pos logit contributions
 theirs+0.003
rings+0.003
 what+0.003
 wow+0.002
 are+0.002
Neg logit contributions
Just-0.005
ager-0.005
age-0.005
P-0.005
ivering-0.004
TokenI
Token ID40
Feature activation-1.58e-01

Pos logit contributions
Just+0.019
age+0.019
ager+0.018
bes+0.018
ivering+0.018
Neg logit contributions
 theirs-0.024
rings-0.021
 what-0.020
 are-0.019
 wow-0.018
Token know
Token ID760
Feature activation+1.81e+00

Pos logit contributions
Just+0.015
age+0.014
ager+0.014
P+0.014
sy+0.013
Neg logit contributions
 theirs-0.015
rings-0.013
 what-0.011
 wow-0.011
nam-0.011
Token you
Token ID345
Feature activation-1.52e-04

Pos logit contributions
 theirs+0.193
rings+0.162
nam+0.147
ours+0.134
 wow+0.134
Neg logit contributions
Just-0.147
ager-0.131
P-0.120
bes-0.120
rd-0.119
Token want
Token ID765
Feature activation+3.28e-01

Pos logit contributions
ager+0.000
Just+0.000
sy+0.000
age+0.000
bes+0.000
Neg logit contributions
 theirs-0.000
rings-0.000
 wow-0.000
nam-0.000
ours-0.000
TokenThe
Token ID464
Feature activation+9.18e-02

Pos logit contributions
amas+0.025
bes+0.024
ivering+0.024
age+0.024
ager+0.023
Neg logit contributions
 theirs-0.028
 what-0.024
 wow-0.022
rings-0.022
 their-0.021
Token goat
Token ID26917
Feature activation+5.47e-02

Pos logit contributions
 theirs+0.009
 what+0.007
rings+0.007
 are+0.007
 wow+0.007
Neg logit contributions
Just-0.008
bes-0.008
age-0.008
ager-0.008
ivering-0.007
Token quickly
Token ID2952
Feature activation-7.68e-01

Pos logit contributions
 theirs+0.004
 what+0.004
rings+0.004
 are+0.004
 wow+0.003
Neg logit contributions
Just-0.005
P-0.005
bes-0.005
amas-0.005
ager-0.005
Token ran
Token ID4966
Feature activation-4.31e-01

Pos logit contributions
Just+0.075
age+0.069
ager+0.069
amas+0.069
bes+0.068
Neg logit contributions
 theirs-0.067
rings-0.056
 what-0.054
 are-0.051
 wow-0.051
Token out
Token ID503
Feature activation+8.76e-01

Pos logit contributions
Just+0.043
ager+0.041
age+0.040
bes+0.040
P+0.040
Neg logit contributions
 theirs-0.039
rings-0.031
 what-0.031
 their-0.028
 wow-0.027
Token of
Token ID286
Feature activation+1.15e+00

Pos logit contributions
 theirs+0.075
rings+0.062
 what+0.057
 wow+0.054
 are+0.053
Neg logit contributions
Just-0.091
age-0.085
ager-0.085
P-0.082
bes-0.081
Token the
Token ID262
Feature activation-1.90e-02

Pos logit contributions
 theirs+0.070
rings+0.066
 wow+0.050
 are+0.048
 what+0.045
Neg logit contributions
Just-0.132
P-0.127
bes-0.125
ager-0.125
age-0.125
Token shed
Token ID14999
Feature activation+2.70e-01

Pos logit contributions
Just+0.002
ager+0.002
age+0.002
bes+0.002
ivering+0.002
Neg logit contributions
 theirs-0.002
rings-0.002
 what-0.001
 are-0.001
 their-0.001
Token and
Token ID290
Feature activation-7.08e-02

Pos logit contributions
 theirs+0.027
rings+0.023
 what+0.022
 are+0.020
 wow+0.020
Neg logit contributions
Just-0.024
P-0.022
ager-0.022
age-0.022
bes-0.021
Token back
Token ID736
Feature activation-1.74e-01

Pos logit contributions
Just+0.007
age+0.006
ager+0.006
P+0.006
ivering+0.006
Neg logit contributions
 theirs-0.007
rings-0.006
 what-0.005
 wow-0.005
 are-0.005
Token to
Token ID284
Feature activation+5.51e-01

Pos logit contributions
Just+0.017
age+0.016
ager+0.016
P+0.015
bes+0.015
Neg logit contributions
 theirs-0.016
rings-0.014
 what-0.013
 wow-0.012
 are-0.012
Token and
Token ID290
Feature activation+1.13e-01

Pos logit contributions
Just+0.077
age+0.070
ager+0.070
P+0.067
bes+0.066
Neg logit contributions
 theirs-0.106
rings-0.092
 what-0.086
 wow-0.082
 are-0.082
Token fast
Token ID3049
Feature activation-2.97e-02

Pos logit contributions
 theirs+0.011
rings+0.011
 wow+0.009
 what+0.009
ours+0.009
Neg logit contributions
Just-0.009
sy-0.009
P-0.009
age-0.008
oster-0.008
Token.
Token ID13
Feature activation+4.86e-02

Pos logit contributions
Just+0.002
age+0.002
ager+0.002
bes+0.002
P+0.002
Neg logit contributions
 theirs-0.003
rings-0.003
 what-0.002
 wow-0.002
nam-0.002
Token
Token ID198
Feature activation-5.63e-01

Pos logit contributions
 theirs+0.004
rings+0.003
 what+0.003
 wow+0.002
nam+0.002
Neg logit contributions
Just-0.006
age-0.005
ager-0.005
P-0.005
bes-0.005
Token
Token ID198
Feature activation-5.88e-01

Pos logit contributions
Just+0.055
age+0.053
ager+0.053
ivering+0.051
P+0.051
Neg logit contributions
 theirs-0.048
rings-0.040
 what-0.039
 are-0.037
 wow-0.035
TokenOne
Token ID3198
Feature activation+2.26e-01

Pos logit contributions
age+0.048
amas+0.046
ager+0.046
bes+0.046
Just+0.046
Neg logit contributions
 theirs-0.053
 what-0.046
 are-0.046
rings-0.045
 wow-0.044
Token day
Token ID1110
Feature activation-8.28e-01

Pos logit contributions
 theirs+0.026
rings+0.023
 what+0.021
 wow+0.020
 are+0.020
Neg logit contributions
Just-0.017
age-0.016
ager-0.016
P-0.015
bes-0.014
Token a
Token ID257
Feature activation-1.31e-01

Pos logit contributions
Just+0.068
P+0.061
ager+0.061
age+0.060
bes+0.056
Neg logit contributions
 theirs-0.090
rings-0.077
nam-0.067
 what-0.066
 wow-0.065
Token man
Token ID582
Feature activation+2.31e-01

Pos logit contributions
Just+0.012
age+0.011
bes+0.011
ager+0.010
ivering+0.010
Neg logit contributions
 theirs-0.013
 what-0.011
rings-0.010
 wow-0.010
 are-0.010
Token told
Token ID1297
Feature activation-5.72e-01

Pos logit contributions
 theirs+0.021
rings+0.018
 what+0.017
 are+0.016
 wow+0.016
Neg logit contributions
Just-0.022
age-0.021
ager-0.020
bes-0.020
P-0.020
Token the
Token ID262
Feature activation-2.14e-01

Pos logit contributions
Just+0.063
ager+0.059
P+0.059
age+0.059
zer+0.059
Neg logit contributions
 theirs-0.037
rings-0.036
nam-0.029
 wow-0.026
ours-0.025
Token
Token ID198
Feature activation-6.06e-01

Pos logit contributions
 theirs+0.128
rings+0.111
 wow+0.105
nam+0.102
 what+0.101
Neg logit contributions
Just-0.088
age-0.080
ager-0.075
P-0.075
bes-0.074
Token
Token ID198
Feature activation-5.88e-01

Pos logit contributions
age+0.060
ager+0.059
Just+0.058
ivering+0.057
bes+0.057
Neg logit contributions
 theirs-0.050
rings-0.041
 what-0.041
 are-0.036
 maybe-0.035
TokenShe
Token ID3347
Feature activation-1.35e-02

Pos logit contributions
age+0.048
amas+0.047
ager+0.047
bes+0.047
ivering+0.045
Neg logit contributions
 theirs-0.053
rings-0.046
 what-0.046
nam-0.042
 are-0.041
Token took
Token ID1718
Feature activation-3.27e-01

Pos logit contributions
Just+0.001
age+0.001
ivering+0.001
ager+0.001
P+0.001
Neg logit contributions
 theirs-0.001
rings-0.001
 what-0.001
 wow-0.001
 are-0.001
Token the
Token ID262
Feature activation-3.39e-01

Pos logit contributions
Just+0.035
P+0.033
age+0.033
ce+0.032
ager+0.032
Neg logit contributions
 theirs-0.025
rings-0.019
nam-0.017
 are-0.016
 wow-0.016
Token frame
Token ID5739
Feature activation+1.23e+00

Pos logit contributions
Just+0.032
age+0.030
ager+0.030
P+0.029
bes+0.028
Neg logit contributions
 theirs-0.032
rings-0.026
 what-0.024
 wow-0.023
 are-0.022
Token and
Token ID290
Feature activation-2.76e-01

Pos logit contributions
 theirs+0.117
rings+0.100
 what+0.092
 are+0.086
 wow+0.085
Neg logit contributions
Just-0.118
ager-0.109
age-0.107
P-0.106
ivering-0.104
Token put
Token ID1234
Feature activation-9.78e-01

Pos logit contributions
Just+0.022
ager+0.020
age+0.019
bes+0.019
P+0.019
Neg logit contributions
 theirs-0.030
rings-0.023
 what-0.022
 wow-0.021
 are-0.021
Token it
Token ID340
Feature activation+3.02e-02

Pos logit contributions
Just+0.107
P+0.099
bes+0.099
Now+0.099
age+0.099
Neg logit contributions
 theirs-0.069
rings-0.052
nam-0.045
ours-0.042
 wow-0.040
Token up
Token ID510
Feature activation-1.27e-01

Pos logit contributions
 theirs+0.003
rings+0.003
 what+0.002
 are+0.002
 wow+0.002
Neg logit contributions
Just-0.003
ager-0.002
age-0.002
P-0.002
ivering-0.002
Token on
Token ID319
Feature activation+1.84e-01

Pos logit contributions
Just+0.011
age+0.010
ager+0.010
P+0.009
bes+0.009
Neg logit contributions
 theirs-0.013
rings-0.012
 what-0.011
 wow-0.010
 are-0.010
Tokennight
Token ID3847
Feature activation-1.48e+00

Pos logit contributions
 theirs+0.129
rings+0.111
 what+0.106
 wow+0.103
 are+0.102
Neg logit contributions
Just-0.100
age-0.089
ager-0.088
bes-0.087
P-0.087
Token,
Token ID11
Feature activation+3.22e-01

Pos logit contributions
Just+0.167
P+0.157
ager+0.156
bes+0.151
age+0.147
Neg logit contributions
 theirs-0.114
 what-0.095
rings-0.093
 wow-0.088
 are-0.085
Token car
Token ID1097
Feature activation+6.29e-01

Pos logit contributions
 theirs+0.026
rings+0.022
 what+0.019
nam+0.018
 wow+0.017
Neg logit contributions
Just-0.034
age-0.032
ager-0.032
P-0.031
bes-0.031
Token.
Token ID13
Feature activation+4.03e-01

Pos logit contributions
 theirs+0.058
rings+0.050
 what+0.048
 are+0.048
 wow+0.046
Neg logit contributions
Just-0.060
P-0.055
ager-0.053
bes-0.052
age-0.052
Token I
Token ID314
Feature activation+3.79e-01

Pos logit contributions
 theirs+0.031
rings+0.026
 what+0.024
 wow+0.023
 are+0.023
Neg logit contributions
Just-0.043
ager-0.042
P-0.041
age-0.040
bes-0.040
Token love
Token ID1842
Feature activation-3.16e-01

Pos logit contributions
 theirs+0.027
rings+0.021
 are+0.020
 what+0.020
 wow+0.018
Neg logit contributions
Just-0.044
P-0.041
ager-0.041
bes-0.040
age-0.040
Token you
Token ID345
Feature activation+2.26e-01

Pos logit contributions
Just+0.031
age+0.029
ager+0.029
P+0.028
bes+0.028
Neg logit contributions
 theirs-0.029
rings-0.024
 what-0.022
 wow-0.021
 are-0.021
Token."
Token ID526
Feature activation+6.94e-02

Pos logit contributions
 theirs+0.021
rings+0.017
 what+0.017
 are+0.016
 wow+0.015
Neg logit contributions
Just-0.022
ager-0.021
P-0.021
age-0.020
bes-0.020
Token And
Token ID843
Feature activation+1.65e-01

Pos logit contributions
 theirs+0.006
rings+0.005
 what+0.004
 wow+0.004
 are+0.004
Neg logit contributions
Just-0.007
ager-0.007
age-0.007
P-0.007
ivering-0.007
Token they
Token ID484
Feature activation-2.23e-02

Pos logit contributions
 theirs+0.012
rings+0.010
 what+0.008
 wow+0.008
nam+0.008
Neg logit contributions
Just-0.019
age-0.018
ager-0.018
P-0.017
bes-0.017
Token both
Token ID1111
Feature activation+5.92e-01

Pos logit contributions
Just+0.002
age+0.002
sy+0.002
ager+0.002
P+0.002
Neg logit contributions
 theirs-0.002
rings-0.002
 what-0.002
ours-0.001
nam-0.001
Token's
Token ID338
Feature activation+1.04e+00

Pos logit contributions
 theirs+0.001
rings+0.001
 what+0.001
 wow+0.001
nam+0.001
Neg logit contributions
Just-0.001
age-0.001
ager-0.001
P-0.001
bes-0.001
Token words
Token ID2456
Feature activation+1.01e+00

Pos logit contributions
 theirs+0.105
rings+0.088
 what+0.088
 are+0.081
 wow+0.078
Neg logit contributions
Just-0.093
P-0.088
ager-0.086
age-0.083
eh-0.082
Token.
Token ID13
Feature activation+2.18e-01

Pos logit contributions
 theirs+0.102
rings+0.088
 what+0.080
 wow+0.078
nam+0.077
Neg logit contributions
Just-0.087
age-0.081
ager-0.080
bes-0.075
P-0.075
Token<|endoftext|>
Token ID50256
Feature activation+8.92e-01

Pos logit contributions
 theirs+0.020
rings+0.016
 what+0.015
 are+0.014
 wow+0.014
Neg logit contributions
Just-0.021
ager-0.020
age-0.020
P-0.020
ivering-0.019
TokenOnce
Token ID7454
Feature activation+9.43e-01

Pos logit contributions
 theirs+0.067
 are+0.054
 what+0.054
rings+0.052
 their+0.049
Neg logit contributions
Just-0.098
ager-0.094
age-0.092
ivering-0.092
bes-0.088
Token upon
Token ID2402
Feature activation-2.52e-01

Pos logit contributions
 theirs+0.084
rings+0.077
 wow+0.071
nam+0.071
 flashes+0.062
Neg logit contributions
Just-0.081
P-0.075
 year-0.074
eh-0.072
Lu-0.071
Token a
Token ID257
Feature activation-1.50e-01

Pos logit contributions
Just+0.028
ager+0.025
age+0.025
P+0.025
bes+0.024
Neg logit contributions
 theirs-0.020
rings-0.018
ours-0.015
 wow-0.014
nam-0.014
Token time
Token ID640
Feature activation-3.96e-02

Pos logit contributions
age+0.013
Just+0.013
amas+0.012
bes+0.012
ager+0.012
Neg logit contributions
 theirs-0.013
 what-0.012
 are-0.011
 their-0.011
 look-0.010
Token,
Token ID11
Feature activation+1.77e-01

Pos logit contributions
Just+0.004
ager+0.003
age+0.003
P+0.003
bes+0.003
Neg logit contributions
 theirs-0.004
rings-0.003
 what-0.003
nam-0.003
 wow-0.003
Token there
Token ID612
Feature activation-3.86e-01

Pos logit contributions
 theirs+0.017
rings+0.015
 wow+0.012
nam+0.012
 what+0.011
Neg logit contributions
Just-0.017
P-0.016
ager-0.015
sy-0.015
age-0.015
Token was
Token ID373
Feature activation-2.72e-01

Pos logit contributions
Just+0.024
age+0.021
ager+0.021
P+0.020
bes+0.020
Neg logit contributions
 theirs-0.049
rings-0.044
 what-0.040
nam-0.039
 wow-0.039
Token-
Token ID12
Feature activation-1.20e-01

Pos logit contributions
Just+0.002
age+0.002
lor+0.002
amas+0.002
ager+0.002
Neg logit contributions
 theirs-0.004
 what-0.004
 are-0.003
 their-0.003
rings-0.003
Tokenyears
Token ID19002
Feature activation+1.26e+00

Pos logit contributions
Just+0.012
age+0.011
ager+0.011
P+0.011
bes+0.010
Neg logit contributions
 theirs-0.011
rings-0.009
 what-0.008
 wow-0.008
 are-0.008
Token old
Token ID1468
Feature activation+1.25e+00

Pos logit contributions
 theirs+0.164
rings+0.141
 what+0.136
 are+0.129
 their+0.127
Neg logit contributions
Just-0.074
bes-0.062
Now-0.060
age-0.059
P-0.058
Token.
Token ID13
Feature activation-3.66e-02

Pos logit contributions
 theirs+0.109
rings+0.095
 what+0.094
 are+0.087
 their+0.083
Neg logit contributions
Just-0.124
age-0.117
ager-0.116
oster-0.113
bes-0.112
Token One
Token ID1881
Feature activation+9.35e-01

Pos logit contributions
Just+0.004
age+0.003
P+0.003
ager+0.003
Lu+0.003
Neg logit contributions
 theirs-0.003
rings-0.003
nam-0.002
 wow-0.002
 what-0.002
Token day
Token ID1110
Feature activation-9.06e-01

Pos logit contributions
 theirs+0.098
rings+0.082
 what+0.080
 are+0.077
 wow+0.074
Neg logit contributions
Just-0.080
ager-0.072
age-0.072
bes-0.071
P-0.069
Token,
Token ID11
Feature activation+5.07e-02

Pos logit contributions
Just+0.081
P+0.073
ager+0.073
age+0.072
ivering+0.068
Neg logit contributions
 theirs-0.092
rings-0.079
 what-0.069
nam-0.068
 wow-0.068
Token Sally
Token ID25737
Feature activation+3.51e-01

Pos logit contributions
 theirs+0.004
rings+0.003
 wow+0.003
ours+0.002
 what+0.002
Neg logit contributions
Just-0.006
P-0.005
ager-0.005
eh-0.005
Lu-0.005
Token went
Token ID1816
Feature activation+4.53e-01

Pos logit contributions
 theirs+0.023
 are+0.021
 what+0.020
rings+0.020
 their+0.019
Neg logit contributions
Just-0.039
bes-0.036
age-0.036
oster-0.036
ivering-0.035
Token to
Token ID284
Feature activation+3.39e-01

Pos logit contributions
 theirs+0.036
rings+0.029
 what+0.028
 are+0.025
 their+0.024
Neg logit contributions
Just-0.050
ager-0.047
age-0.047
ivering-0.045
bes-0.045
Token the
Token ID262
Feature activation-2.43e-01

Pos logit contributions
 theirs+0.026
rings+0.023
 wow+0.019
ours+0.018
bars+0.018
Neg logit contributions
Just-0.034
P-0.033
ager-0.032
Lu-0.031
 seek-0.031
Token seeing
Token ID4379
Feature activation-1.87e-01

Pos logit contributions
 theirs+0.041
rings+0.035
 wow+0.030
nam+0.029
 are+0.029
Neg logit contributions
Just-0.050
ager-0.046
age-0.045
P-0.044
bes-0.044
Token all
Token ID477
Feature activation+1.29e+00

Pos logit contributions
Just+0.020
bes+0.019
ze+0.019
zer+0.019
P+0.019
Neg logit contributions
 theirs-0.012
rings-0.010
 wow-0.009
ours-0.008
 are-0.008
Token the
Token ID262
Feature activation-2.82e-01

Pos logit contributions
 theirs+0.086
rings+0.081
 wow+0.070
nam+0.060
ours+0.058
Neg logit contributions
age-0.135
eh-0.134
Just-0.133
ager-0.131
Lu-0.129
Token people
Token ID661
Feature activation-1.83e-01

Pos logit contributions
Just+0.029
age+0.027
ager+0.026
bes+0.026
P+0.025
Neg logit contributions
 theirs-0.026
rings-0.021
 what-0.021
 are-0.019
nam-0.018
Token go
Token ID467
Feature activation+9.86e-01

Pos logit contributions
Just+0.014
age+0.013
ivering+0.013
ager+0.013
bes+0.012
Neg logit contributions
 theirs-0.020
rings-0.017
 wow-0.016
 what-0.015
nam-0.014
Token hungry
Token ID14720
Feature activation-6.33e-01

Pos logit contributions
 theirs+0.094
rings+0.078
 what+0.074
 are+0.069
 their+0.067
Neg logit contributions
Just-0.095
ager-0.088
age-0.088
P-0.084
bes-0.083
Token.
Token ID13
Feature activation+1.29e-01

Pos logit contributions
Just+0.065
age+0.060
ager+0.060
P+0.059
bes+0.057
Neg logit contributions
 theirs-0.057
rings-0.046
 what-0.044
 are-0.042
 their-0.039
Token She
Token ID1375
Feature activation-7.40e-02

Pos logit contributions
 theirs+0.008
rings+0.006
 what+0.006
 are+0.005
 wow+0.005
Neg logit contributions
Just-0.016
ager-0.015
age-0.015
P-0.015
ivering-0.015
Token had
Token ID550
Feature activation-1.81e-01

Pos logit contributions
Just+0.008
age+0.008
ivering+0.008
amas+0.008
bes+0.008
Neg logit contributions
 theirs-0.005
 what-0.004
rings-0.004
 are-0.004
 their-0.004
Token an
Token ID281
Feature activation-3.89e-01

Pos logit contributions
Just+0.020
age+0.019
ager+0.019
P+0.018
bes+0.018
Neg logit contributions
 theirs-0.014
rings-0.012
 what-0.011
 wow-0.010
 are-0.010
Token idea
Token ID2126
Feature activation+5.01e-01

Pos logit contributions
Just+0.040
age+0.038
ager+0.037
P+0.036
bes+0.036
Neg logit contributions
 theirs-0.033
rings-0.028
 what-0.025
 wow-0.024
 are-0.024
Token 3
Token ID513
Feature activation-2.79e-01

Pos logit contributions
Just+0.072
age+0.070
ager+0.069
P+0.063
ivering+0.062
Neg logit contributions
 theirs-0.117
rings-0.103
 what-0.093
nam-0.090
 are-0.090
Token year
Token ID614
Feature activation-9.00e-01

Pos logit contributions
Just+0.017
amas+0.016
ivering+0.014
P+0.014
lor+0.013
Neg logit contributions
 theirs-0.034
 what-0.032
 are-0.029
 their-0.029
 it-0.028
Token old
Token ID1468
Feature activation+1.17e+00

Pos logit contributions
Just+0.094
age+0.088
ager+0.087
P+0.084
bes+0.083
Neg logit contributions
 theirs-0.077
rings-0.064
 what-0.058
 wow-0.055
 are-0.054
Token named
Token ID3706
Feature activation+8.64e-01

Pos logit contributions
 theirs+0.121
rings+0.104
 what+0.097
 wow+0.092
 are+0.092
Neg logit contributions
Just-0.101
age-0.093
ager-0.093
P-0.089
bes-0.088
Token Tommy
Token ID19919
Feature activation+6.45e-01

Pos logit contributions
 theirs+0.060
rings+0.047
 what+0.041
 wow+0.038
 are+0.038
Neg logit contributions
Just-0.104
age-0.098
ager-0.098
P-0.095
bes-0.094
Token wanted
Token ID2227
Feature activation-5.49e-01

Pos logit contributions
 theirs+0.064
rings+0.054
 what+0.050
 wow+0.048
 are+0.047
Neg logit contributions
Just-0.058
age-0.054
ager-0.054
P-0.052
bes-0.051
Token to
Token ID284
Feature activation+3.77e-01

Pos logit contributions
Just+0.049
age+0.046
ager+0.045
P+0.043
sy+0.042
Neg logit contributions
 theirs-0.053
rings-0.046
 wow-0.042
 are-0.040
nam-0.040
Token open
Token ID1280
Feature activation+6.61e-02

Pos logit contributions
 theirs+0.033
rings+0.027
 what+0.024
 wow+0.024
nam+0.023
Neg logit contributions
Just-0.038
age-0.037
ager-0.036
P-0.034
bes-0.033
Token it
Token ID340
Feature activation+2.02e-01

Pos logit contributions
 theirs+0.005
rings+0.004
 wow+0.004
ours+0.004
 are+0.004
Neg logit contributions
Just-0.005
zer-0.005
bes-0.005
ers-0.005
ce-0.005
Token,
Token ID11
Feature activation+1.59e-01

Pos logit contributions
 theirs+0.020
rings+0.017
 what+0.015
 wow+0.015
 are+0.015
Neg logit contributions
Just-0.019
age-0.017
ager-0.017
P-0.016
bes-0.016
Token but
Token ID475
Feature activation-8.92e-01

Pos logit contributions
 theirs+0.018
rings+0.016
ours+0.014
 wow+0.014
angles+0.014
Neg logit contributions
Just-0.012
age-0.010
ager-0.009
sy-0.009
bes-0.009
Token label
Token ID6167
Feature activation+3.00e-01

Pos logit contributions
Just+0.030
age+0.028
ager+0.027
bes+0.026
P+0.026
Neg logit contributions
 theirs-0.029
rings-0.024
 what-0.022
 wow-0.021
 are-0.021
Token that
Token ID326
Feature activation+1.83e-01

Pos logit contributions
 theirs+0.028
rings+0.023
 what+0.021
 wow+0.021
nam+0.020
Neg logit contributions
Just-0.028
age-0.027
ager-0.026
P-0.025
bes-0.025
Token said
Token ID531
Feature activation-2.48e-01

Pos logit contributions
 theirs+0.017
rings+0.014
 what+0.013
 wow+0.013
nam+0.012
Neg logit contributions
Just-0.017
ager-0.015
age-0.015
P-0.015
bes-0.015
Token "
Token ID366
Feature activation-2.89e-01

Pos logit contributions
Just+0.021
age+0.020
bes+0.018
ager+0.018
ze+0.018
Neg logit contributions
 theirs-0.024
rings-0.020
nam-0.020
 ours-0.018
angles-0.017
Tokendel
Token ID12381
Feature activation-1.52e+00

Pos logit contributions
Just+0.022
ager+0.021
age+0.020
ivering+0.019
bes+0.019
Neg logit contributions
 theirs-0.032
rings-0.029
 what-0.026
 are-0.025
nam-0.025
Tokeniver
Token ID1428
Feature activation-2.92e+00

Pos logit contributions
Just+0.095
ager+0.091
bes+0.088
P+0.085
age+0.083
Neg logit contributions
 theirs-0.177
rings-0.157
 what-0.142
 are-0.141
angles-0.137
Token to
Token ID284
Feature activation+3.32e-01

Pos logit contributions
Just+0.233
ager+0.206
P+0.198
bes+0.195
age+0.192
Neg logit contributions
 theirs-0.332
 what-0.286
rings-0.282
 are-0.274
 wow-0.257
Token Mr
Token ID1770
Feature activation+1.72e+00

Pos logit contributions
 theirs+0.030
rings+0.025
 what+0.022
 wow+0.022
 are+0.021
Neg logit contributions
Just-0.033
age-0.031
ager-0.030
P-0.029
bes-0.029
Token.
Token ID13
Feature activation+3.70e-01

Pos logit contributions
 theirs+0.161
rings+0.136
 what+0.126
 are+0.118
 wow+0.115
Neg logit contributions
Just-0.169
ager-0.155
age-0.155
P-0.149
bes-0.148
Token Smith
Token ID4176
Feature activation-7.58e-01

Pos logit contributions
 theirs+0.031
rings+0.027
 what+0.025
 wow+0.023
 are+0.023
Neg logit contributions
Just-0.039
ager-0.037
age-0.036
P-0.036
ivering-0.035
Token".
Token ID1911
Feature activation+5.12e-01

Pos logit contributions
Just+0.057
age+0.051
ager+0.051
P+0.049
bes+0.048
Neg logit contributions
 theirs-0.087
rings-0.076
 what-0.072
 are-0.069
 wow-0.068
Token Then
Token ID3244
Feature activation-5.80e-01

Pos logit contributions
Just+0.052
age+0.049
ager+0.048
P+0.047
bes+0.046
Neg logit contributions
 theirs-0.037
rings-0.030
 what-0.027
 wow-0.025
 are-0.025
Token she
Token ID673
Feature activation-6.76e-01

Pos logit contributions
Just+0.069
age+0.065
ager+0.065
P+0.064
bes+0.062
Neg logit contributions
 theirs-0.040
rings-0.031
 what-0.025
nam-0.025
 wow-0.024
Token went
Token ID1816
Feature activation+4.83e-01

Pos logit contributions
Just+0.066
age+0.061
ager+0.061
P+0.059
bes+0.058
Neg logit contributions
 theirs-0.061
rings-0.052
 what-0.049
 are-0.046
 wow-0.046
Token to
Token ID284
Feature activation+1.85e-02

Pos logit contributions
 theirs+0.041
rings+0.034
 what+0.033
 their+0.029
 wow+0.028
Neg logit contributions
Just-0.051
ager-0.049
age-0.047
P-0.046
ivering-0.046
Token the
Token ID262
Feature activation-3.36e-01

Pos logit contributions
 theirs+0.001
rings+0.001
 wow+0.001
nam+0.001
ours+0.001
Neg logit contributions
Just-0.002
age-0.002
ager-0.002
bes-0.002
P-0.002
Token kitchen
Token ID9592
Feature activation-2.20e+00

Pos logit contributions
Just+0.029
ager+0.027
age+0.026
ivering+0.025
bes+0.025
Neg logit contributions
 theirs-0.033
rings-0.030
 what-0.029
 are-0.027
 wow-0.027
Token to
Token ID284
Feature activation+1.50e-01

Pos logit contributions
Just+0.220
P+0.208
age+0.207
ager+0.206
oster+0.200
Neg logit contributions
 theirs-0.196
rings-0.163
 what-0.160
 their-0.146
 are-0.146
Token get
Token ID651
Feature activation+9.82e-03

Pos logit contributions
 theirs+0.012
rings+0.011
 wow+0.009
 what+0.008
nam+0.008
Neg logit contributions
Just-0.016
age-0.015
ager-0.015
P-0.014
bes-0.014
Token a
Token ID257
Feature activation-1.17e-01

Pos logit contributions
 theirs+0.001
rings+0.001
 wow+0.001
 are+0.001
angles+0.001
Neg logit contributions
Just-0.001
P-0.001
sy-0.001
age-0.001
ager-0.001
Token snack
Token ID26906
Feature activation-4.95e-01

Pos logit contributions
Just+0.011
age+0.010
ager+0.010
P+0.010
sy+0.009
Neg logit contributions
 theirs-0.011
rings-0.010
 what-0.008
nam-0.008
 wow-0.008
Token.
Token ID13
Feature activation-2.00e-01

Pos logit contributions
Just+0.053
ager+0.049
age+0.047
ivering+0.047
P+0.047
Neg logit contributions
 theirs-0.042
rings-0.035
 what-0.032
 are-0.032
 their-0.029
Token They
Token ID1119
Feature activation-3.26e-01

Pos logit contributions
Just+0.027
ager+0.024
age+0.024
bes+0.023
P+0.023
Neg logit contributions
 theirs-0.018
rings-0.016
nam-0.014
 wow-0.013
 what-0.013
Token could
Token ID714
Feature activation+3.71e-01

Pos logit contributions
Just+0.029
ager+0.027
age+0.026
P+0.026
bes+0.026
Neg logit contributions
 theirs-0.032
rings-0.027
 wow-0.024
 what-0.023
ours-0.023
Token see
Token ID766
Feature activation+6.00e-01

Pos logit contributions
 theirs+0.038
rings+0.035
nam+0.031
 wow+0.030
ours+0.030
Neg logit contributions
Just-0.030
age-0.027
ager-0.026
bes-0.026
ze-0.025
Token it
Token ID340
Feature activation-1.15e-01

Pos logit contributions
rings+0.040
 theirs+0.039
nam+0.034
 wow+0.029
bars+0.029
Neg logit contributions
ers-0.055
fire-0.055
zer-0.055
ze-0.055
Just-0.055
Token sailing
Token ID28499
Feature activation+1.01e+00

Pos logit contributions
Just+0.009
age+0.008
ze+0.008
ager+0.008
fire+0.008
Neg logit contributions
 theirs-0.012
rings-0.011
nam-0.011
 wow-0.009
ours-0.009
Token away
Token ID1497
Feature activation-2.23e+00

Pos logit contributions
 theirs+0.100
rings+0.091
 what+0.080
 wow+0.079
nam+0.078
Neg logit contributions
Just-0.085
age-0.080
ager-0.079
P-0.075
bes-0.074
Token in
Token ID287
Feature activation-7.33e-01

Pos logit contributions
Just+0.197
age+0.181
ager+0.181
P+0.173
bes+0.172
Neg logit contributions
 theirs-0.224
rings-0.193
 what-0.176
 wow-0.171
 are-0.167
Token the
Token ID262
Feature activation-3.60e-01

Pos logit contributions
Just+0.082
P+0.078
bes+0.078
ager+0.077
fire+0.076
Neg logit contributions
 theirs-0.046
rings-0.045
 wow-0.034
ours-0.032
nam-0.030
Token distance
Token ID5253
Feature activation+1.27e+00

Pos logit contributions
Just+0.038
age+0.035
ager+0.035
P+0.034
bes+0.034
Neg logit contributions
 theirs-0.031
rings-0.025
 what-0.023
 are-0.022
 wow-0.022
Token.
Token ID13
Feature activation-2.44e-01

Pos logit contributions
 theirs+0.128
rings+0.110
 what+0.100
 wow+0.098
nam+0.097
Neg logit contributions
Just-0.110
age-0.102
ager-0.101
P-0.095
bes-0.095
Token They
Token ID1119
Feature activation-3.47e-01

Pos logit contributions
Just+0.023
ager+0.020
age+0.020
P+0.019
bes+0.019
Neg logit contributions
 theirs-0.024
rings-0.021
nam-0.019
 wow-0.018
 what-0.018
Token and
Token ID290
Feature activation-3.23e-01

Pos logit contributions
Just+0.206
ager+0.195
age+0.194
P+0.187
bes+0.183
Neg logit contributions
 theirs-0.226
rings-0.189
 what-0.184
 are-0.171
 wow-0.166
Token said
Token ID531
Feature activation-4.03e-01

Pos logit contributions
Just+0.031
age+0.028
ager+0.028
P+0.027
bes+0.027
Neg logit contributions
 theirs-0.031
rings-0.026
 what-0.022
 wow-0.022
 are-0.021
Token,
Token ID11
Feature activation+2.74e-02

Pos logit contributions
Just+0.030
age+0.027
P+0.025
ze+0.025
ager+0.024
Neg logit contributions
 theirs-0.045
rings-0.039
nam-0.036
 ours-0.035
angles-0.034
Token "
Token ID366
Feature activation-3.12e-01

Pos logit contributions
 theirs+0.002
rings+0.002
 what+0.002
 wow+0.002
 are+0.002
Neg logit contributions
Just-0.003
age-0.003
ager-0.003
P-0.003
bes-0.003
TokenGo
Token ID5247
Feature activation+4.52e-01

Pos logit contributions
sy+0.027
age+0.027
ager+0.026
amas+0.026
bes+0.025
Neg logit contributions
 theirs-0.026
rings-0.024
 are-0.023
 Tom-0.021
 what-0.021
Token away
Token ID1497
Feature activation-2.22e+00

Pos logit contributions
 theirs+0.038
 what+0.035
 are+0.033
 look+0.031
 their+0.030
Neg logit contributions
Just-0.044
bes-0.044
amas-0.040
ager-0.040
rd-0.040
Token!
Token ID0
Feature activation-1.57e-01

Pos logit contributions
Just+0.287
age+0.266
ager+0.264
P+0.261
bes+0.259
Neg logit contributions
 theirs-0.134
 what-0.131
 are-0.114
 their-0.105
 Tom-0.102
Token Anna
Token ID11735
Feature activation-2.60e-01

Pos logit contributions
Just+0.015
age+0.014
ager+0.014
P+0.013
bes+0.013
Neg logit contributions
 theirs-0.015
rings-0.013
 what-0.012
 wow-0.011
 are-0.011
Token is
Token ID318
Feature activation+4.74e-01

Pos logit contributions
Just+0.029
age+0.026
P+0.026
ager+0.026
bes+0.025
Neg logit contributions
 theirs-0.020
 are-0.018
 what-0.017
rings-0.016
 their-0.014
Token mine
Token ID6164
Feature activation-1.22e+00

Pos logit contributions
 theirs+0.042
rings+0.035
 what+0.032
 wow+0.030
 are+0.030
Neg logit contributions
Just-0.048
age-0.045
ager-0.045
P-0.043
bes-0.043
Token now
Token ID783
Feature activation-7.08e-01

Pos logit contributions
Just+0.114
age+0.111
P+0.109
ager+0.107
oster+0.105
Neg logit contributions
 theirs-0.116
 what-0.099
rings-0.095
 are-0.094
 wow-0.086
Token!"
Token ID2474
Feature activation-1.17e+00

Pos logit contributions
 theirs+0.128
rings+0.106
 what+0.101
 are+0.099
 wow+0.092
Neg logit contributions
Just-0.155
ager-0.144
age-0.143
P-0.141
bes-0.139
Token Anna
Token ID11735
Feature activation-6.36e-01

Pos logit contributions
Just+0.144
ager+0.139
age+0.138
ivering+0.134
bes+0.133
Neg logit contributions
 theirs-0.075
rings-0.058
 what-0.053
 are-0.048
 wow-0.047
Token said
Token ID531
Feature activation-4.26e-01

Pos logit contributions
Just+0.072
age+0.068
ager+0.067
P+0.066
bes+0.065
Neg logit contributions
 theirs-0.048
rings-0.039
 what-0.035
 wow-0.033
 are-0.033
Token.
Token ID13
Feature activation-4.72e-01

Pos logit contributions
Just+0.039
age+0.036
ager+0.035
P+0.034
bes+0.034
Neg logit contributions
 theirs-0.042
rings-0.036
 what-0.033
 wow-0.031
 are-0.031
Token "
Token ID366
Feature activation-5.63e-01

Pos logit contributions
Just+0.049
age+0.045
ager+0.044
P+0.044
bes+0.043
Neg logit contributions
 theirs-0.041
rings-0.034
 what-0.031
 wow-0.029
 are-0.029
TokenBut
Token ID1537
Feature activation-2.32e+00

Pos logit contributions
Just+0.041
age+0.039
ager+0.039
ivering+0.038
bes+0.038
Neg logit contributions
 theirs-0.062
rings-0.054
 what-0.050
 are-0.049
 wow-0.049
Token can
Token ID460
Feature activation+7.29e-01

Pos logit contributions
Just+0.234
ager+0.209
age+0.208
P+0.207
bes+0.207
Neg logit contributions
 theirs-0.199
rings-0.161
nam-0.131
 wow-0.123
 what-0.120
Token you
Token ID345
Feature activation-2.91e-01

Pos logit contributions
 theirs+0.071
rings+0.057
 wow+0.051
 what+0.051
nam+0.048
Neg logit contributions
Just-0.068
age-0.062
bes-0.061
P-0.060
ager-0.060
Token number
Token ID1271
Feature activation-1.13e+00

Pos logit contributions
Just+0.035
ager+0.033
age+0.032
bes+0.032
P+0.032
Neg logit contributions
 theirs-0.020
rings-0.016
 what-0.015
 are-0.015
 wow-0.013
Token the
Token ID262
Feature activation-4.38e-01

Pos logit contributions
Just+0.115
co+0.105
P+0.105
age+0.103
ce+0.103
Neg logit contributions
 theirs-0.088
rings-0.067
 wow-0.062
nam-0.056
 maybe-0.052
Token flowers
Token ID12734
Feature activation-9.08e-02

Pos logit contributions
Just+0.043
ager+0.040
age+0.040
P+0.038
bes+0.038
Neg logit contributions
 theirs-0.040
rings-0.034
 what-0.031
 are-0.029
 wow-0.029