TOP ACTIVATIONS
MAX = 6.813

voice , but John smiled anyways . He â
down side - by - side . They were having so
hesitated but walked towards him anyways . The farmer offered the
but Julie wasn 't sad anymore . She slowly walked back
with them not being friends anymore . <|endoftext|> Once upon a
â t Tuesday anymore ! It was Wednesday !
his hunger began to sub side . When the
â t run anymore . Then he stopped .
but she followed her parents anyway . She threw the salt
him not to be upset anymore . Tim my was happy
But his friends found him anyways . They
together side - by - side . No
and refused to be miserable anymore . The
t have to be scared anymore . But Daisy
didn 't want to wait anymore ! But
play side - by - side with the infant . They
her too and thanked her too . Jack and
t feel so alone anymore . He â
and decided to take Max anyway . They
, but he followed Lily anyway . When they got to

MIN ACTIVATIONS
MIN = -13.113

that said " No T resp assing ". But Lily was
that said " No T resp assing ". "
that said " No T resp assing " and " Private
that said " No T resp assing ". And behind the
a strange , raspberry - col oured object hiding under a
, he saw a red rad ish in the garden .
, Benny saw a big rad ish and he wanted to
pond . It was a tort oise ! The all igator
day , a chocolate - col oured whip named C heddar
Lucy noticed the weather was uncom fort ably hot . She
my ! I saw an ostr ich in our backyard !"
saw a big , red rad ish . He wanted to
suddenly , a brightly - col oured belt caught her eye
spotted a big , brown rad ish . Benny loved rad
sudden , she saw a rad ish ! She was really
legs . It is an ostr ich . "
, she found a big rad ish in her garden and
Spot was a very lovely po och and he always tried
the zoo and saw an ostr ich . It was so
burger with fries and a mil ksh ake . But after

INTERVAL 1.832 - 6.813
CONTAINS 14.407%

watched as they baked until they were golden . When they
He smiled and carefully brought it down . When
and had stripes all over his body . Jack wanted to
had never seen before . â
in the town were scared when they saw the tank .

INTERVAL -3.150 - 1.832
CONTAINS 79.831%

." Mom said . They closed the book and
Annie . She loved going to the beach , playing with
The fox worked hard , and when he was done ,
" L ila , you know you are not allowed
bright light shone ! She was so surprised that she jumped

INTERVAL -8.131 - -3.150
CONTAINS 5.721%

smiled and said , " L ily , I think that
magic word ." " Let 's try ," Ben
, " You are welcome , animals ! I love you
She got her rain coat and boots ready .
said , We need to find

INTERVAL -13.113 - -8.131
CONTAINS 0.041%

and started eating the ch ocol ates . The shop keeper
and tw inkle . The par rot felt peaceful while it
But then one of the se ag ull s suddenly became
, " That is an aer opl ane ! It 's
an orange rope to the kay ak for him . His
Token voice
Token ID3809
Feature activation+2.14e+00

Pos logit contributions
izing+0.042
ning+0.040
king+0.040
bul+0.039
ening+0.039
Neg logit contributions
 am-0.025
 done-0.021
-0.021
-0.021
'm-0.019
Token,
Token ID11
Feature activation-2.14e+00

Pos logit contributions
 am+0.021
 done+0.018
+0.017
 story+0.016
 big+0.015
Neg logit contributions
izing-0.073
ning-0.071
king-0.070
yles-0.070
rily-0.069
Token but
Token ID475
Feature activation-9.01e-02

Pos logit contributions
izing+0.061
yles+0.059
ning+0.058
ellery+0.058
rily+0.057
Neg logit contributions
 am-0.033
-0.031
 done-0.030
 big-0.028
 story-0.028
Token John
Token ID1757
Feature activation+3.00e-01

Pos logit contributions
izing+0.003
yles+0.002
ning+0.002
king+0.002
ellery+0.002
Neg logit contributions
 am-0.001
 done-0.001
-0.001
 story-0.001
 big-0.001
Token smiled
Token ID13541
Feature activation+2.19e+00

Pos logit contributions
 am+0.003
 done+0.003
+0.003
 story+0.003
 big+0.003
Neg logit contributions
izing-0.010
yles-0.010
ning-0.010
king-0.009
ellery-0.009
Token anyways
Token ID32845
Feature activation+5.98e+00

Pos logit contributions
 am+0.025
 done+0.022
 story+0.019
+0.018
 bad+0.016
Neg logit contributions
izing-0.072
king-0.071
rily-0.071
ning-0.071
bing-0.069
Token.
Token ID13
Feature activation+2.61e+00

Pos logit contributions
 am+0.072
 done+0.055
ossible+0.054
+0.053
 met+0.052
Neg logit contributions
izing-0.187
rily-0.178
king-0.173
ning-0.171
bing-0.170
Token He
Token ID679
Feature activation+2.01e+00

Pos logit contributions
 am+0.027
 done+0.025
 bad+0.022
 story+0.021
 big+0.020
Neg logit contributions
izing-0.084
yles-0.083
ning-0.082
rily-0.080
shadow-0.079
Tokenâ
Token ID22940
Feature activation-3.23e+00

Pos logit contributions
 am+0.023
 done+0.020
+0.020
 story+0.019
 big+0.017
Neg logit contributions
izing-0.064
ning-0.062
yles-0.062
king-0.061
ellery-0.061
Token
Token ID26391
Feature activation+6.11e-01

Pos logit contributions
izing+0.071
ning+0.067
king+0.066
yles+0.066
ellery+0.064
Neg logit contributions
 am-0.071
-0.066
 done-0.066
 big-0.065
 story-0.065
Token
Token ID8151
Feature activation-1.72e-01

Pos logit contributions
 am+0.007
 done+0.006
 bad+0.006
 story+0.006
 big+0.006
Neg logit contributions
yles-0.019
izing-0.019
ning-0.018
king-0.018
ellery-0.018
Token down
Token ID866
Feature activation+1.24e+00

Pos logit contributions
izing+0.052
ning+0.051
king+0.050
yles+0.050
rily+0.050
Neg logit contributions
 am-0.039
 story-0.036
 done-0.036
-0.034
 big-0.033
Token side
Token ID1735
Feature activation+1.94e+00

Pos logit contributions
 am+0.017
 done+0.016
 story+0.015
+0.014
 bad+0.013
Neg logit contributions
izing-0.037
ning-0.036
rily-0.035
king-0.035
yles-0.035
Token-
Token ID12
Feature activation-5.09e+00

Pos logit contributions
 am+0.014
 done+0.011
+0.010
 story+0.009
 big+0.008
Neg logit contributions
izing-0.071
yles-0.069
ning-0.069
king-0.069
rily-0.068
Tokenby
Token ID1525
Feature activation+2.85e+00

Pos logit contributions
izing+0.117
rily+0.110
yles+0.110
ning+0.107
ellery+0.107
Neg logit contributions
 am-0.108
-0.105
 done-0.103
 to-0.099
 big-0.094
Token-
Token ID12
Feature activation-5.10e+00

Pos logit contributions
 am+0.040
 done+0.034
+0.033
 story+0.032
 bad+0.030
Neg logit contributions
izing-0.085
king-0.083
yles-0.082
ning-0.082
rily-0.081
Tokenside
Token ID1589
Feature activation+5.97e+00

Pos logit contributions
izing+0.116
rily+0.109
yles+0.109
ning+0.106
ellery+0.105
Neg logit contributions
 am-0.109
-0.106
 done-0.105
 to-0.101
 big-0.096
Token.
Token ID13
Feature activation+1.75e+00

Pos logit contributions
 am+0.069
 done+0.048
 story+0.043
'm+0.043
+0.041
Neg logit contributions
izing-0.204
rily-0.191
bing-0.191
king-0.190
ning-0.188
Token They
Token ID1119
Feature activation+1.71e+00

Pos logit contributions
 am+0.021
 done+0.020
 story+0.017
 bad+0.016
 big+0.016
Neg logit contributions
yles-0.055
izing-0.054
ning-0.053
king-0.053
rily-0.053
Token were
Token ID547
Feature activation+5.55e-01

Pos logit contributions
 am+0.020
+0.017
 done+0.017
 story+0.017
 big+0.015
Neg logit contributions
izing-0.054
yles-0.053
ning-0.052
king-0.052
ellery-0.051
Token having
Token ID1719
Feature activation+2.20e+00

Pos logit contributions
 am+0.007
 done+0.007
+0.007
 big+0.006
 story+0.006
Neg logit contributions
izing-0.017
yles-0.017
ning-0.016
ellery-0.016
king-0.016
Token so
Token ID523
Feature activation+1.05e+00

Pos logit contributions
 am+0.038
 story+0.032
 done+0.031
+0.030
 own+0.028
Neg logit contributions
yles-0.054
izing-0.054
ning-0.053
ellery-0.052
rily-0.051
Token hesitated
Token ID41723
Feature activation+2.18e+00

Pos logit contributions
izing+0.029
yles+0.028
ning+0.028
king+0.028
ellery+0.028
Neg logit contributions
 am-0.011
 done-0.010
-0.010
 story-0.009
 big-0.009
Token but
Token ID475
Feature activation+9.39e-01

Pos logit contributions
 am+0.036
 done+0.031
 story+0.030
ossible+0.028
+0.027
Neg logit contributions
izing-0.060
king-0.059
rily-0.058
bing-0.056
ning-0.055
Token walked
Token ID6807
Feature activation-4.83e-01

Pos logit contributions
 am+0.018
 done+0.016
+0.016
 story+0.016
 big+0.015
Neg logit contributions
izing-0.024
yles-0.023
ning-0.023
king-0.022
ellery-0.022
Token towards
Token ID3371
Feature activation+8.99e-01

Pos logit contributions
izing+0.012
king+0.012
rily+0.011
ning+0.011
bing+0.011
Neg logit contributions
 am-0.010
 done-0.009
 story-0.009
-0.008
ossible-0.008
Token him
Token ID683
Feature activation+2.83e+00

Pos logit contributions
 am+0.013
 done+0.011
+0.011
 story+0.011
 big+0.010
Neg logit contributions
izing-0.027
yles-0.026
ning-0.026
king-0.025
rily-0.025
Token anyways
Token ID32845
Feature activation+5.91e+00

Pos logit contributions
 am+0.028
 done+0.024
+0.021
 story+0.021
 big+0.019
Neg logit contributions
izing-0.096
ning-0.093
king-0.093
rily-0.092
bing-0.091
Token.
Token ID13
Feature activation+1.76e+00

Pos logit contributions
 am+0.066
 done+0.055
ossible+0.047
+0.045
 story+0.044
Neg logit contributions
izing-0.191
rily-0.184
king-0.178
ning-0.178
ants-0.177
Token The
Token ID383
Feature activation-9.06e-01

Pos logit contributions
 am+0.021
 done+0.019
 story+0.017
 bad+0.016
 big+0.016
Neg logit contributions
izing-0.056
yles-0.054
ning-0.054
rily-0.054
king-0.053
Token farmer
Token ID18739
Feature activation-4.23e-01

Pos logit contributions
izing+0.024
yles+0.024
rily+0.023
ellery+0.023
ning+0.023
Neg logit contributions
 am-0.016
-0.015
 done-0.015
 big-0.014
 story-0.014
Token offered
Token ID4438
Feature activation-6.94e-01

Pos logit contributions
izing+0.013
yles+0.013
ellery+0.013
ning+0.013
rily+0.013
Neg logit contributions
 am-0.005
 done-0.005
-0.005
 to-0.005
 story-0.005
Token the
Token ID262
Feature activation-1.03e+00

Pos logit contributions
izing+0.019
ning+0.019
king+0.019
yles+0.019
rily+0.019
Neg logit contributions
 am-0.011
 done-0.010
 story-0.009
-0.009
 big-0.008
Token but
Token ID475
Feature activation+8.65e-01

Pos logit contributions
 am+0.023
 story+0.021
 done+0.020
ossible+0.020
+0.019
Neg logit contributions
izing-0.046
king-0.043
rily-0.043
bing-0.042
ning-0.042
Token Julie
Token ID21946
Feature activation+1.55e-01

Pos logit contributions
 am+0.013
 done+0.012
 story+0.012
+0.012
 big+0.011
Neg logit contributions
izing-0.025
yles-0.023
ning-0.023
rily-0.023
bing-0.023
Token wasn
Token ID2492
Feature activation-2.23e-01

Pos logit contributions
 am+0.001
 done+0.001
+0.001
 story+0.001
 big+0.001
Neg logit contributions
izing-0.005
yles-0.005
ning-0.005
king-0.005
rily-0.005
Token't
Token ID470
Feature activation+1.20e+00

Pos logit contributions
izing+0.006
yles+0.006
ning+0.006
king+0.006
ellery+0.006
Neg logit contributions
 am-0.004
 done-0.003
-0.003
 story-0.003
 big-0.003
Token sad
Token ID6507
Feature activation+2.89e+00

Pos logit contributions
 am+0.020
 story+0.017
+0.017
 done+0.017
ossible+0.015
Neg logit contributions
izing-0.032
yles-0.032
king-0.031
ning-0.031
rily-0.031
Token anymore
Token ID7471
Feature activation+5.78e+00

Pos logit contributions
 am+0.057
ossible+0.053
 done+0.053
 story+0.049
+0.048
Neg logit contributions
izing-0.071
king-0.064
ellery-0.063
yles-0.063
ning-0.063
Token.
Token ID13
Feature activation+1.70e+00

Pos logit contributions
 am+0.045
 done+0.038
+0.030
 story+0.029
 big+0.028
Neg logit contributions
izing-0.209
yles-0.201
king-0.199
ellery-0.198
ning-0.198
Token She
Token ID1375
Feature activation+2.13e+00

Pos logit contributions
 am+0.025
 done+0.025
 story+0.022
 bad+0.022
 big+0.021
Neg logit contributions
izing-0.049
yles-0.047
ning-0.047
rily-0.046
ellery-0.046
Token slowly
Token ID6364
Feature activation+1.21e+00

Pos logit contributions
 am+0.024
 done+0.021
+0.021
 story+0.020
 big+0.019
Neg logit contributions
izing-0.069
yles-0.067
ning-0.066
king-0.066
ellery-0.065
Token walked
Token ID6807
Feature activation-9.51e-01

Pos logit contributions
 am+0.019
 done+0.018
+0.018
 to+0.017
 big+0.017
Neg logit contributions
izing-0.034
yles-0.033
ning-0.032
rily-0.032
ellery-0.032
Token back
Token ID736
Feature activation+2.62e+00

Pos logit contributions
izing+0.026
king+0.026
rily+0.026
ning+0.025
bing+0.025
Neg logit contributions
 am-0.016
 done-0.014
 story-0.014
-0.012
 bad-0.012
Token with
Token ID351
Feature activation-1.37e+00

Pos logit contributions
izing+0.014
yles+0.013
ning+0.013
king+0.013
bing+0.013
Neg logit contributions
 am-0.010
 done-0.010
-0.009
 story-0.009
 big-0.009
Token them
Token ID606
Feature activation+3.53e+00

Pos logit contributions
izing+0.041
yles+0.041
ellery+0.040
ning+0.039
king+0.039
Neg logit contributions
 am-0.019
 done-0.016
-0.016
 story-0.016
 to-0.014
Token not
Token ID407
Feature activation-5.83e-01

Pos logit contributions
 am+0.054
 story+0.044
+0.044
+0.044
 done+0.042
Neg logit contributions
izing-0.098
king-0.096
ning-0.092
yles-0.091
bing-0.091
Token being
Token ID852
Feature activation-9.28e-01

Pos logit contributions
izing+0.013
yles+0.013
ning+0.012
rily+0.012
king+0.012
Neg logit contributions
 am-0.012
 done-0.012
-0.012
 to-0.011
 big-0.011
Token friends
Token ID2460
Feature activation+1.76e+00

Pos logit contributions
izing+0.027
yles+0.027
ning+0.026
rily+0.026
ellery+0.026
Neg logit contributions
 am-0.013
 done-0.013
-0.012
 big-0.012
 to-0.012
Token anymore
Token ID7471
Feature activation+5.77e+00

Pos logit contributions
 am+0.031
 done+0.029
 story+0.028
+0.028
 big+0.027
Neg logit contributions
izing-0.045
yles-0.043
king-0.043
ning-0.043
ellery-0.042
Token.
Token ID13
Feature activation+2.17e+00

Pos logit contributions
 am+0.059
 done+0.050
 story+0.047
ossible+0.046
 big+0.046
Neg logit contributions
izing-0.185
yles-0.176
king-0.175
bing-0.175
ning-0.171
Token<|endoftext|>
Token ID50256
Feature activation+3.27e+00

Pos logit contributions
 am+0.023
 done+0.022
 story+0.017
 bad+0.016
 big+0.015
Neg logit contributions
yles-0.068
izing-0.066
ellery-0.065
ksh-0.064
rily-0.064
TokenOnce
Token ID7454
Feature activation+3.07e+00

Pos logit contributions
 done+0.037
 am+0.032
 bad+0.031
 own+0.027
 tum+0.027
Neg logit contributions
yles-0.094
ning-0.092
med-0.091
etti-0.089
rily-0.088
Token upon
Token ID2402
Feature activation+2.30e+00

Pos logit contributions
 am+0.044
 done+0.038
 consequences+0.037
 learned+0.036
 care+0.033
Neg logit contributions
yles-0.078
ants-0.074
rily-0.073
izing-0.072
ang-0.071
Token a
Token ID257
Feature activation+1.12e+00

Pos logit contributions
 am+0.030
 done+0.029
 story+0.025
 way+0.023
 bad+0.022
Neg logit contributions
yles-0.064
izing-0.063
rily-0.061
king-0.061
ellery-0.061
Tokenâ
Token ID22940
Feature activation-3.31e+00

Pos logit contributions
izing+0.035
yles+0.033
ning+0.033
king+0.033
ellery+0.033
Neg logit contributions
 am-0.021
-0.020
 done-0.020
 story-0.018
 big-0.018
Token
Token ID26391
Feature activation-1.01e+00

Pos logit contributions
izing+0.081
ning+0.076
king+0.076
yles+0.074
bing+0.074
Neg logit contributions
 am-0.063
 big-0.059
 done-0.059
-0.058
 story-0.057
Token
Token ID8151
Feature activation-1.54e+00

Pos logit contributions
izing+0.020
yles+0.019
ning+0.019
king+0.019
ellery+0.018
Neg logit contributions
 am-0.024
 done-0.023
-0.022
 story-0.022
 big-0.021
Tokent
Token ID83
Feature activation+6.07e-01

Pos logit contributions
izing+0.053
yles+0.051
ning+0.050
ellery+0.050
king+0.050
Neg logit contributions
 am-0.015
 done-0.013
-0.013
 story-0.012
 big-0.011
Token Tuesday
Token ID3431
Feature activation+2.41e+00

Pos logit contributions
 am+0.009
+0.008
 done+0.008
 story+0.008
 big+0.007
Neg logit contributions
izing-0.017
yles-0.017
ning-0.017
king-0.017
rily-0.016
Token anymore
Token ID7471
Feature activation+5.72e+00

Pos logit contributions
 am+0.024
 done+0.019
+0.018
 story+0.017
 big+0.017
Neg logit contributions
izing-0.082
ning-0.080
king-0.077
yles-0.077
ting-0.076
Token!
Token ID0
Feature activation+2.82e+00

Pos logit contributions
 am+0.052
 done+0.046
 story+0.038
+0.037
 big+0.037
Neg logit contributions
izing-0.198
ning-0.188
yles-0.188
king-0.187
rily-0.185
Token It
Token ID632
Feature activation+8.78e-01

Pos logit contributions
 done+0.014
 am+0.013
 story+0.010
 bad+0.008
 big+0.007
Neg logit contributions
izing-0.106
yles-0.104
ning-0.103
rily-0.101
king-0.100
Token was
Token ID373
Feature activation+2.67e-01

Pos logit contributions
 am+0.006
 done+0.006
+0.005
 story+0.005
ossible+0.005
Neg logit contributions
izing-0.031
ning-0.030
yles-0.029
bul-0.029
bing-0.028
Token Wednesday
Token ID3583
Feature activation+2.12e+00

Pos logit contributions
 am+0.004
+0.003
 story+0.003
 done+0.003
ossible+0.003
Neg logit contributions
izing-0.008
ning-0.008
yles-0.008
rily-0.008
ellery-0.008
Token!
Token ID0
Feature activation+2.46e+00

Pos logit contributions
 am+0.028
 done+0.024
+0.023
 story+0.022
 big+0.021
Neg logit contributions
izing-0.066
ning-0.064
king-0.062
yles-0.062
rily-0.062
Token his
Token ID465
Feature activation+2.56e+00

Pos logit contributions
izing+0.055
bing+0.052
yles+0.052
ning+0.051
rily+0.051
Neg logit contributions
 am-0.035
 story-0.032
-0.029
 done-0.029
ossible-0.028
Token hunger
Token ID16460
Feature activation+1.52e+00

Pos logit contributions
 am+0.047
 done+0.043
+0.043
+0.040
ossible+0.038
Neg logit contributions
izing-0.062
ning-0.059
burn-0.059
rily-0.059
bing-0.059
Token began
Token ID2540
Feature activation+2.94e+00

Pos logit contributions
 am+0.019
+0.017
ossible+0.016
 story+0.016
 done+0.016
Neg logit contributions
izing-0.047
rily-0.044
ning-0.044
king-0.044
bing-0.043
Token to
Token ID284
Feature activation-1.58e-01

Pos logit contributions
 am+0.026
 done+0.019
+0.016
 story+0.016
ossible+0.015
Neg logit contributions
ning-0.102
izing-0.100
king-0.100
bing-0.098
rily-0.098
Token sub
Token ID850
Feature activation-2.99e+00

Pos logit contributions
izing+0.004
ning+0.004
burn+0.004
rily+0.004
king+0.004
Neg logit contributions
 am-0.003
 done-0.003
-0.003
 story-0.002
 to-0.002
Tokenside
Token ID1589
Feature activation+5.72e+00

Pos logit contributions
izing+0.078
yles+0.078
ants+0.076
ellery+0.075
ning+0.075
Neg logit contributions
-0.051
 am-0.048
 done-0.047
 to-0.045
 big-0.044
Token.
Token ID13
Feature activation+2.13e+00

Pos logit contributions
 am+0.062
 done+0.046
ossible+0.040
+0.039
+0.038
Neg logit contributions
izing-0.196
bing-0.185
ning-0.184
rily-0.184
king-0.184
Token
Token ID198
Feature activation+1.14e+00

Pos logit contributions
 am+0.021
 done+0.018
 story+0.016
 bad+0.014
 big+0.014
Neg logit contributions
izing-0.073
yles-0.071
ning-0.071
rily-0.070
king-0.069
Token
Token ID198
Feature activation-1.21e+00

Pos logit contributions
 am+0.007
 done+0.007
 bad+0.005
 story+0.004
 way+0.004
Neg logit contributions
izing-0.041
yles-0.040
ants-0.040
rily-0.040
bing-0.040
TokenWhen
Token ID2215
Feature activation+1.53e+00

Pos logit contributions
yles+0.033
ning+0.032
ellery+0.032
izing+0.032
ries+0.032
Neg logit contributions
-0.021
 am-0.021
 big-0.019
 done-0.019
 story-0.019
Token the
Token ID262
Feature activation+2.09e-01

Pos logit contributions
 am+0.024
 done+0.021
 story+0.020
+0.020
 own+0.019
Neg logit contributions
izing-0.042
ning-0.040
yles-0.040
rily-0.039
bing-0.038
Tokenâ
Token ID22940
Feature activation-4.37e+00

Pos logit contributions
 am+0.043
 done+0.043
 story+0.040
+0.039
 big+0.038
Neg logit contributions
izing-0.058
yles-0.055
ning-0.055
rily-0.054
bing-0.053
Token
Token ID26391
Feature activation+3.60e-01

Pos logit contributions
izing+0.103
ellery+0.096
king+0.095
yles+0.094
ning+0.094
Neg logit contributions
 am-0.081
 big-0.078
-0.078
 story-0.076
 to-0.076
Token
Token ID8151
Feature activation-9.23e-02

Pos logit contributions
 am+0.009
 done+0.008
 bad+0.008
 story+0.008
 big+0.008
Neg logit contributions
yles-0.007
izing-0.006
ellery-0.006
king-0.006
ning-0.006
Tokent
Token ID83
Feature activation+8.62e-01

Pos logit contributions
izing+0.003
yles+0.003
king+0.003
ning+0.003
ants+0.003
Neg logit contributions
 am-0.001
 done-0.001
 story-0.001
 bad-0.001
 big-0.001
Token run
Token ID1057
Feature activation-1.14e+00

Pos logit contributions
 done+0.013
 am+0.012
 story+0.012
ossible+0.011
+0.011
Neg logit contributions
izing-0.023
king-0.023
ivating-0.022
yles-0.022
rily-0.022
Token anymore
Token ID7471
Feature activation+5.70e+00

Pos logit contributions
izing+0.032
king+0.030
ning+0.029
rily+0.029
ivating+0.029
Neg logit contributions
 am-0.018
 story-0.017
 done-0.017
ossible-0.016
-0.015
Token.
Token ID13
Feature activation+2.03e+00

Pos logit contributions
 am+0.049
 done+0.042
 story+0.035
+0.033
ossible+0.032
Neg logit contributions
izing-0.200
yles-0.193
king-0.191
ning-0.191
ellery-0.190
Token Then
Token ID3244
Feature activation+1.89e+00

Pos logit contributions
 done+0.028
 am+0.027
 story+0.023
 bad+0.019
 time+0.018
Neg logit contributions
rily-0.058
izing-0.057
ting-0.057
ivating-0.056
yles-0.056
Token he
Token ID339
Feature activation+2.11e+00

Pos logit contributions
 am+0.028
 done+0.026
 story+0.023
 own+0.021
 whole+0.020
Neg logit contributions
izing-0.052
ting-0.051
rily-0.049
bing-0.047
yles-0.046
Token stopped
Token ID5025
Feature activation+1.13e+00

Pos logit contributions
 am+0.031
 done+0.027
 story+0.027
+0.027
 bad+0.024
Neg logit contributions
izing-0.059
ning-0.058
yles-0.058
king-0.058
ellery-0.057
Token.
Token ID13
Feature activation+1.70e+00

Pos logit contributions
 am+0.015
 done+0.014
 story+0.013
+0.012
 time+0.012
Neg logit contributions
izing-0.034
ning-0.034
king-0.033
yles-0.033
bing-0.033
Token but
Token ID475
Feature activation+1.16e+00

Pos logit contributions
izing+0.044
king+0.041
yles+0.041
ning+0.041
rily+0.041
Neg logit contributions
 am-0.030
 done-0.027
 story-0.026
-0.026
 big-0.025
Token she
Token ID673
Feature activation+2.55e+00

Pos logit contributions
 am+0.023
 done+0.020
 story+0.020
+0.019
 big+0.019
Neg logit contributions
izing-0.028
yles-0.027
rily-0.027
ellery-0.026
bing-0.025
Token followed
Token ID3940
Feature activation-7.72e-01

Pos logit contributions
 am+0.037
 done+0.032
+0.032
 story+0.031
 big+0.030
Neg logit contributions
izing-0.073
yles-0.070
ning-0.069
rily-0.069
king-0.069
Token her
Token ID607
Feature activation+2.70e+00

Pos logit contributions
izing+0.022
yles+0.022
ning+0.021
rily+0.021
ellery+0.021
Neg logit contributions
 am-0.012
 done-0.011
-0.010
 story-0.010
 big-0.009
Token parents
Token ID3397
Feature activation+1.45e+00

Pos logit contributions
 am+0.055
 done+0.047
+0.044
+0.044
'm+0.043
Neg logit contributions
izing-0.063
bing-0.062
rily-0.061
yles-0.061
ning-0.059
Token anyway
Token ID6949
Feature activation+5.69e+00

Pos logit contributions
 am+0.016
 done+0.014
+0.013
 story+0.012
 big+0.012
Neg logit contributions
izing-0.048
yles-0.047
ning-0.046
king-0.046
rily-0.046
Token.
Token ID13
Feature activation+2.52e+00

Pos logit contributions
 am+0.056
 done+0.042
 story+0.036
+0.036
 big+0.033
Neg logit contributions
izing-0.199
rily-0.190
king-0.188
ning-0.185
bing-0.184
Token She
Token ID1375
Feature activation+2.30e+00

Pos logit contributions
 am+0.039
 done+0.039
 bad+0.036
 story+0.034
 big+0.033
Neg logit contributions
rily-0.069
yles-0.068
izing-0.068
ning-0.067
ants-0.067
Token threw
Token ID9617
Feature activation-3.29e+00

Pos logit contributions
 am+0.032
 done+0.028
+0.028
 story+0.027
 big+0.025
Neg logit contributions
izing-0.068
yles-0.066
ning-0.066
king-0.065
rily-0.065
Token the
Token ID262
Feature activation+2.23e-01

Pos logit contributions
izing+0.112
yles+0.108
king+0.106
ning+0.106
ellery+0.106
Neg logit contributions
 am-0.034
-0.032
 done-0.030
 big-0.030
 to-0.029
Token salt
Token ID8268
Feature activation-1.36e+00

Pos logit contributions
 am+0.005
+0.004
 done+0.004
 He+0.004
 story+0.004
Neg logit contributions
izing-0.005
king-0.005
ning-0.005
rily-0.004
 chick-0.004
Token him
Token ID683
Feature activation+3.64e+00

Pos logit contributions
izing+0.033
yles+0.032
ning+0.031
ellery+0.031
rily+0.031
Neg logit contributions
 am-0.020
 done-0.018
-0.018
 story-0.017
 big-0.016
Token not
Token ID407
Feature activation+1.12e+00

Pos logit contributions
 am+0.051
+0.045
+0.045
 done+0.043
 time+0.043
Neg logit contributions
izing-0.101
ellery-0.098
ants-0.096
yles-0.096
rily-0.095
Token to
Token ID284
Feature activation-2.12e+00

Pos logit contributions
 am+0.004
+0.003
 done+0.003
 story+0.002
 big+0.001
Neg logit contributions
izing-0.045
yles-0.043
ning-0.043
king-0.043
ellery-0.043
Token be
Token ID307
Feature activation-9.16e-01

Pos logit contributions
izing+0.058
yles+0.056
ning+0.055
rily+0.055
king+0.054
Neg logit contributions
 am-0.036
 done-0.033
-0.033
 story-0.031
 big-0.031
Token upset
Token ID9247
Feature activation+2.06e+00

Pos logit contributions
izing+0.026
yles+0.025
ning+0.024
king+0.024
ellery+0.024
Neg logit contributions
 am-0.015
 done-0.014
-0.014
 story-0.013
 big-0.013
Token anymore
Token ID7471
Feature activation+5.69e+00

Pos logit contributions
 am+0.026
 done+0.023
 story+0.022
ossible+0.021
+0.021
Neg logit contributions
izing-0.065
ning-0.062
king-0.061
yles-0.061
bing-0.061
Token.
Token ID13
Feature activation+1.47e+00

Pos logit contributions
 am+0.051
 done+0.043
 story+0.037
 big+0.036
ossible+0.034
Neg logit contributions
izing-0.198
yles-0.188
bing-0.187
king-0.187
ning-0.186
Token Tim
Token ID5045
Feature activation-1.20e+00

Pos logit contributions
 am+0.027
 done+0.026
 story+0.024
 big+0.023
 bad+0.023
Neg logit contributions
izing-0.037
yles-0.036
ning-0.035
ants-0.035
ellery-0.034
Tokenmy
Token ID1820
Feature activation+9.11e-01

Pos logit contributions
ning+0.020
burn+0.019
izing+0.019
king+0.019
ellery+0.018
Neg logit contributions
 am-0.031
-0.028
 big-0.027
 bad-0.027
 done-0.027
Token was
Token ID373
Feature activation+4.98e-01

Pos logit contributions
 am+0.009
 done+0.007
+0.007
 story+0.006
 time+0.006
Neg logit contributions
izing-0.030
ning-0.029
king-0.029
bing-0.028
rily-0.028
Token happy
Token ID3772
Feature activation+3.31e+00

Pos logit contributions
 am+0.007
 done+0.006
 story+0.006
+0.006
 time+0.005
Neg logit contributions
izing-0.015
yles-0.014
ning-0.014
king-0.014
ellery-0.014
Token But
Token ID887
Feature activation+4.12e-01

Pos logit contributions
 am+0.019
 done+0.017
 story+0.015
 bad+0.015
 big+0.014
Neg logit contributions
izing-0.032
rily-0.032
ning-0.032
yles-0.032
ksh-0.032
Token his
Token ID465
Feature activation+2.28e+00

Pos logit contributions
 am+0.009
 done+0.008
 story+0.008
+0.008
 big+0.007
Neg logit contributions
izing-0.010
yles-0.009
ning-0.009
king-0.009
bing-0.009
Token friends
Token ID2460
Feature activation+1.27e+00

Pos logit contributions
 am+0.037
+0.035
+0.032
 done+0.032
 He+0.031
Neg logit contributions
ning-0.054
bing-0.053
izing-0.052
ellery-0.052
yles-0.052
Token found
Token ID1043
Feature activation-1.18e+00

Pos logit contributions
 am+0.016
 story+0.014
+0.014
 done+0.013
 big+0.013
Neg logit contributions
izing-0.038
ning-0.037
king-0.037
yles-0.037
ting-0.036
Token him
Token ID683
Feature activation+2.56e+00

Pos logit contributions
izing+0.033
ning+0.033
yles+0.032
ellery+0.032
rily+0.032
Neg logit contributions
 am-0.018
 story-0.016
 done-0.016
-0.016
ossible-0.014
Token anyways
Token ID32845
Feature activation+5.68e+00

Pos logit contributions
 am+0.039
+0.034
 done+0.033
 story+0.032
ossible+0.031
Neg logit contributions
izing-0.070
ning-0.069
king-0.068
ellery-0.067
bing-0.067
Token.
Token ID13
Feature activation+1.69e+00

Pos logit contributions
 am+0.077
ossible+0.068
+0.064
 done+0.063
 story+0.062
Neg logit contributions
izing-0.155
rily-0.147
ning-0.144
king-0.144
bing-0.141
Token
Token ID220
Feature activation+3.59e+00

Pos logit contributions
 am+0.022
 done+0.021
 story+0.018
 bad+0.018
 big+0.017
Neg logit contributions
izing-0.052
yles-0.051
ning-0.050
rily-0.050
king-0.049
Token
Token ID198
Feature activation+1.30e+00

Pos logit contributions
 am+0.019
 done+0.017
 story+0.015
 bad+0.013
 big+0.010
Neg logit contributions
yles-0.134
izing-0.132
ning-0.132
ants-0.131
rily-0.128
Token
Token ID198
Feature activation-1.07e+00

Pos logit contributions
 am+0.007
 done+0.007
 bad+0.005
 story+0.004
 big+0.003
Neg logit contributions
izing-0.047
yles-0.047
ants-0.046
bing-0.046
ning-0.045
TokenThey
Token ID2990
Feature activation+2.12e+00

Pos logit contributions
izing+0.028
yles+0.028
ning+0.027
ellery+0.027
rily+0.027
Neg logit contributions
 am-0.020
-0.019
 done-0.018
 big-0.017
 story-0.017
Token together
Token ID1978
Feature activation+3.93e+00

Pos logit contributions
izing+0.003
king+0.003
rily+0.003
bing+0.003
ning+0.003
Neg logit contributions
 am-0.003
 done-0.002
 story-0.002
-0.002
 bad-0.002
Token side
Token ID1735
Feature activation+2.26e+00

Pos logit contributions
 am+0.052
 done+0.044
 story+0.042
+0.041
 bad+0.039
Neg logit contributions
izing-0.120
king-0.117
ning-0.117
bing-0.115
yles-0.115
Token-
Token ID12
Feature activation-4.51e+00

Pos logit contributions
 am+0.017
 done+0.014
+0.013
 story+0.012
 big+0.011
Neg logit contributions
izing-0.083
yles-0.080
ning-0.080
king-0.079
ellery-0.079
Tokenby
Token ID1525
Feature activation+2.72e+00

Pos logit contributions
izing+0.105
yles+0.100
ning+0.098
rily+0.098
ellery+0.097
Neg logit contributions
 am-0.094
 done-0.089
-0.089
 story-0.084
 to-0.083
Token-
Token ID12
Feature activation-4.67e+00

Pos logit contributions
 am+0.037
 done+0.033
+0.032
 story+0.031
 big+0.029
Neg logit contributions
izing-0.083
king-0.080
yles-0.080
ning-0.080
ellery-0.078
Tokenside
Token ID1589
Feature activation+5.66e+00

Pos logit contributions
izing+0.110
yles+0.105
rily+0.103
ning+0.103
ellery+0.102
Neg logit contributions
 am-0.096
 done-0.091
-0.091
 to-0.086
 story-0.084
Token.
Token ID13
Feature activation+2.04e+00

Pos logit contributions
 am+0.065
 done+0.047
 story+0.042
ossible+0.040
'm+0.040
Neg logit contributions
izing-0.193
king-0.180
bing-0.180
ning-0.179
rily-0.176
Token
Token ID220
Feature activation+3.35e+00

Pos logit contributions
 am+0.024
 done+0.022
 bad+0.020
 big+0.019
 story+0.019
Neg logit contributions
yles-0.063
izing-0.062
ellery-0.061
ning-0.061
ants-0.061
Token
Token ID198
Feature activation+1.40e+00

Pos logit contributions
 am+0.016
 done+0.014
 story+0.012
 bad+0.011
 big+0.008
Neg logit contributions
yles-0.126
izing-0.124
ning-0.124
ants-0.124
king-0.122
Token
Token ID198
Feature activation-5.33e-01

Pos logit contributions
 am+0.006
 done+0.005
 bad+0.004
 story+0.003
 big+0.003
Neg logit contributions
yles-0.053
izing-0.053
ants-0.051
ning-0.051
rily-0.051
TokenNo
Token ID2949
Feature activation+7.33e-01

Pos logit contributions
izing+0.013
yles+0.012
ning+0.012
king+0.012
rily+0.012
Neg logit contributions
 am-0.011
-0.010
 done-0.010
 story-0.010
 big-0.010
Token and
Token ID290
Feature activation-2.19e+00

Pos logit contributions
 am+0.024
 story+0.022
 He+0.020
+0.020
 big+0.019
Neg logit contributions
izing-0.043
king-0.042
yles-0.041
ning-0.041
ellery-0.041
Token refused
Token ID6520
Feature activation+2.65e+00

Pos logit contributions
izing+0.058
yles+0.057
ning+0.056
ellery+0.056
bul+0.055
Neg logit contributions
 am-0.031
-0.029
 story-0.029
 done-0.028
-0.027
Token to
Token ID284
Feature activation-1.23e+00

Pos logit contributions
 am+0.028
ossible+0.023
 done+0.021
 story+0.021
+0.020
Neg logit contributions
izing-0.088
ning-0.083
king-0.082
ellery-0.081
yles-0.081
Token be
Token ID307
Feature activation-9.37e-01

Pos logit contributions
izing+0.036
king+0.034
ning+0.034
yles+0.034
ellery+0.033
Neg logit contributions
 am-0.017
-0.016
 done-0.016
 story-0.014
 big-0.014
Token miserable
Token ID22444
Feature activation+1.59e+00

Pos logit contributions
izing+0.024
king+0.023
ning+0.023
yles+0.023
ellery+0.023
Neg logit contributions
 am-0.017
-0.015
 story-0.015
 done-0.014
ossible-0.014
Token anymore
Token ID7471
Feature activation+5.63e+00

Pos logit contributions
 am+0.019
 done+0.017
 story+0.016
+0.016
ossible+0.015
Neg logit contributions
izing-0.051
ning-0.048
yles-0.048
king-0.048
rily-0.047
Token.
Token ID13
Feature activation+2.30e+00

Pos logit contributions
 am+0.053
 done+0.047
 big+0.039
ossible+0.038
 story+0.038
Neg logit contributions
izing-0.190
yles-0.179
bing-0.178
king-0.178
ning-0.178
Token
Token ID220
Feature activation+3.57e+00

Pos logit contributions
 done+0.027
 am+0.025
 bad+0.023
 big+0.022
 story+0.020
Neg logit contributions
yles-0.068
izing-0.068
ellery-0.067
ning-0.066
bul-0.066
Token
Token ID198
Feature activation+1.46e+00

Pos logit contributions
 am+0.014
 done+0.011
 story+0.009
 bad+0.007
 big+0.006
Neg logit contributions
izing-0.138
yles-0.137
ning-0.136
ants-0.134
king-0.133
Token
Token ID198
Feature activation-7.34e-01

Pos logit contributions
 done+0.010
 am+0.010
 bad+0.008
 way+0.007
 time+0.007
Neg logit contributions
izing-0.050
yles-0.049
bing-0.048
ning-0.048
ants-0.048
TokenThe
Token ID464
Feature activation-7.46e-01

Pos logit contributions
izing+0.018
yles+0.018
ning+0.017
king+0.017
rily+0.017
Neg logit contributions
 am-0.014
-0.014
 done-0.013
 story-0.013
 big-0.012
Tokent
Token ID83
Feature activation+3.41e-01

Pos logit contributions
izing+0.022
yles+0.022
ning+0.022
king+0.021
rily+0.021
Neg logit contributions
 am-0.007
 done-0.006
-0.006
 story-0.006
 big-0.006
Token have
Token ID423
Feature activation+6.57e-01

Pos logit contributions
 am+0.004
+0.004
 done+0.004
 story+0.004
ossible+0.004
Neg logit contributions
izing-0.009
burn-0.009
king-0.009
ning-0.009
shadow-0.009
Token to
Token ID284
Feature activation-1.06e+00

Pos logit contributions
 am+0.007
 story+0.005
+0.005
 done+0.004
 He+0.004
Neg logit contributions
ellery-0.021
ning-0.021
yles-0.021
izing-0.020
burn-0.020
Token be
Token ID307
Feature activation-6.42e-01

Pos logit contributions
izing+0.029
burn+0.028
ning+0.027
ellery+0.027
king+0.027
Neg logit contributions
 am-0.015
-0.014
 done-0.014
-0.013
 story-0.013
Token scared
Token ID12008
Feature activation+1.18e+00

Pos logit contributions
izing+0.018
ning+0.017
yles+0.017
king+0.017
ellery+0.017
Neg logit contributions
 am-0.010
-0.009
 done-0.009
 story-0.009
 big-0.008
Token anymore
Token ID7471
Feature activation+5.62e+00

Pos logit contributions
 am+0.011
 done+0.010
+0.009
 story+0.009
 big+0.008
Neg logit contributions
izing-0.041
ning-0.039
yles-0.039
king-0.039
rily-0.038
Token.
Token ID13
Feature activation+2.29e+00

Pos logit contributions
 am+0.046
 done+0.040
 story+0.032
+0.032
 big+0.032
Neg logit contributions
izing-0.198
yles-0.190
ning-0.189
king-0.189
ellery-0.187
Token
Token ID198
Feature activation+1.14e+00

Pos logit contributions
 am+0.026
 done+0.024
 bad+0.020
 story+0.019
 big+0.018
Neg logit contributions
yles-0.071
izing-0.071
ning-0.069
rily-0.069
ellery-0.068
Token
Token ID198
Feature activation-1.60e+00

Pos logit contributions
 am+0.010
 done+0.010
 bad+0.008
 consequences+0.008
 way+0.007
Neg logit contributions
izing-0.035
yles-0.035
bing-0.034
ants-0.034
shadow-0.034
TokenBut
Token ID1537
Feature activation+4.32e-01

Pos logit contributions
izing+0.036
yles+0.035
ning+0.035
rily+0.034
king+0.034
Neg logit contributions
 am-0.035
-0.034
 done-0.033
 big-0.032
 story-0.032
Token Daisy
Token ID40355
Feature activation+6.43e-01

Pos logit contributions
 am+0.010
+0.009
 done+0.009
 story+0.009
 to+0.009
Neg logit contributions
izing-0.010
yles-0.009
ning-0.009
king-0.009
ellery-0.009
Token didn
Token ID1422
Feature activation+1.28e+00

Pos logit contributions
izing+0.052
yles+0.050
ning+0.050
king+0.049
rily+0.049
Neg logit contributions
 am-0.029
 story-0.025
 done-0.025
-0.025
 big-0.023
Token't
Token ID470
Feature activation+6.62e-01

Pos logit contributions
 am+0.021
+0.019
 done+0.019
 story+0.018
 big+0.018
Neg logit contributions
izing-0.036
yles-0.035
ning-0.035
king-0.034
ellery-0.034
Token want
Token ID765
Feature activation+1.52e+00

Pos logit contributions
 am+0.008
+0.008
 done+0.008
 story+0.007
 big+0.007
Neg logit contributions
izing-0.019
yles-0.019
ellery-0.019
rily-0.018
king-0.018
Token to
Token ID284
Feature activation-1.06e+00

Pos logit contributions
 am+0.013
 done+0.012
ossible+0.010
 story+0.009
 learned+0.008
Neg logit contributions
ning-0.049
ellery-0.049
burn-0.048
izing-0.048
yles-0.048
Token wait
Token ID4043
Feature activation+2.81e+00

Pos logit contributions
izing+0.030
yles+0.029
ning+0.029
ellery+0.029
burn+0.029
Neg logit contributions
 am-0.015
 done-0.014
-0.013
 story-0.013
 to-0.012
Token anymore
Token ID7471
Feature activation+5.61e+00

Pos logit contributions
 am+0.034
 story+0.026
 done+0.024
+0.024
 learned+0.023
Neg logit contributions
izing-0.087
rily-0.086
king-0.084
ning-0.083
yles-0.083
Token!
Token ID0
Feature activation+1.02e+00

Pos logit contributions
 am+0.046
 done+0.037
 story+0.031
+0.030
 big+0.030
Neg logit contributions
izing-0.197
yles-0.194
ning-0.192
king-0.191
ellery-0.191
Token
Token ID220
Feature activation+2.58e+00

Pos logit contributions
 done+0.016
 am+0.016
 story+0.014
 bad+0.013
 big+0.013
Neg logit contributions
rily-0.027
yles-0.027
izing-0.027
ning-0.027
ender-0.027
Token
Token ID198
Feature activation+6.14e-01

Pos logit contributions
 done+0.018
 am+0.016
 bad+0.014
 story+0.014
 learned+0.010
Neg logit contributions
yles-0.089
ning-0.087
ants-0.087
rily-0.087
izing-0.087
Token
Token ID198
Feature activation-1.72e+00

Pos logit contributions
 done+0.005
 am+0.004
 bad+0.003
 story+0.003
 consequences+0.003
Neg logit contributions
yles-0.021
izing-0.021
rily-0.020
shadow-0.020
ning-0.020
TokenBut
Token ID1537
Feature activation-3.91e-01

Pos logit contributions
izing+0.040
yles+0.039
ning+0.038
ellery+0.038
king+0.038
Neg logit contributions
 am-0.037
-0.035
 done-0.034
 story-0.033
 big-0.033
Token play
Token ID711
Feature activation+1.82e-01

Pos logit contributions
 am+0.009
 done+0.008
+0.008
 story+0.007
 big+0.007
Neg logit contributions
izing-0.020
yles-0.019
ning-0.019
king-0.019
ellery-0.019
Token side
Token ID1735
Feature activation+7.00e-01

Pos logit contributions
 am+0.003
 done+0.003
 story+0.002
ossible+0.002
+0.002
Neg logit contributions
izing-0.005
bing-0.005
ning-0.005
king-0.005
rily-0.005
Token-
Token ID12
Feature activation-5.32e+00

Pos logit contributions
 am+0.007
 done+0.006
+0.006
 story+0.006
 big+0.005
Neg logit contributions
izing-0.024
yles-0.023
ning-0.023
king-0.023
ellery-0.023
Tokenby
Token ID1525
Feature activation+2.16e+00

Pos logit contributions
izing+0.119
yles+0.114
ning+0.112
king+0.111
ellery+0.110
Neg logit contributions
 am-0.115
 done-0.108
-0.108
 story-0.105
 big-0.102
Token-
Token ID12
Feature activation-5.23e+00

Pos logit contributions
 am+0.027
 done+0.023
+0.022
 story+0.021
 bad+0.020
Neg logit contributions
izing-0.068
king-0.066
yles-0.066
ning-0.066
bing-0.065
Tokenside
Token ID1589
Feature activation+5.60e+00

Pos logit contributions
izing+0.122
yles+0.117
ning+0.115
king+0.114
ellery+0.113
Neg logit contributions
 am-0.109
 done-0.102
-0.102
 story-0.099
 big-0.096
Token with
Token ID351
Feature activation-5.60e-01

Pos logit contributions
 am+0.068
 done+0.051
 bad+0.045
'm+0.044
+0.044
Neg logit contributions
izing-0.186
bing-0.176
ning-0.173
king-0.173
rily-0.171
Token the
Token ID262
Feature activation+1.56e+00

Pos logit contributions
izing+0.018
yles+0.018
ning+0.017
king+0.017
ellery+0.017
Neg logit contributions
 am-0.006
-0.006
 done-0.006
 big-0.005
 story-0.005
Token infant
Token ID11212
Feature activation+2.19e-01

Pos logit contributions
 am+0.028
+0.026
 done+0.025
 story+0.024
ossible+0.022
Neg logit contributions
izing-0.039
yles-0.038
rily-0.038
ning-0.038
king-0.037
Token.
Token ID13
Feature activation+1.86e+00

Pos logit contributions
 am+0.003
 done+0.002
+0.002
 story+0.002
 bad+0.002
Neg logit contributions
izing-0.007
ning-0.007
yles-0.007
king-0.007
ellery-0.007
Token They
Token ID1119
Feature activation+1.73e+00

Pos logit contributions
 am+0.023
 done+0.021
 story+0.019
 bad+0.018
 big+0.018
Neg logit contributions
izing-0.058
yles-0.057
ning-0.056
rily-0.056
king-0.055
Token her
Token ID607
Feature activation+2.23e+00

Pos logit contributions
izing+0.033
yles+0.032
ning+0.032
king+0.031
ellery+0.031
Neg logit contributions
 am-0.015
-0.015
 done-0.014
 to-0.013
 big-0.013
Token too
Token ID1165
Feature activation+5.20e+00

Pos logit contributions
 am+0.027
 done+0.024
+0.024
 story+0.022
 big+0.021
Neg logit contributions
izing-0.072
yles-0.070
ning-0.069
king-0.069
ellery-0.069
Token and
Token ID290
Feature activation-1.45e+00

Pos logit contributions
 am+0.062
 done+0.050
 story+0.046
+0.045
+0.040
Neg logit contributions
izing-0.169
king-0.161
rily-0.159
ning-0.157
yles-0.157
Token thanked
Token ID26280
Feature activation-1.07e+00

Pos logit contributions
izing+0.044
yles+0.043
ning+0.042
ellery+0.042
king+0.042
Neg logit contributions
 am-0.020
 done-0.018
-0.017
 story-0.017
 big-0.016
Token her
Token ID607
Feature activation+2.17e+00

Pos logit contributions
izing+0.032
yles+0.031
ning+0.031
king+0.030
ellery+0.030
Neg logit contributions
 am-0.015
-0.014
 done-0.014
 story-0.013
 big-0.013
Token too
Token ID1165
Feature activation+5.58e+00

Pos logit contributions
 am+0.026
 done+0.024
+0.023
 story+0.021
 big+0.020
Neg logit contributions
izing-0.070
yles-0.067
ning-0.067
king-0.066
rily-0.066
Token.
Token ID13
Feature activation+2.19e+00

Pos logit contributions
 am+0.049
 done+0.038
 story+0.032
+0.029
ossible+0.025
Neg logit contributions
izing-0.199
king-0.190
rily-0.189
yles-0.187
ellery-0.186
Token
Token ID198
Feature activation+9.56e-01

Pos logit contributions
 am+0.028
 done+0.026
 bad+0.023
 story+0.022
 big+0.022
Neg logit contributions
yles-0.067
izing-0.067
ning-0.065
ellery-0.065
rily-0.065
Token
Token ID198
Feature activation-1.05e+00

Pos logit contributions
 am+0.008
 done+0.007
 bad+0.006
 way+0.005
 felt+0.004
Neg logit contributions
yles-0.033
ants-0.032
izing-0.032
bing-0.031
rily-0.031
TokenJack
Token ID14295
Feature activation+4.73e-01

Pos logit contributions
izing+0.025
ning+0.024
yles+0.024
king+0.024
rily+0.024
Neg logit contributions
 am-0.021
-0.021
 done-0.020
 story-0.019
 big-0.019
Token and
Token ID290
Feature activation-2.12e+00

Pos logit contributions
 am+0.005
 done+0.005
+0.005
 story+0.004
 big+0.004
Neg logit contributions
izing-0.015
ning-0.015
yles-0.015
king-0.015
ellery-0.014
Token
Token ID8151
Feature activation-3.50e-01

Pos logit contributions
yles+0.003
izing+0.003
king+0.003
ning+0.003
ellery+0.003
Neg logit contributions
 am-0.004
 done-0.003
 bad-0.003
 big-0.003
 story-0.003
Tokent
Token ID83
Feature activation+5.24e-01

Pos logit contributions
izing+0.011
ning+0.011
yles+0.011
king+0.010
ants+0.010
Neg logit contributions
 am-0.004
 done-0.004
 story-0.004
-0.003
 big-0.003
Token feel
Token ID1254
Feature activation+9.01e-01

Pos logit contributions
 am+0.007
+0.007
ossible+0.007
+0.007
 done+0.007
Neg logit contributions
izing-0.014
burn-0.013
king-0.013
shadow-0.013
ning-0.013
Token so
Token ID523
Feature activation-4.80e-01

Pos logit contributions
ossible+0.016
 am+0.015
 story+0.014
 done+0.014
+0.012
Neg logit contributions
izing-0.022
rily-0.021
ting-0.020
ivating-0.020
king-0.020
Token alone
Token ID3436
Feature activation+1.95e+00

Pos logit contributions
izing+0.012
ivating+0.011
rily+0.011
bly+0.011
bing+0.011
Neg logit contributions
 am-0.008
ossible-0.007
 story-0.007
 done-0.007
-0.007
Token anymore
Token ID7471
Feature activation+5.57e+00

Pos logit contributions
 am+0.021
 done+0.018
ossible+0.018
 story+0.017
+0.016
Neg logit contributions
izing-0.062
ning-0.060
rily-0.059
ting-0.059
king-0.059
Token.
Token ID13
Feature activation+1.61e+00

Pos logit contributions
 am+0.056
 done+0.050
 big+0.042
ossible+0.042
 story+0.039
Neg logit contributions
izing-0.184
yles-0.174
rily-0.173
king-0.173
ning-0.173
Token He
Token ID679
Feature activation+1.90e+00

Pos logit contributions
 done+0.022
 am+0.022
 bad+0.019
 big+0.019
 story+0.017
Neg logit contributions
izing-0.045
ning-0.044
yles-0.043
ellery-0.043
bul-0.043
Tokenâ
Token ID22940
Feature activation-3.40e+00

Pos logit contributions
 am+0.027
 done+0.024
+0.023
 story+0.022
 big+0.021
Neg logit contributions
izing-0.052
ning-0.052
yles-0.051
ellery-0.050
rily-0.050
Token
Token ID26391
Feature activation+1.18e-01

Pos logit contributions
izing+0.067
king+0.061
ning+0.061
bing+0.058
ellery+0.058
Neg logit contributions
 am-0.080
 big-0.079
-0.077
 story-0.076
 to-0.075
Token
Token ID8151
Feature activation-3.03e-01

Pos logit contributions
 am+0.002
 bad+0.002
 done+0.002
 big+0.002
 time+0.002
Neg logit contributions
yles-0.003
izing-0.003
ellery-0.003
king-0.003
ning-0.003
Token and
Token ID290
Feature activation-2.23e+00

Pos logit contributions
 am+0.046
 done+0.037
ossible+0.037
'm+0.036
 whole+0.036
Neg logit contributions
izing-0.070
ning-0.064
bing-0.063
king-0.062
ting-0.061
Token decided
Token ID3066
Feature activation+1.84e+00

Pos logit contributions
izing+0.062
ning+0.060
king+0.059
yles+0.059
rily+0.057
Neg logit contributions
 am-0.037
 story-0.032
-0.032
 done-0.031
 big-0.029
Token to
Token ID284
Feature activation+9.09e-02

Pos logit contributions
 am+0.021
 story+0.017
 done+0.015
ossible+0.015
 time+0.013
Neg logit contributions
izing-0.059
shadow-0.058
ning-0.057
king-0.057
ellery-0.055
Token take
Token ID1011
Feature activation-2.81e+00

Pos logit contributions
 am+0.001
 done+0.001
+0.001
 story+0.001
 big+0.001
Neg logit contributions
izing-0.002
ning-0.002
burn-0.002
yles-0.002
rily-0.002
Token Max
Token ID5436
Feature activation+1.83e+00

Pos logit contributions
izing+0.072
yles+0.070
ning+0.070
ellery+0.068
king+0.068
Neg logit contributions
 am-0.050
 done-0.046
-0.045
 story-0.044
 big-0.041
Token anyway
Token ID6949
Feature activation+5.57e+00

Pos logit contributions
 am+0.022
 done+0.018
 story+0.016
+0.015
 grown+0.015
Neg logit contributions
ning-0.057
king-0.056
ellery-0.055
burn-0.054
bing-0.054
Token.
Token ID13
Feature activation+1.31e+00

Pos logit contributions
 am+0.060
 done+0.048
 story+0.041
+0.040
+0.039
Neg logit contributions
izing-0.182
rily-0.175
ning-0.173
bing-0.170
king-0.169
Token
Token ID220
Feature activation+3.45e+00

Pos logit contributions
 am+0.015
 done+0.013
 story+0.012
 bad+0.011
 big+0.010
Neg logit contributions
izing-0.042
ning-0.041
yles-0.041
bing-0.040
king-0.040
Token
Token ID198
Feature activation+3.50e-01

Pos logit contributions
 am+0.022
 done+0.021
 bad+0.017
 story+0.017
 big+0.013
Neg logit contributions
yles-0.122
ning-0.120
izing-0.120
ants-0.119
rily-0.117
Token
Token ID198
Feature activation-1.70e+00

Pos logit contributions
 am+0.002
 done+0.002
 bad+0.001
 story+0.001
 big+0.001
Neg logit contributions
izing-0.013
yles-0.013
ning-0.013
king-0.012
bing-0.012
TokenThey
Token ID2990
Feature activation+1.98e+00

Pos logit contributions
izing+0.039
yles+0.038
rily+0.037
ellery+0.037
ning+0.037
Neg logit contributions
-0.036
 am-0.036
 done-0.035
 big-0.033
 story-0.033
Token,
Token ID11
Feature activation-2.93e+00

Pos logit contributions
 am+0.018
 done+0.015
 story+0.014
+0.013
'm+0.012
Neg logit contributions
izing-0.035
king-0.034
ning-0.033
yles-0.033
ting-0.032
Token but
Token ID475
Feature activation+3.23e-01

Pos logit contributions
izing+0.081
yles+0.077
ning+0.076
king+0.076
ellery+0.075
Neg logit contributions
 am-0.049
 done-0.045
-0.045
 story-0.042
 big-0.042
Token he
Token ID339
Feature activation+1.96e+00

Pos logit contributions
 am+0.003
+0.003
 done+0.003
 big+0.002
 to+0.002
Neg logit contributions
izing-0.011
yles-0.011
ning-0.011
king-0.011
ellery-0.011
Token followed
Token ID3940
Feature activation-1.77e+00

Pos logit contributions
 am+0.024
 done+0.022
+0.021
 story+0.019
 big+0.019
Neg logit contributions
izing-0.063
yles-0.061
ning-0.060
rily-0.059
king-0.059
Token Lily
Token ID20037
Feature activation+2.58e+00

Pos logit contributions
izing+0.050
yles+0.048
ning+0.047
king+0.047
ellery+0.047
Neg logit contributions
 am-0.028
 done-0.026
-0.026
 story-0.024
 big-0.024
Token anyway
Token ID6949
Feature activation+5.55e+00

Pos logit contributions
 am+0.030
 done+0.025
+0.023
 story+0.023
 bad+0.022
Neg logit contributions
izing-0.082
ning-0.082
king-0.081
yles-0.080
bing-0.080
Token.
Token ID13
Feature activation+8.44e-01

Pos logit contributions
 am+0.056
 done+0.043
 story+0.037
+0.033
'm+0.033
Neg logit contributions
izing-0.192
rily-0.185
king-0.182
ning-0.181
bing-0.180
Token When
Token ID1649
Feature activation+1.79e+00

Pos logit contributions
 am+0.013
 done+0.012
 story+0.011
+0.010
 bad+0.010
Neg logit contributions
izing-0.024
ning-0.023
rily-0.023
yles-0.023
king-0.023
Token they
Token ID484
Feature activation+2.21e+00

Pos logit contributions
 am+0.029
 done+0.026
 story+0.025
+0.025
 big+0.023
Neg logit contributions
izing-0.049
yles-0.048
ning-0.047
ellery-0.046
burn-0.045
Token got
Token ID1392
Feature activation-7.17e-03

Pos logit contributions
 am+0.032
 story+0.031
 done+0.027
+0.026
 lesson+0.026
Neg logit contributions
yles-0.058
ellery-0.056
king-0.056
izing-0.056
ting-0.055
Token to
Token ID284
Feature activation+3.75e-01

Pos logit contributions
yles+0.000
ning+0.000
izing+0.000
ellery+0.000
king+0.000
Neg logit contributions
 am-0.000
 story-0.000
 done-0.000
-0.000
 time-0.000
Token that
Token ID326
Feature activation+4.33e-01

Pos logit contributions
izing+0.048
yles+0.047
ellery+0.045
ning+0.045
rily+0.045
Neg logit contributions
 am-0.018
-0.017
 done-0.017
 big-0.016
 to-0.016
Token said
Token ID531
Feature activation-1.56e-01

Pos logit contributions
 am+0.005
 done+0.005
 story+0.004
+0.004
 time+0.004
Neg logit contributions
izing-0.014
yles-0.013
ning-0.013
king-0.013
ellery-0.012
Token "
Token ID366
Feature activation-6.23e+00

Pos logit contributions
izing+0.004
ning+0.004
rily+0.004
king+0.004
yles+0.004
Neg logit contributions
 am-0.003
 done-0.003
 own-0.002
ossible-0.002
 time-0.002
TokenNo
Token ID2949
Feature activation+2.29e-01

Pos logit contributions
izing+0.134
rily+0.133
yles+0.131
ellery+0.128
ants+0.125
Neg logit contributions
 am-0.142
-0.138
 whole-0.126
 time-0.122
 to-0.122
Token T
Token ID309
Feature activation-5.46e+00

Pos logit contributions
 am+0.003
 done+0.003
+0.003
 story+0.003
 big+0.003
Neg logit contributions
yles-0.007
izing-0.007
rily-0.007
king-0.007
ellery-0.007
Tokenresp
Token ID4363
Feature activation-1.31e+01

Pos logit contributions
izing+0.112
yles+0.111
ning+0.105
rily+0.103
king+0.102
Neg logit contributions
 am-0.128
-0.121
 done-0.119
 story-0.119
 to-0.115
Tokenassing
Token ID19696
Feature activation-2.18e+00

Pos logit contributions
rily+0.312
bul+0.304
bly+0.286
ants+0.286
izing+0.285
Neg logit contributions
-0.267
 am-0.262
 find-0.248
 to-0.238
 learned-0.235
Token".
Token ID1911
Feature activation+2.45e-01

Pos logit contributions
izing+0.052
yles+0.050
ning+0.049
ellery+0.049
king+0.049
Neg logit contributions
 am-0.044
 done-0.041
-0.041
 story-0.039
 big-0.038
Token But
Token ID887
Feature activation-7.89e-01

Pos logit contributions
 am+0.005
 done+0.004
 story+0.004
 bad+0.004
 big+0.004
Neg logit contributions
izing-0.006
ning-0.006
rily-0.006
ender-0.006
ellery-0.006
Token Lily
Token ID20037
Feature activation+1.47e-02

Pos logit contributions
izing+0.025
yles+0.024
king+0.024
rily+0.024
ning+0.024
Neg logit contributions
 am-0.010
-0.009
 done-0.009
 to-0.009
 big-0.008
Token was
Token ID373
Feature activation+9.82e-01

Pos logit contributions
 am+0.000
 done+0.000
+0.000
 story+0.000
 big+0.000
Neg logit contributions
izing-0.000
ning-0.000
yles-0.000
king-0.000
ellery-0.000
Token that
Token ID326
Feature activation-2.59e-01

Pos logit contributions
izing+0.038
yles+0.037
ning+0.037
king+0.036
ellery+0.036
Neg logit contributions
 am-0.018
 done-0.016
-0.016
 story-0.015
 big-0.014
Token said
Token ID531
Feature activation-4.28e-01

Pos logit contributions
izing+0.008
yles+0.008
ning+0.008
king+0.007
ellery+0.007
Neg logit contributions
 am-0.003
 done-0.003
 story-0.003
-0.003
 time-0.002
Token "
Token ID366
Feature activation-5.34e+00

Pos logit contributions
izing+0.012
ning+0.011
yles+0.011
king+0.011
rily+0.011
Neg logit contributions
 am-0.007
 done-0.007
-0.006
 story-0.006
 big-0.006
TokenNo
Token ID2949
Feature activation+4.71e-01

Pos logit contributions
izing+0.112
rily+0.108
yles+0.104
ellery+0.104
ning+0.100
Neg logit contributions
 am-0.131
-0.127
 to-0.114
 whole-0.112
 time-0.112
Token T
Token ID309
Feature activation-4.88e+00

Pos logit contributions
 am+0.007
 done+0.006
+0.006
 story+0.006
 big+0.006
Neg logit contributions
izing-0.014
yles-0.013
ning-0.013
king-0.013
ellery-0.013
Tokenresp
Token ID4363
Feature activation-1.25e+01

Pos logit contributions
izing+0.089
yles+0.087
ning+0.082
rily+0.081
ellery+0.081
Neg logit contributions
 am-0.126
-0.120
 done-0.119
 story-0.117
 to-0.115
Tokenassing
Token ID19696
Feature activation-1.95e+00

Pos logit contributions
rily+0.291
bul+0.286
izing+0.273
ants+0.264
yles+0.264
Neg logit contributions
 am-0.269
-0.266
 find-0.246
 to-0.242
-0.237
Token".
Token ID1911
Feature activation+9.84e-01

Pos logit contributions
izing+0.048
yles+0.046
ellery+0.045
ning+0.045
rily+0.045
Neg logit contributions
 am-0.038
-0.036
 done-0.036
 story-0.034
 to-0.034
Token
Token ID198
Feature activation-8.62e-02

Pos logit contributions
 done+0.010
 am+0.009
 story+0.009
 bad+0.007
 whole+0.007
Neg logit contributions
izing-0.032
yles-0.031
ants-0.031
rily-0.031
ning-0.030
Token
Token ID198
Feature activation-1.86e+00

Pos logit contributions
izing+0.003
ants+0.003
yles+0.003
bing+0.003
ning+0.003
Neg logit contributions
 done-0.001
 am-0.000
 story-0.000
 bad-0.000
 time-0.000
Token"
Token ID1
Feature activation-6.53e+00

Pos logit contributions
izing+0.044
yles+0.042
ning+0.041
king+0.041
ellery+0.041
Neg logit contributions
 am-0.039
-0.037
 done-0.036
 story-0.034
 big-0.034
Token that
Token ID326
Feature activation+3.89e-01

Pos logit contributions
izing+0.045
yles+0.044
ning+0.043
ellery+0.043
rily+0.043
Neg logit contributions
 am-0.014
 done-0.013
-0.012
 story-0.011
 to-0.011
Token said
Token ID531
Feature activation-7.56e-01

Pos logit contributions
 am+0.005
 done+0.004
+0.004
 story+0.004
 big+0.004
Neg logit contributions
izing-0.012
yles-0.012
ning-0.011
king-0.011
ellery-0.011
Token "
Token ID366
Feature activation-4.65e+00

Pos logit contributions
izing+0.021
ning+0.020
yles+0.020
king+0.020
rily+0.020
Neg logit contributions
 am-0.011
 done-0.010
-0.010
ossible-0.009
 story-0.009
TokenNo
Token ID2949
Feature activation+2.36e-01

Pos logit contributions
izing+0.097
ellery+0.094
rily+0.092
yles+0.092
ants+0.090
Neg logit contributions
 am-0.111
-0.105
 done-0.098
 to-0.096
 time-0.096
Token T
Token ID309
Feature activation-4.98e+00

Pos logit contributions
 am+0.003
 done+0.002
+0.002
 story+0.002
 big+0.002
Neg logit contributions
izing-0.008
yles-0.008
ning-0.007
king-0.007
ellery-0.007
Tokenresp
Token ID4363
Feature activation-1.24e+01

Pos logit contributions
izing+0.093
yles+0.090
ning+0.087
ellery+0.086
king+0.084
Neg logit contributions
 am-0.127
-0.120
 done-0.120
 story-0.118
 to-0.114
Tokenassing
Token ID19696
Feature activation-1.96e+00

Pos logit contributions
rily+0.288
bul+0.282
ants+0.273
izing+0.267
yles+0.259
Neg logit contributions
 am-0.259
-0.256
 find-0.239
 to-0.235
 learned-0.232
Token"
Token ID1
Feature activation-1.36e+00

Pos logit contributions
izing+0.049
yles+0.047
ning+0.046
ellery+0.046
king+0.046
Neg logit contributions
 am-0.037
 done-0.035
-0.035
 story-0.033
 big-0.032
Token and
Token ID290
Feature activation-3.18e+00

Pos logit contributions
izing+0.038
ning+0.037
yles+0.037
king+0.037
rily+0.036
Neg logit contributions
 am-0.021
 done-0.019
 story-0.018
-0.017
 big-0.017
Token "
Token ID366
Feature activation-4.50e+00

Pos logit contributions
izing+0.090
yles+0.087
ning+0.085
king+0.085
ellery+0.083
Neg logit contributions
 am-0.049
-0.045
 done-0.045
 story-0.044
 big-0.041
TokenPrivate
Token ID29067
Feature activation-1.77e+00

Pos logit contributions
izing+0.096
ellery+0.090
rily+0.089
yles+0.087
ning+0.087
Neg logit contributions
 am-0.108
-0.102
 done-0.096
 to-0.092
 whole-0.090
Token that
Token ID326
Feature activation-7.31e-02

Pos logit contributions
izing+0.017
ning+0.016
yles+0.016
king+0.016
ellery+0.016
Neg logit contributions
 am-0.006
 done-0.006
-0.005
 story-0.005
 big-0.005
Token said
Token ID531
Feature activation-4.08e-01

Pos logit contributions
izing+0.002
yles+0.002
ning+0.002
rily+0.002
ellery+0.002
Neg logit contributions
 am-0.001
 done-0.001
 story-0.001
-0.001
 time-0.001
Token "
Token ID366
Feature activation-4.78e+00

Pos logit contributions
izing+0.012
ning+0.011
yles+0.011
king+0.011
rily+0.011
Neg logit contributions
 am-0.006
 done-0.005
-0.005
 story-0.005
 big-0.005
TokenNo
Token ID2949
Feature activation+3.89e-01

Pos logit contributions
izing+0.102
rily+0.097
yles+0.096
ellery+0.095
ning+0.092
Neg logit contributions
 am-0.115
-0.111
 to-0.101
 time-0.100
 done-0.100
Token T
Token ID309
Feature activation-4.73e+00

Pos logit contributions
 am+0.006
 done+0.006
+0.006
 story+0.005
 big+0.005
Neg logit contributions
izing-0.011
yles-0.011
ning-0.010
king-0.010
ellery-0.010
Tokenresp
Token ID4363
Feature activation-1.24e+01

Pos logit contributions
izing+0.092
yles+0.090
ning+0.085
ellery+0.084
rily+0.083
Neg logit contributions
 am-0.115
-0.112
 story-0.109
 done-0.109
 to-0.107
Tokenassing
Token ID19696
Feature activation-1.53e+00

Pos logit contributions
rily+0.292
bul+0.289
izing+0.275
bly+0.270
ants+0.261
Neg logit contributions
-0.257
 am-0.250
 find-0.242
 to-0.233
-0.225
Token".
Token ID1911
Feature activation+7.05e-01

Pos logit contributions
izing+0.039
yles+0.037
ellery+0.036
ning+0.036
rily+0.036
Neg logit contributions
 am-0.029
-0.027
 done-0.027
 to-0.025
 story-0.025
Token And
Token ID843
Feature activation-8.42e-01

Pos logit contributions
 done+0.014
 am+0.013
 whole+0.012
 story+0.011
 rest+0.011
Neg logit contributions
rily-0.017
izing-0.016
yles-0.016
king-0.015
ender-0.015
Token behind
Token ID2157
Feature activation-1.16e+00

Pos logit contributions
izing+0.021
yles+0.021
rily+0.020
king+0.020
ning+0.020
Neg logit contributions
 am-0.015
 done-0.013
 story-0.013
 whole-0.013
-0.012
Token the
Token ID262
Feature activation+3.64e-01

Pos logit contributions
izing+0.032
yles+0.031
ning+0.031
king+0.030
ellery+0.030
Neg logit contributions
 am-0.019
 done-0.017
-0.017
 story-0.016
 big-0.016
Token a
Token ID257
Feature activation-3.81e-01

Pos logit contributions
 am+0.006
+0.005
 done+0.005
 big+0.005
 to+0.005
Neg logit contributions
izing-0.021
yles-0.021
king-0.020
ning-0.020
rily-0.020
Token strange
Token ID6283
Feature activation-1.04e+00

Pos logit contributions
izing+0.013
yles+0.012
ning+0.012
ellery+0.012
rily+0.012
Neg logit contributions
 am-0.004
 big-0.004
-0.004
 story-0.004
 done-0.004
Token,
Token ID11
Feature activation-4.43e+00

Pos logit contributions
izing+0.027
ning+0.026
yles+0.025
king+0.025
rily+0.025
Neg logit contributions
 am-0.019
 done-0.018
-0.017
 story-0.016
 big-0.016
Token raspberry
Token ID38973
Feature activation-1.88e+00

Pos logit contributions
izing+0.131
yles+0.127
ning+0.125
king+0.124
ellery+0.124
Neg logit contributions
 am-0.064
 done-0.058
-0.058
 story-0.054
 big-0.053
Token-
Token ID12
Feature activation-8.52e+00

Pos logit contributions
izing+0.053
ning+0.051
yles+0.050
ellery+0.050
king+0.049
Neg logit contributions
 am-0.029
 done-0.027
-0.026
 story-0.024
ossible-0.024
Tokencol
Token ID4033
Feature activation-1.22e+01

Pos logit contributions
izing+0.179
yles+0.172
king+0.167
rily+0.164
ning+0.163
Neg logit contributions
-0.199
 am-0.193
 to-0.192
 big-0.189
 done-0.178
Tokenoured
Token ID8167
Feature activation-1.92e+00

Pos logit contributions
izing+0.220
bly+0.212
bul+0.209
shadow+0.203
pole+0.202
Neg logit contributions
 to-0.262
 done-0.261
-0.235
 am-0.233
ossible-0.230
Token object
Token ID2134
Feature activation-3.23e+00

Pos logit contributions
izing+0.045
ning+0.042
yles+0.042
ellery+0.042
king+0.041
Neg logit contributions
 am-0.040
 done-0.037
-0.037
 story-0.035
 big-0.034
Token hiding
Token ID11816
Feature activation-1.48e+00

Pos logit contributions
izing+0.111
yles+0.109
rily+0.105
king+0.105
ellery+0.105
Neg logit contributions
 am-0.030
-0.027
 done-0.026
 to-0.026
 big-0.025
Token under
Token ID739
Feature activation-3.43e-01

Pos logit contributions
izing+0.035
rily+0.033
yles+0.033
ning+0.033
ellery+0.033
Neg logit contributions
 am-0.031
 done-0.029
-0.028
 story-0.028
 big-0.026
Token a
Token ID257
Feature activation+1.98e+00

Pos logit contributions
izing+0.012
yles+0.011
ning+0.011
king+0.011
ellery+0.011
Neg logit contributions
 am-0.004
-0.003
 done-0.003
 story-0.003
 big-0.003
Token,
Token ID11
Feature activation-3.27e+00

Pos logit contributions
izing+0.045
ning+0.044
yles+0.043
king+0.043
ants+0.043
Neg logit contributions
 am-0.011
 done-0.010
 story-0.010
-0.009
 big-0.008
Token he
Token ID339
Feature activation+9.86e-01

Pos logit contributions
izing+0.093
yles+0.090
ning+0.088
ellery+0.088
king+0.088
Neg logit contributions
 am-0.052
-0.049
 done-0.047
 big-0.045
 to-0.044
Token saw
Token ID2497
Feature activation-1.48e-01

Pos logit contributions
 am+0.012
 story+0.011
 done+0.011
 lesson+0.010
+0.010
Neg logit contributions
ellery-0.026
 chick-0.026
ning-0.025
yles-0.025
bug-0.025
Token a
Token ID257
Feature activation-7.70e-01

Pos logit contributions
ning+0.005
izing+0.004
yles+0.004
ellery+0.004
ants+0.004
Neg logit contributions
 am-0.002
 done-0.002
 story-0.001
-0.001
 own-0.001
Token red
Token ID2266
Feature activation-3.73e+00

Pos logit contributions
izing+0.029
yles+0.029
ellery+0.028
rily+0.028
ants+0.028
Neg logit contributions
 am-0.005
 big-0.004
 story-0.004
-0.004
 done-0.004
Token rad
Token ID2511
Feature activation-1.18e+01

Pos logit contributions
yles+0.093
izing+0.090
ellery+0.086
king+0.084
rily+0.084
Neg logit contributions
 am-0.076
 big-0.073
 story-0.073
-0.072
 to-0.070
Tokenish
Token ID680
Feature activation-3.71e+00

Pos logit contributions
izing+0.200
yles+0.195
king+0.181
ivating+0.180
rily+0.180
Neg logit contributions
 am-0.317
-0.303
 big-0.297
 to-0.295
 done-0.287
Token in
Token ID287
Feature activation-7.09e-01

Pos logit contributions
izing+0.116
yles+0.113
ning+0.110
king+0.110
ellery+0.110
Neg logit contributions
 am-0.048
-0.043
 done-0.043
 story-0.040
 big-0.039
Token the
Token ID262
Feature activation+1.39e+00

Pos logit contributions
izing+0.024
yles+0.023
ning+0.023
king+0.023
ellery+0.023
Neg logit contributions
 am-0.008
 done-0.007
-0.007
 story-0.006
 big-0.006
Token garden
Token ID11376
Feature activation+3.30e-01

Pos logit contributions
 am+0.023
 done+0.022
 lesson+0.019
ossible+0.018
 story+0.018
Neg logit contributions
ning-0.035
burn-0.033
 chick-0.032
ting-0.032
ellery-0.031
Token.
Token ID13
Feature activation-2.54e-01

Pos logit contributions
 am+0.004
 done+0.003
 story+0.003
 lesson+0.003
 bad+0.003
Neg logit contributions
izing-0.011
ning-0.011
king-0.010
bing-0.010
ting-0.010
Token,
Token ID11
Feature activation-2.77e+00

Pos logit contributions
izing+0.035
yles+0.033
ning+0.033
bing+0.033
king+0.033
Neg logit contributions
 am-0.010
 done-0.009
 story-0.009
-0.007
 own-0.007
Token Benny
Token ID44275
Feature activation-6.29e-01

Pos logit contributions
izing+0.068
yles+0.064
ning+0.063
king+0.062
bing+0.062
Neg logit contributions
 am-0.054
 done-0.052
 story-0.049
-0.047
 big-0.045
Token saw
Token ID2497
Feature activation-2.66e-01

Pos logit contributions
ning+0.018
izing+0.017
ellery+0.017
 chick+0.017
bing+0.017
Neg logit contributions
 am-0.008
 done-0.008
 story-0.007
-0.006
 lesson-0.006
Token a
Token ID257
Feature activation-6.53e-01

Pos logit contributions
ning+0.008
izing+0.008
yles+0.008
ellery+0.008
bing+0.008
Neg logit contributions
 am-0.003
 done-0.003
 story-0.003
 own-0.002
 time-0.002
Token big
Token ID1263
Feature activation-3.78e+00

Pos logit contributions
izing+0.024
yles+0.024
ellery+0.023
rily+0.023
ning+0.023
Neg logit contributions
 am-0.005
 big-0.004
-0.004
 story-0.004
 done-0.004
Token rad
Token ID2511
Feature activation-1.17e+01

Pos logit contributions
yles+0.119
izing+0.115
king+0.112
ants+0.112
ellery+0.112
Neg logit contributions
 big-0.052
 am-0.051
 story-0.048
 bad-0.047
-0.046
Tokenish
Token ID680
Feature activation-3.49e+00

Pos logit contributions
izing+0.196
yles+0.190
king+0.176
ivating+0.175
rily+0.173
Neg logit contributions
 am-0.315
-0.302
 big-0.297
 to-0.295
 done-0.288
Token and
Token ID290
Feature activation-2.82e+00

Pos logit contributions
izing+0.107
yles+0.105
ellery+0.102
ning+0.101
king+0.101
Neg logit contributions
 am-0.047
-0.042
 done-0.042
 story-0.040
 big-0.040
Token he
Token ID339
Feature activation+8.69e-01

Pos logit contributions
izing+0.081
yles+0.076
ning+0.075
rily+0.075
ellery+0.075
Neg logit contributions
 am-0.042
 done-0.038
 story-0.038
-0.034
 time-0.034
Token wanted
Token ID2227
Feature activation+1.58e+00

Pos logit contributions
 am+0.014
 done+0.012
 story+0.012
+0.011
 time+0.010
Neg logit contributions
izing-0.024
ellery-0.023
ning-0.023
king-0.022
ants-0.022
Token to
Token ID284
Feature activation-4.37e-01

Pos logit contributions
 am+0.014
 story+0.011
 done+0.011
ossible+0.009
+0.008
Neg logit contributions
ning-0.053
ellery-0.053
izing-0.053
yles-0.052
ries-0.051
Token pond
Token ID16723
Feature activation+1.79e+00

Pos logit contributions
 am+0.027
 done+0.026
ossible+0.025
 story+0.024
+0.024
Neg logit contributions
izing-0.036
ning-0.035
ting-0.033
ivating-0.033
bing-0.033
Token.
Token ID13
Feature activation+7.94e-02

Pos logit contributions
 am+0.022
 done+0.018
 story+0.017
ossible+0.016
 bad+0.015
Neg logit contributions
izing-0.055
ning-0.053
rily-0.053
king-0.053
bing-0.052
Token It
Token ID632
Feature activation+5.26e-01

Pos logit contributions
 am+0.001
 done+0.001
 story+0.001
 bad+0.001
+0.001
Neg logit contributions
izing-0.002
ning-0.002
rily-0.002
yles-0.002
king-0.002
Token was
Token ID373
Feature activation-3.80e-01

Pos logit contributions
 am+0.004
 done+0.003
 story+0.003
+0.002
ossible+0.002
Neg logit contributions
izing-0.019
ning-0.019
yles-0.018
rily-0.018
king-0.018
Token a
Token ID257
Feature activation-4.35e-02

Pos logit contributions
izing+0.013
ning+0.012
yles+0.012
king+0.012
ellery+0.012
Neg logit contributions
 am-0.004
 done-0.003
-0.003
 story-0.003
 big-0.003
Token tort
Token ID7619
Feature activation-1.17e+01

Pos logit contributions
izing+0.001
yles+0.001
ning+0.001
ellery+0.001
king+0.001
Neg logit contributions
 am-0.001
-0.000
 done-0.000
 big-0.000
 story-0.000
Tokenoise
Token ID25678
Feature activation-1.75e+00

Pos logit contributions
izing+0.198
rily+0.194
ender+0.179
ksh+0.171
yles+0.169
Neg logit contributions
 am-0.327
'm-0.290
 done-0.284
-0.273
ossible-0.268
Token!
Token ID0
Feature activation+3.71e-01

Pos logit contributions
izing+0.057
yles+0.056
ning+0.054
king+0.054
rily+0.054
Neg logit contributions
 am-0.020
-0.018
 done-0.017
 to-0.017
 big-0.017
Token The
Token ID383
Feature activation-1.08e+00

Pos logit contributions
 am+0.004
 done+0.004
 story+0.004
+0.003
 big+0.003
Neg logit contributions
izing-0.012
ning-0.012
yles-0.011
rily-0.011
king-0.011
Token all
Token ID477
Feature activation-1.20e+00

Pos logit contributions
izing+0.028
yles+0.027
ning+0.027
king+0.026
ellery+0.026
Neg logit contributions
 am-0.020
-0.019
 done-0.018
 story-0.018
 big-0.018
Tokenigator
Token ID23823
Feature activation-1.64e+00

Pos logit contributions
izing+0.019
yles+0.018
ning+0.017
king+0.017
ellery+0.017
Neg logit contributions
 am-0.034
 done-0.032
-0.032
 story-0.031
 big-0.031
Token day
Token ID1110
Feature activation+1.07e-01

Pos logit contributions
ning+0.048
izing+0.047
ting+0.044
bing+0.044
ants+0.043
Neg logit contributions
 am-0.031
 done-0.029
 story-0.027
 own-0.027
 bad-0.027
Token,
Token ID11
Feature activation-2.94e+00

Pos logit contributions
 am+0.001
 done+0.001
+0.001
 story+0.001
 big+0.001
Neg logit contributions
izing-0.004
ning-0.004
yles-0.004
king-0.004
rily-0.004
Token a
Token ID257
Feature activation-1.42e+00

Pos logit contributions
izing+0.067
yles+0.065
ning+0.064
king+0.063
ellery+0.063
Neg logit contributions
 am-0.063
-0.059
 done-0.059
 big-0.056
 story-0.056
Token chocolate
Token ID11311
Feature activation-3.38e+00

Pos logit contributions
izing+0.048
yles+0.047
ellery+0.046
rily+0.046
ning+0.046
Neg logit contributions
 am-0.015
-0.014
 big-0.013
 done-0.013
 story-0.013
Token-
Token ID12
Feature activation-8.24e+00

Pos logit contributions
izing+0.085
yles+0.081
ning+0.081
king+0.079
ellery+0.078
Neg logit contributions
 am-0.064
 done-0.060
-0.059
 story-0.056
 big-0.055
Tokencol
Token ID4033
Feature activation-1.16e+01

Pos logit contributions
izing+0.165
yles+0.161
rily+0.154
king+0.152
ellery+0.152
Neg logit contributions
-0.207
 am-0.200
 to-0.197
 big-0.187
 done-0.185
Tokenoured
Token ID8167
Feature activation-2.52e+00

Pos logit contributions
izing+0.233
bly+0.220
bul+0.219
 spe+0.200
quet+0.199
Neg logit contributions
 to-0.247
 done-0.219
 back-0.217
ossible-0.217
-0.214
Token whip
Token ID22972
Feature activation-2.56e+00

Pos logit contributions
izing+0.058
yles+0.057
king+0.054
ellery+0.054
ning+0.054
Neg logit contributions
 am-0.053
-0.051
 done-0.050
 big-0.049
 story-0.049
Token named
Token ID3706
Feature activation-5.37e+00

Pos logit contributions
izing+0.083
yles+0.081
ning+0.080
king+0.079
ellery+0.079
Neg logit contributions
 am-0.029
 done-0.026
-0.026
 story-0.024
 big-0.023
Token C
Token ID327
Feature activation-4.78e+00

Pos logit contributions
izing+0.136
yles+0.130
ellery+0.126
rily+0.124
bul+0.124
Neg logit contributions
-0.118
 big-0.104
 am-0.104
 to-0.103
-0.098
Tokenheddar
Token ID44937
Feature activation-1.68e+00

Pos logit contributions
izing+0.102
ning+0.098
king+0.097
yles+0.097
ellery+0.097
Neg logit contributions
 am-0.107
 done-0.101
-0.096
 story-0.096
 bad-0.096
Token Lucy
Token ID22162
Feature activation+1.29e-01

Pos logit contributions
izing+0.064
yles+0.061
ning+0.060
rily+0.058
king+0.058
Neg logit contributions
 am-0.065
 done-0.062
-0.061
 story-0.059
 big-0.058
Token noticed
Token ID6810
Feature activation+6.60e-01

Pos logit contributions
 am+0.001
 story+0.001
 done+0.001
+0.001
 lesson+0.001
Neg logit contributions
ning-0.004
yles-0.004
izing-0.004
king-0.004
ellery-0.004
Token the
Token ID262
Feature activation+1.28e+00

Pos logit contributions
 am+0.007
 done+0.006
+0.006
 story+0.006
 big+0.005
Neg logit contributions
izing-0.022
yles-0.021
ning-0.021
ellery-0.021
king-0.021
Token weather
Token ID6193
Feature activation-1.96e+00

Pos logit contributions
 am+0.020
+0.018
 done+0.018
ossible+0.017
 learned+0.015
Neg logit contributions
izing-0.035
ning-0.035
burn-0.033
bul-0.033
king-0.033
Token was
Token ID373
Feature activation-7.23e-01

Pos logit contributions
izing+0.063
yles+0.061
ning+0.061
king+0.060
ellery+0.060
Neg logit contributions
 am-0.023
 done-0.021
-0.021
 story-0.019
 big-0.018
Token uncom
Token ID8820
Feature activation-1.16e+01

Pos logit contributions
izing+0.020
ning+0.019
yles+0.019
king+0.018
rily+0.018
Neg logit contributions
 am-0.012
-0.011
 done-0.011
 story-0.010
 big-0.010
Tokenfort
Token ID3319
Feature activation-4.64e+00

Pos logit contributions
yles+0.258
rily+0.252
ning+0.230
ants+0.227
ries+0.227
Neg logit contributions
 own-0.236
 done-0.227
 to-0.224
 am-0.221
 find-0.219
Tokenably
Token ID1346
Feature activation-4.90e-01

Pos logit contributions
izing+0.078
yles+0.073
ning+0.071
king+0.070
ellery+0.070
Neg logit contributions
 am-0.127
 done-0.121
-0.121
 story-0.117
 big-0.115
Token hot
Token ID3024
Feature activation-1.67e+00

Pos logit contributions
izing+0.014
ning+0.014
rily+0.013
king+0.013
yles+0.013
Neg logit contributions
 am-0.007
-0.007
 done-0.006
 story-0.006
ossible-0.006
Token.
Token ID13
Feature activation-2.20e-01

Pos logit contributions
izing+0.064
yles+0.062
ning+0.061
king+0.061
ellery+0.061
Neg logit contributions
 am-0.010
-0.008
 done-0.008
 story-0.006
 big-0.006
Token She
Token ID1375
Feature activation+1.54e+00

Pos logit contributions
izing+0.007
yles+0.007
ning+0.007
ellery+0.006
rily+0.006
Neg logit contributions
 am-0.003
 done-0.003
-0.002
 story-0.002
 big-0.002
Tokenmy
Token ID1820
Feature activation+2.31e-01

Pos logit contributions
izing+0.043
yles+0.042
rily+0.042
king+0.041
ellery+0.040
Neg logit contributions
 am-0.025
 done-0.025
-0.024
 to-0.023
 big-0.022
Token!
Token ID0
Feature activation-7.53e-01

Pos logit contributions
 am+0.002
 done+0.002
+0.002
 story+0.002
 big+0.002
Neg logit contributions
izing-0.008
yles-0.007
ning-0.007
king-0.007
ellery-0.007
Token I
Token ID314
Feature activation-8.43e-01

Pos logit contributions
izing+0.026
ellery+0.025
yles+0.025
king+0.025
bing+0.024
Neg logit contributions
-0.010
 am-0.009
 big-0.008
 He-0.007
 to-0.007
Token saw
Token ID2497
Feature activation-1.69e+00

Pos logit contributions
izing+0.025
yles+0.025
burn+0.025
ning+0.025
king+0.025
Neg logit contributions
 done-0.008
-0.008
 story-0.008
 am-0.008
 big-0.007
Token an
Token ID281
Feature activation-4.02e+00

Pos logit contributions
izing+0.060
king+0.058
rily+0.058
yles+0.057
ellery+0.057
Neg logit contributions
-0.015
 big-0.015
 to-0.015
 am-0.014
 done-0.014
Token ostr
Token ID42387
Feature activation-1.15e+01

Pos logit contributions
yles+0.092
izing+0.089
king+0.085
etti+0.082
rily+0.081
Neg logit contributions
 big-0.090
 bad-0.088
 done-0.087
 am-0.086
 story-0.084
Tokenich
Token ID488
Feature activation-3.23e+00

Pos logit contributions
rily+0.184
izing+0.179
yles+0.172
ivating+0.163
ellery+0.157
Neg logit contributions
 am-0.317
-0.302
 done-0.300
 to-0.296
 story-0.295
Token in
Token ID287
Feature activation+9.48e-02

Pos logit contributions
yles+0.093
izing+0.093
rily+0.089
ellery+0.089
ants+0.088
Neg logit contributions
 am-0.051
 done-0.048
-0.047
 to-0.047
 big-0.046
Token our
Token ID674
Feature activation+1.15e+00

Pos logit contributions
 big+0.001
+0.001
 am+0.001
 bad+0.001
 story+0.001
Neg logit contributions
king-0.004
yles-0.004
izing-0.004
ants-0.003
ksh-0.003
Token backyard
Token ID24296
Feature activation+2.59e-02

Pos logit contributions
 am+0.018
 done+0.015
+0.015
 story+0.014
'm+0.013
Neg logit contributions
ning-0.032
ellery-0.032
izing-0.030
king-0.029
bing-0.029
Token!"
Token ID2474
Feature activation+1.53e-01

Pos logit contributions
 am+0.000
 done+0.000
+0.000
 story+0.000
 bad+0.000
Neg logit contributions
izing-0.001
ning-0.001
yles-0.001
king-0.001
ellery-0.001
Token saw
Token ID2497
Feature activation-2.27e-01

Pos logit contributions
ning+0.027
 chick+0.026
ellery+0.026
bug+0.026
king+0.025
Neg logit contributions
 am-0.012
 story-0.011
 done-0.011
 lesson-0.010
 bad-0.010
Token a
Token ID257
Feature activation-4.46e-01

Pos logit contributions
ning+0.007
izing+0.007
yles+0.007
ellery+0.006
ants+0.006
Neg logit contributions
 am-0.003
 done-0.003
 story-0.002
-0.002
 own-0.002
Token big
Token ID1263
Feature activation-3.62e+00

Pos logit contributions
izing+0.017
yles+0.016
ellery+0.016
ning+0.016
rily+0.016
Neg logit contributions
 am-0.003
-0.003
 big-0.002
 done-0.002
 story-0.002
Token,
Token ID11
Feature activation-5.57e+00

Pos logit contributions
yles+0.119
izing+0.116
king+0.114
ants+0.113
ellery+0.113
Neg logit contributions
 am-0.044
 big-0.043
 story-0.040
 bad-0.039
-0.039
Token red
Token ID2266
Feature activation-3.36e+00

Pos logit contributions
izing+0.167
yles+0.165
ning+0.160
ellery+0.159
king+0.159
Neg logit contributions
 am-0.079
 done-0.072
-0.072
 big-0.071
 story-0.068
Token rad
Token ID2511
Feature activation-1.15e+01

Pos logit contributions
yles+0.076
izing+0.076
ellery+0.071
king+0.071
ning+0.070
Neg logit contributions
 am-0.074
-0.069
 big-0.069
 story-0.068
 to-0.067
Tokenish
Token ID680
Feature activation-3.61e+00

Pos logit contributions
izing+0.188
yles+0.178
rily+0.167
king+0.166
ivating+0.163
Neg logit contributions
 am-0.322
-0.305
 big-0.298
 to-0.298
 done-0.294
Token.
Token ID13
Feature activation-5.85e-01

Pos logit contributions
izing+0.116
yles+0.111
ning+0.111
king+0.110
ellery+0.109
Neg logit contributions
 am-0.043
 done-0.039
-0.038
 story-0.035
 big-0.034
Token He
Token ID679
Feature activation+1.11e+00

Pos logit contributions
izing+0.019
ning+0.019
rily+0.019
yles+0.018
ants+0.018
Neg logit contributions
 am-0.006
 done-0.005
 story-0.004
 bad-0.004
 time-0.004
Token wanted
Token ID2227
Feature activation+6.86e-01

Pos logit contributions
 am+0.015
 done+0.013
 story+0.013
+0.012
 bad+0.011
Neg logit contributions
izing-0.033
yles-0.032
ning-0.032
ellery-0.032
king-0.031
Token to
Token ID284
Feature activation-1.01e+00

Pos logit contributions
 am+0.005
 done+0.004
 story+0.004
ossible+0.003
+0.003
Neg logit contributions
izing-0.024
ning-0.024
ellery-0.023
yles-0.023
ries-0.023
Token suddenly
Token ID6451
Feature activation+8.65e-02

Pos logit contributions
 am+0.029
 done+0.028
+0.026
 story+0.025
 big+0.024
Neg logit contributions
yles-0.053
izing-0.052
ellery-0.050
ning-0.050
rily-0.049
Token,
Token ID11
Feature activation-2.01e+00

Pos logit contributions
 am+0.001
 done+0.001
+0.001
 story+0.001
 own+0.001
Neg logit contributions
izing-0.002
yles-0.002
ning-0.002
ellery-0.002
rily-0.002
Token a
Token ID257
Feature activation-1.07e+00

Pos logit contributions
izing+0.053
yles+0.052
rily+0.051
ellery+0.050
ning+0.050
Neg logit contributions
 am-0.033
 done-0.032
 story-0.029
-0.028
 time-0.027
Token brightly
Token ID35254
Feature activation-2.47e+00

Pos logit contributions
izing+0.035
ning+0.034
yles+0.034
king+0.034
rily+0.033
Neg logit contributions
 am-0.011
 done-0.010
-0.010
 story-0.009
 to-0.008
Token-
Token ID12
Feature activation-8.83e+00

Pos logit contributions
izing+0.054
yles+0.053
ellery+0.051
ning+0.051
king+0.051
Neg logit contributions
 am-0.054
 done-0.052
-0.051
 story-0.049
 big-0.049
Tokencol
Token ID4033
Feature activation-1.15e+01

Pos logit contributions
izing+0.234
yles+0.219
arians+0.216
bing+0.215
ning+0.214
Neg logit contributions
-0.175
 big-0.169
 am-0.167
 to-0.167
 bad-0.151
Tokenoured
Token ID8167
Feature activation-2.21e+00

Pos logit contributions
izing+0.215
bing+0.197
bly+0.192
rily+0.187
yles+0.183
Neg logit contributions
 to-0.254
 done-0.250
 am-0.235
ossible-0.231
 back-0.229
Token belt
Token ID10999
Feature activation-3.55e+00

Pos logit contributions
izing+0.054
yles+0.052
ning+0.051
king+0.050
ellery+0.050
Neg logit contributions
 am-0.043
 done-0.040
-0.040
 story-0.039
 big-0.038
Token caught
Token ID4978
Feature activation-3.50e+00

Pos logit contributions
izing+0.106
yles+0.102
ning+0.101
king+0.100
ellery+0.099
Neg logit contributions
 am-0.050
 done-0.046
-0.046
 story-0.043
 big-0.042
Token her
Token ID607
Feature activation+2.51e+00

Pos logit contributions
izing+0.115
yles+0.113
shadow+0.109
king+0.109
arians+0.109
Neg logit contributions
 to-0.037
 big-0.036
-0.035
 am-0.035
 done-0.034
Token eye
Token ID4151
Feature activation-5.87e-01

Pos logit contributions
 am+0.038
 done+0.035
+0.034
 story+0.032
 bad+0.029
Neg logit contributions
izing-0.071
ning-0.070
king-0.069
rily-0.068
ellery-0.067
Token spotted
Token ID13489
Feature activation-5.97e-01

Pos logit contributions
izing+0.038
yles+0.038
ning+0.037
king+0.037
ellery+0.037
Neg logit contributions
 am-0.018
 story-0.016
 done-0.014
-0.014
 time-0.013
Token a
Token ID257
Feature activation-3.04e-01

Pos logit contributions
izing+0.020
ning+0.019
yles+0.019
ellery+0.019
rily+0.019
Neg logit contributions
 am-0.007
 done-0.006
 story-0.005
-0.005
 time-0.004
Token big
Token ID1263
Feature activation-3.29e+00

Pos logit contributions
izing+0.011
yles+0.011
ellery+0.011
ning+0.011
rily+0.011
Neg logit contributions
 am-0.002
 big-0.002
-0.002
 story-0.002
 done-0.002
Token,
Token ID11
Feature activation-5.40e+00

Pos logit contributions
yles+0.111
izing+0.109
ants+0.105
king+0.105
ellery+0.104
Neg logit contributions
 am-0.037
 big-0.036
 story-0.034
-0.033
 done-0.032
Token brown
Token ID7586
Feature activation-3.24e+00

Pos logit contributions
izing+0.150
yles+0.148
ning+0.144
ellery+0.142
king+0.142
Neg logit contributions
 am-0.088
 big-0.083
-0.082
 done-0.082
 story-0.079
Token rad
Token ID2511
Feature activation-1.14e+01

Pos logit contributions
yles+0.080
izing+0.080
ellery+0.075
king+0.074
ants+0.073
Neg logit contributions
 am-0.064
 big-0.061
-0.061
 story-0.061
 to-0.059
Tokenish
Token ID680
Feature activation-3.53e+00

Pos logit contributions
izing+0.192
yles+0.182
rily+0.170
king+0.169
ivating+0.169
Neg logit contributions
 am-0.315
-0.298
 big-0.293
 to-0.292
 done-0.286
Token.
Token ID13
Feature activation+4.62e-01

Pos logit contributions
izing+0.122
yles+0.120
ellery+0.116
ning+0.116
king+0.115
Neg logit contributions
 am-0.033
-0.029
 done-0.028
 to-0.027
 story-0.027
Token Benny
Token ID44275
Feature activation-1.11e+00

Pos logit contributions
 done+0.006
 am+0.006
 story+0.005
 bad+0.005
 time+0.004
Neg logit contributions
izing-0.014
ning-0.014
rily-0.013
yles-0.013
bing-0.013
Token loved
Token ID6151
Feature activation+7.15e-01

Pos logit contributions
izing+0.034
ning+0.033
king+0.032
ellery+0.032
bing+0.032
Neg logit contributions
 am-0.015
 done-0.013
 story-0.012
-0.012
 time-0.011
Token rad
Token ID2511
Feature activation-9.53e+00

Pos logit contributions
 am+0.010
 done+0.009
+0.008
 story+0.008
 big+0.007
Neg logit contributions
izing-0.022
yles-0.021
ning-0.021
ellery-0.021
king-0.021
Token sudden
Token ID4802
Feature activation-5.38e-01

Pos logit contributions
 am+0.008
 big+0.008
+0.008
 story+0.008
 bad+0.008
Neg logit contributions
izing-0.009
yles-0.009
rily-0.009
ellery-0.009
ning-0.009
Token,
Token ID11
Feature activation-3.08e+00

Pos logit contributions
izing+0.020
yles+0.019
ning+0.019
ellery+0.019
king+0.019
Neg logit contributions
 am-0.004
 done-0.003
-0.003
 story-0.003
 big-0.002
Token she
Token ID673
Feature activation+1.10e+00

Pos logit contributions
izing+0.082
yles+0.078
ning+0.076
ellery+0.075
rily+0.074
Neg logit contributions
 am-0.051
 story-0.049
 done-0.048
-0.044
ossible-0.043
Token saw
Token ID2497
Feature activation+2.24e-01

Pos logit contributions
 am+0.014
 story+0.012
+0.012
 done+0.011
 lesson+0.011
Neg logit contributions
yles-0.033
king-0.032
ning-0.032
izing-0.032
ellery-0.031
Token a
Token ID257
Feature activation-6.32e-01

Pos logit contributions
 am+0.003
 done+0.002
 story+0.002
+0.002
 own+0.002
Neg logit contributions
izing-0.007
yles-0.007
ning-0.007
ellery-0.007
ants-0.007
Token rad
Token ID2511
Feature activation-1.14e+01

Pos logit contributions
izing+0.022
yles+0.022
ellery+0.021
rily+0.021
ning+0.021
Neg logit contributions
 am-0.006
 big-0.006
 story-0.005
-0.005
 done-0.005
Tokenish
Token ID680
Feature activation-3.57e+00

Pos logit contributions
izing+0.184
yles+0.177
king+0.165
rily+0.164
ellery+0.162
Neg logit contributions
 am-0.316
-0.300
 big-0.296
 done-0.294
 to-0.292
Token!
Token ID0
Feature activation+2.88e-01

Pos logit contributions
izing+0.116
yles+0.114
ning+0.110
ellery+0.110
king+0.110
Neg logit contributions
 am-0.042
-0.037
 done-0.036
 story-0.034
 big-0.034
Token She
Token ID1375
Feature activation+1.38e+00

Pos logit contributions
 done+0.005
 am+0.005
 story+0.005
 bad+0.004
 own+0.004
Neg logit contributions
izing-0.007
yles-0.007
ning-0.007
rily-0.007
ivating-0.007
Token was
Token ID373
Feature activation+7.41e-02

Pos logit contributions
 am+0.014
 done+0.012
+0.012
 story+0.011
 big+0.010
Neg logit contributions
izing-0.047
yles-0.045
ning-0.045
king-0.044
ellery-0.044
Token really
Token ID1107
Feature activation+1.16e+00

Pos logit contributions
 am+0.001
 done+0.001
+0.001
 big+0.001
 to+0.001
Neg logit contributions
izing-0.003
yles-0.002
ning-0.002
king-0.002
ellery-0.002
Token legs
Token ID7405
Feature activation-2.50e+00

Pos logit contributions
izing+0.020
ning+0.019
king+0.019
yles+0.018
ellery+0.018
Neg logit contributions
 am-0.025
 done-0.024
-0.023
 story-0.023
 big-0.022
Token.
Token ID13
Feature activation+8.87e-01

Pos logit contributions
izing+0.094
yles+0.091
ning+0.091
king+0.091
rily+0.090
Neg logit contributions
 am-0.015
 done-0.012
-0.011
 story-0.010
 big-0.009
Token It
Token ID632
Feature activation-4.53e-01

Pos logit contributions
 done+0.011
 am+0.011
 story+0.009
 bad+0.008
 big+0.007
Neg logit contributions
rily-0.028
yles-0.027
izing-0.027
ning-0.026
ants-0.026
Token is
Token ID318
Feature activation-4.29e-01

Pos logit contributions
izing+0.016
yles+0.016
ning+0.016
king+0.015
rily+0.015
Neg logit contributions
 am-0.003
 done-0.003
-0.003
 story-0.002
 big-0.002
Token an
Token ID281
Feature activation-2.40e+00

Pos logit contributions
izing+0.014
yles+0.014
ellery+0.013
rily+0.013
ants+0.013
Neg logit contributions
 am-0.005
 big-0.005
 done-0.005
-0.005
 to-0.004
Token ostr
Token ID42387
Feature activation-1.13e+01

Pos logit contributions
yles+0.059
izing+0.058
king+0.056
ning+0.054
etti+0.053
Neg logit contributions
 big-0.047
 done-0.046
 bad-0.046
 story-0.045
 am-0.045
Tokenich
Token ID488
Feature activation-2.92e+00

Pos logit contributions
izing+0.166
rily+0.161
yles+0.159
ivating+0.148
ellery+0.144
Neg logit contributions
 am-0.326
 done-0.310
-0.309
 story-0.307
 big-0.299
Token.
Token ID13
Feature activation+6.02e-01

Pos logit contributions
izing+0.114
yles+0.112
rily+0.109
king+0.109
ellery+0.108
Neg logit contributions
 am-0.017
-0.014
 done-0.012
 to-0.011
 story-0.011
Token
Token ID198
Feature activation+1.12e-01

Pos logit contributions
 am+0.006
 done+0.006
 story+0.005
 bad+0.004
 big+0.004
Neg logit contributions
izing-0.020
yles-0.020
rily-0.020
ning-0.019
king-0.019
Token
Token ID198
Feature activation-1.81e+00

Pos logit contributions
 done+0.001
 am+0.001
 bad+0.000
 story+0.000
 way+0.000
Neg logit contributions
izing-0.004
yles-0.004
rily-0.004
ning-0.004
ivating-0.004
Token"
Token ID1
Feature activation-7.08e+00

Pos logit contributions
yles+0.049
ning+0.048
izing+0.048
ellery+0.048
bul+0.047
Neg logit contributions
 am-0.032
-0.032
 big-0.029
 done-0.028
 time-0.027
Token,
Token ID11
Feature activation-3.12e+00

Pos logit contributions
izing+0.040
yles+0.039
rily+0.038
ning+0.038
ellery+0.038
Neg logit contributions
 am-0.005
-0.004
 done-0.004
 to-0.003
 big-0.003
Token she
Token ID673
Feature activation+1.35e+00

Pos logit contributions
izing+0.090
yles+0.087
rily+0.087
ning+0.087
king+0.086
Neg logit contributions
 am-0.047
-0.047
 to-0.043
 big-0.043
 done-0.042
Token found
Token ID1043
Feature activation-1.07e+00

Pos logit contributions
 am+0.015
 done+0.014
 story+0.014
+0.013
 bad+0.012
Neg logit contributions
yles-0.041
ning-0.040
burn-0.039
king-0.039
izing-0.039
Token a
Token ID257
Feature activation+9.66e-01

Pos logit contributions
izing+0.038
yles+0.037
ning+0.037
king+0.036
ellery+0.036
Neg logit contributions
 am-0.009
 done-0.008
-0.008
 story-0.007
 big-0.007
Token big
Token ID1263
Feature activation-2.56e+00

Pos logit contributions
 am+0.009
+0.008
 done+0.008
 story+0.008
 big+0.008
Neg logit contributions
izing-0.033
yles-0.032
ning-0.032
ellery-0.032
king-0.032
Token rad
Token ID2511
Feature activation-1.12e+01

Pos logit contributions
yles+0.083
izing+0.082
ants+0.081
rily+0.080
king+0.080
Neg logit contributions
 am-0.032
 big-0.031
 story-0.029
 done-0.028
 to-0.027
Tokenish
Token ID680
Feature activation-3.48e+00

Pos logit contributions
izing+0.189
yles+0.181
rily+0.170
king+0.169
ivating+0.168
Neg logit contributions
 am-0.307
-0.289
 to-0.285
 big-0.284
 done-0.281
Token in
Token ID287
Feature activation-3.84e-01

Pos logit contributions
izing+0.109
yles+0.107
ning+0.104
ellery+0.103
king+0.103
Neg logit contributions
 am-0.044
-0.040
 done-0.039
 to-0.037
 story-0.037
Token her
Token ID607
Feature activation+2.68e+00

Pos logit contributions
izing+0.013
king+0.013
yles+0.013
ning+0.013
ants+0.013
Neg logit contributions
 am-0.004
-0.004
 big-0.003
 done-0.003
 to-0.003
Token garden
Token ID11376
Feature activation+7.38e-01

Pos logit contributions
 am+0.042
 done+0.039
 story+0.033
 lesson+0.033
 bad+0.032
Neg logit contributions
ning-0.073
ellery-0.073
bing-0.068
izing-0.068
yles-0.068
Token and
Token ID290
Feature activation-1.67e+00

Pos logit contributions
 am+0.007
 done+0.006
 bad+0.005
 story+0.005
+0.005
Neg logit contributions
izing-0.026
ning-0.025
king-0.024
ellery-0.024
bing-0.024
Token Spot
Token ID15899
Feature activation-2.25e+00

Pos logit contributions
izing+0.030
yles+0.028
ellery+0.028
rily+0.028
king+0.028
Neg logit contributions
 am-0.020
-0.020
 done-0.018
 big-0.018
 to-0.018
Token was
Token ID373
Feature activation-2.98e-01

Pos logit contributions
ning+0.062
izing+0.061
bing+0.061
yles+0.059
ellery+0.059
Neg logit contributions
 done-0.025
 am-0.024
 story-0.024
 lesson-0.021
 tum-0.021
Token a
Token ID257
Feature activation-1.78e+00

Pos logit contributions
izing+0.011
yles+0.011
ning+0.010
rily+0.010
ellery+0.010
Neg logit contributions
 am-0.002
-0.002
 done-0.002
 big-0.002
 story-0.002
Token very
Token ID845
Feature activation-9.59e-01

Pos logit contributions
izing+0.062
yles+0.062
rily+0.060
ants+0.060
ellery+0.060
Neg logit contributions
 am-0.019
 big-0.017
-0.017
 bad-0.015
 done-0.015
Token lovely
Token ID14081
Feature activation-1.19e+00

Pos logit contributions
izing+0.027
king+0.025
yles+0.025
ning+0.025
ellery+0.025
Neg logit contributions
 am-0.015
 done-0.013
-0.013
 story-0.012
 to-0.012
Token po
Token ID745
Feature activation-1.12e+01

Pos logit contributions
izing+0.031
ning+0.031
king+0.030
yles+0.029
burn+0.029
Neg logit contributions
 am-0.020
 done-0.019
-0.018
 story-0.016
 bad-0.016
Tokenoch
Token ID5374
Feature activation-3.72e+00

Pos logit contributions
rily+0.214
izing+0.211
yles+0.202
ellery+0.189
bul+0.187
Neg logit contributions
 am-0.275
-0.272
 to-0.251
ossible-0.249
 story-0.246
Token and
Token ID290
Feature activation-2.95e+00

Pos logit contributions
izing+0.124
yles+0.123
rily+0.118
ellery+0.118
ants+0.118
Neg logit contributions
 am-0.040
-0.039
 to-0.038
 done-0.034
 big-0.033
Token he
Token ID339
Feature activation+4.88e-01

Pos logit contributions
izing+0.101
yles+0.098
ning+0.097
king+0.096
ellery+0.096
Neg logit contributions
 am-0.029
 done-0.025
-0.025
 story-0.023
 big-0.021
Token always
Token ID1464
Feature activation+5.15e-01

Pos logit contributions
 am+0.006
 done+0.006
 story+0.006
+0.006
ossible+0.005
Neg logit contributions
izing-0.014
yles-0.013
ning-0.013
ellery-0.013
king-0.013
Token tried
Token ID3088
Feature activation+1.54e+00

Pos logit contributions
 am+0.006
 story+0.006
+0.006
 done+0.006
 big+0.005
Neg logit contributions
izing-0.016
yles-0.015
ning-0.015
king-0.015
ellery-0.015
Token the
Token ID262
Feature activation+1.71e-01

Pos logit contributions
 am+0.010
 done+0.010
 story+0.009
+0.009
 bad+0.008
Neg logit contributions
izing-0.024
yles-0.024
ning-0.024
ellery-0.023
rily-0.023
Token zoo
Token ID26626
Feature activation-9.59e-01

Pos logit contributions
 am+0.003
 done+0.003
+0.003
 story+0.003
 to+0.003
Neg logit contributions
izing-0.004
ning-0.004
yles-0.004
ellery-0.004
king-0.004
Token and
Token ID290
Feature activation-1.05e+00

Pos logit contributions
izing+0.023
ning+0.023
king+0.022
ellery+0.021
bing+0.021
Neg logit contributions
 am-0.018
 done-0.016
 bad-0.016
 story-0.015
 lesson-0.014
Token saw
Token ID2497
Feature activation+4.36e-02

Pos logit contributions
yles+0.032
ning+0.031
izing+0.030
ting+0.030
king+0.030
Neg logit contributions
 am-0.013
 story-0.012
 done-0.011
 time-0.010
 lesson-0.010
Token an
Token ID281
Feature activation-3.21e+00

Pos logit contributions
 am+0.000
 done+0.000
 story+0.000
+0.000
 time+0.000
Neg logit contributions
izing-0.001
ning-0.001
yles-0.001
ellery-0.001
rily-0.001
Token ostr
Token ID42387
Feature activation-1.12e+01

Pos logit contributions
yles+0.094
izing+0.091
king+0.089
burn+0.088
ning+0.086
Neg logit contributions
 big-0.053
 bad-0.049
 story-0.047
 am-0.046
-0.046
Tokenich
Token ID488
Feature activation-2.61e+00

Pos logit contributions
rily+0.190
izing+0.175
yles+0.174
ivating+0.160
ellery+0.159
Neg logit contributions
 am-0.303
-0.288
 story-0.282
 done-0.280
 big-0.276
Token.
Token ID13
Feature activation+1.83e-01

Pos logit contributions
izing+0.092
yles+0.089
ning+0.089
king+0.088
ellery+0.087
Neg logit contributions
 am-0.023
 done-0.020
-0.019
 story-0.017
 big-0.017
Token It
Token ID632
Feature activation-4.82e-01

Pos logit contributions
 am+0.002
 done+0.002
+0.001
 story+0.001
 big+0.001
Neg logit contributions
izing-0.006
yles-0.006
ning-0.006
king-0.006
ellery-0.006
Token was
Token ID373
Feature activation-1.04e+00

Pos logit contributions
izing+0.020
yles+0.019
ellery+0.019
king+0.019
ning+0.019
Neg logit contributions
 am-0.002
-0.001
 done-0.001
 big-0.001
 story-0.001
Token so
Token ID523
Feature activation-2.90e-01

Pos logit contributions
izing+0.035
yles+0.034
ning+0.034
king+0.034
ellery+0.034
Neg logit contributions
 am-0.011
 done-0.010
-0.009
 big-0.009
 story-0.009
Token burger
Token ID26593
Feature activation-2.18e+00

Pos logit contributions
izing+0.031
yles+0.030
ning+0.030
king+0.029
ellery+0.029
Neg logit contributions
 am-0.023
 done-0.021
-0.021
 story-0.020
 big-0.020
Token with
Token ID351
Feature activation-1.19e+00

Pos logit contributions
izing+0.069
ning+0.067
king+0.066
yles+0.066
rily+0.066
Neg logit contributions
 am-0.026
 done-0.023
-0.022
 story-0.021
 big-0.020
Token fries
Token ID31757
Feature activation-1.01e+00

Pos logit contributions
izing+0.036
yles+0.034
ning+0.034
king+0.034
ellery+0.033
Neg logit contributions
 am-0.017
-0.016
 done-0.016
 big-0.016
 to-0.015
Token and
Token ID290
Feature activation-2.76e+00

Pos logit contributions
izing+0.034
ning+0.033
king+0.033
yles+0.033
rily+0.032
Neg logit contributions
 am-0.010
 done-0.009
-0.008
 story-0.008
 big-0.008
Token a
Token ID257
Feature activation+8.85e-01

Pos logit contributions
izing+0.060
yles+0.058
ning+0.056
rily+0.056
ellery+0.056
Neg logit contributions
 am-0.061
 done-0.057
-0.056
 story-0.055
 big-0.052
Token mil
Token ID1465
Feature activation-1.12e+01

Pos logit contributions
 am+0.013
 done+0.012
+0.011
 story+0.010
 to+0.010
Neg logit contributions
izing-0.025
king-0.024
rily-0.024
yles-0.024
ning-0.024
Tokenksh
Token ID50133
Feature activation-4.76e+00

Pos logit contributions
izing+0.130
yles+0.119
bul+0.107
ths+0.096
ning+0.096
Neg logit contributions
 done-0.341
-0.339
 to-0.338
 am-0.333
 whole-0.327
Tokenake
Token ID539
Feature activation-5.05e-01

Pos logit contributions
izing+0.094
yles+0.090
ning+0.087
ellery+0.086
king+0.086
Neg logit contributions
 am-0.116
 done-0.110
-0.109
 story-0.106
 big-0.103
Token.
Token ID13
Feature activation+6.16e-01

Pos logit contributions
izing+0.017
yles+0.017
ning+0.017
king+0.017
rily+0.017
Neg logit contributions
 am-0.005
 done-0.004
-0.004
 story-0.004
 big-0.004
Token But
Token ID887
Feature activation-1.15e-02

Pos logit contributions
+0.007
 am+0.006
 to+0.006
 done+0.005
 big+0.005
Neg logit contributions
izing-0.021
yles-0.020
ning-0.020
king-0.020
ellery-0.020
Token after
Token ID706
Feature activation+3.24e+00

Pos logit contributions
izing+0.000
yles+0.000
king+0.000
ellery+0.000
ning+0.000
Neg logit contributions
 am-0.000
-0.000
 done-0.000
 to-0.000
 was-0.000
Token watched
Token ID7342
Feature activation-7.26e-01

Pos logit contributions
 am+0.018
 done+0.016
+0.016
 story+0.016
 time+0.015
Neg logit contributions
izing-0.038
yles-0.038
rily-0.037
ellery-0.037
ning-0.036
Token as
Token ID355
Feature activation-2.30e-01

Pos logit contributions
yles+0.023
ellery+0.023
izing+0.022
ning+0.022
burn+0.022
Neg logit contributions
 to-0.009
-0.009
 big-0.009
 done-0.008
 time-0.008
Token they
Token ID484
Feature activation+1.08e+00

Pos logit contributions
izing+0.007
yles+0.007
ning+0.007
king+0.007
ellery+0.007
Neg logit contributions
 am-0.003
-0.002
 done-0.002
 big-0.002
 to-0.002
Token baked
Token ID22979
Feature activation-4.87e-01

Pos logit contributions
 am+0.015
 done+0.014
+0.014
 big+0.013
 story+0.013
Neg logit contributions
izing-0.033
yles-0.032
ning-0.031
king-0.031
rily-0.031
Token until
Token ID1566
Feature activation+2.04e+00

Pos logit contributions
izing+0.016
yles+0.015
ning+0.015
king+0.015
ellery+0.015
Neg logit contributions
 am-0.006
 done-0.005
-0.005
 big-0.005
 story-0.005
Token they
Token ID484
Feature activation+2.03e+00

Pos logit contributions
 am+0.029
 done+0.026
+0.026
 story+0.025
 big+0.024
Neg logit contributions
izing-0.061
yles-0.059
ning-0.058
rily-0.057
king-0.057
Token were
Token ID547
Feature activation+1.66e+00

Pos logit contributions
 am+0.025
 story+0.022
+0.021
 done+0.019
 bad+0.018
Neg logit contributions
yles-0.061
izing-0.060
rily-0.059
ellery-0.059
king-0.058
Token golden
Token ID10861
Feature activation-1.50e+00

Pos logit contributions
 am+0.022
+0.019
 done+0.018
 story+0.018
 big+0.016
Neg logit contributions
izing-0.051
yles-0.050
ning-0.049
king-0.049
rily-0.049
Token.
Token ID13
Feature activation+1.60e+00

Pos logit contributions
izing+0.047
yles+0.047
ning+0.045
ellery+0.045
king+0.045
Neg logit contributions
 am-0.018
 done-0.016
-0.016
 big-0.016
 to-0.015
Token When
Token ID1649
Feature activation+1.54e+00

Pos logit contributions
 am+0.013
 done+0.011
+0.011
 story+0.010
 big+0.009
Neg logit contributions
izing-0.057
yles-0.055
ning-0.055
king-0.054
ellery-0.054
Token they
Token ID484
Feature activation+1.96e+00

Pos logit contributions
 am+0.023
 done+0.021
+0.021
 story+0.020
 big+0.019
Neg logit contributions
izing-0.044
yles-0.043
ning-0.042
ellery-0.041
rily-0.041
Token He
Token ID679
Feature activation+1.88e+00

Pos logit contributions
 done+0.032
 am+0.032
 bad+0.029
 story+0.028
 big+0.026
Neg logit contributions
izing-0.048
rily-0.046
ning-0.046
ants-0.046
yles-0.046
Token smiled
Token ID13541
Feature activation+1.77e+00

Pos logit contributions
 am+0.023
+0.021
 done+0.021
 story+0.019
 big+0.019
Neg logit contributions
izing-0.060
yles-0.058
ning-0.057
king-0.056
ellery-0.056
Token and
Token ID290
Feature activation-6.60e-01

Pos logit contributions
 am+0.024
 done+0.022
+0.020
 story+0.020
 time+0.018
Neg logit contributions
izing-0.055
king-0.053
ning-0.053
rily-0.053
yles-0.053
Token carefully
Token ID7773
Feature activation+2.08e+00

Pos logit contributions
izing+0.019
yles+0.018
ning+0.018
king+0.018
ellery+0.018
Neg logit contributions
 am-0.010
 done-0.009
-0.009
 story-0.009
 big-0.008
Token brought
Token ID3181
Feature activation-1.77e+00

Pos logit contributions
 am+0.037
 done+0.034
+0.034
 story+0.032
 big+0.032
Neg logit contributions
izing-0.055
yles-0.053
ning-0.052
king-0.051
ellery-0.051
Token it
Token ID340
Feature activation+2.10e+00

Pos logit contributions
izing+0.046
rily+0.046
ning+0.045
yles+0.044
ellery+0.044
Neg logit contributions
 am-0.031
 done-0.027
 story-0.026
-0.026
 bad-0.024
Token down
Token ID866
Feature activation+1.82e+00

Pos logit contributions
 am+0.023
 done+0.018
 story+0.018
+0.016
 bad+0.015
Neg logit contributions
ellery-0.067
ning-0.067
rily-0.067
izing-0.066
king-0.065
Token.
Token ID13
Feature activation+2.33e+00

Pos logit contributions
 am+0.021
 done+0.018
 story+0.017
+0.016
 bad+0.015
Neg logit contributions
izing-0.059
ning-0.057
rily-0.057
king-0.056
bing-0.055
Token
Token ID198
Feature activation+1.17e+00

Pos logit contributions
 done+0.027
 am+0.026
 bad+0.025
 story+0.023
 big+0.020
Neg logit contributions
izing-0.070
yles-0.069
ning-0.069
rily-0.068
ants-0.068
Token
Token ID198
Feature activation-8.07e-01

Pos logit contributions
 done+0.008
 am+0.008
 bad+0.007
 way+0.006
 story+0.006
Neg logit contributions
ants-0.039
izing-0.038
yles-0.038
shadow-0.038
rily-0.038
TokenWhen
Token ID2215
Feature activation+1.69e+00

Pos logit contributions
izing+0.016
yles+0.015
ning+0.015
king+0.015
ants+0.015
Neg logit contributions
 am-0.019
 done-0.018
 story-0.018
-0.017
 big-0.017
Token and
Token ID290
Feature activation-4.48e+00

Pos logit contributions
izing+0.045
yles+0.045
ellery+0.044
rily+0.044
king+0.043
Neg logit contributions
 am-0.010
-0.010
 to-0.009
 big-0.009
 done-0.008
Token had
Token ID550
Feature activation-9.37e-01

Pos logit contributions
izing+0.154
yles+0.150
ellery+0.148
king+0.148
ning+0.148
Neg logit contributions
 am-0.045
-0.041
 done-0.039
 big-0.038
 to-0.034
Token stripes
Token ID28806
Feature activation-2.08e+00

Pos logit contributions
ning+0.027
izing+0.027
ellery+0.027
yles+0.027
king+0.027
Neg logit contributions
 am-0.013
 done-0.011
 story-0.010
-0.009
ossible-0.009
Token all
Token ID477
Feature activation+8.49e-01

Pos logit contributions
izing+0.068
ning+0.067
king+0.066
yles+0.065
rily+0.065
Neg logit contributions
 am-0.022
 done-0.019
 story-0.018
-0.017
 bad-0.015
Token over
Token ID625
Feature activation+4.66e-01

Pos logit contributions
 am+0.015
 story+0.013
 done+0.012
+0.012
 bad+0.012
Neg logit contributions
izing-0.022
ning-0.022
yles-0.021
bing-0.021
ellery-0.021
Token his
Token ID465
Feature activation+2.65e+00

Pos logit contributions
 am+0.006
 done+0.005
 story+0.005
+0.005
 bad+0.004
Neg logit contributions
izing-0.015
yles-0.014
ning-0.014
ellery-0.014
rily-0.014
Token body
Token ID1767
Feature activation+1.12e-01

Pos logit contributions
 am+0.056
 done+0.051
+0.046
 story+0.045
 lesson+0.045
Neg logit contributions
ning-0.061
king-0.060
izing-0.060
bing-0.059
rily-0.056
Token.
Token ID13
Feature activation+1.01e+00

Pos logit contributions
 am+0.001
 done+0.001
 story+0.001
+0.001
 bad+0.001
Neg logit contributions
izing-0.004
ning-0.004
king-0.004
rily-0.004
bing-0.004
Token Jack
Token ID3619
Feature activation-7.60e-01

Pos logit contributions
 am+0.017
 done+0.016
 bad+0.014
 story+0.013
 big+0.012
Neg logit contributions
yles-0.027
izing-0.026
ning-0.025
rily-0.025
ivating-0.024
Token wanted
Token ID2227
Feature activation+5.61e-01

Pos logit contributions
izing+0.025
yles+0.024
ning+0.024
king+0.024
ellery+0.023
Neg logit contributions
 am-0.008
 done-0.007
 story-0.007
-0.007
 big-0.006
Token to
Token ID284
Feature activation-1.06e+00

Pos logit contributions
 am+0.005
 done+0.003
 story+0.003
+0.003
ossible+0.002
Neg logit contributions
ning-0.019
yles-0.019
ellery-0.019
izing-0.018
king-0.018
Token had
Token ID550
Feature activation+6.14e-03

Pos logit contributions
 am+0.003
 done+0.002
+0.002
 story+0.002
 to+0.002
Neg logit contributions
izing-0.008
yles-0.007
ning-0.007
king-0.007
ellery-0.007
Token never
Token ID1239
Feature activation-8.58e-01

Pos logit contributions
 am+0.000
 story+0.000
+0.000
ossible+0.000
+0.000
Neg logit contributions
ellery-0.000
ning-0.000
izing-0.000
yles-0.000
king-0.000
Token seen
Token ID1775
Feature activation-3.66e-01

Pos logit contributions
ning+0.020
ellery+0.020
king+0.020
shadow+0.020
yles+0.020
Neg logit contributions
 am-0.015
 story-0.014
-0.014
ossible-0.014
 big-0.012
Token before
Token ID878
Feature activation+3.18e+00

Pos logit contributions
izing+0.010
yles+0.009
rily+0.009
ants+0.009
king+0.009
Neg logit contributions
-0.006
 am-0.006
 done-0.006
 to-0.006
 time-0.006
Token.
Token ID13
Feature activation+2.58e-01

Pos logit contributions
 am+0.028
 done+0.023
 story+0.019
+0.018
ossible+0.018
Neg logit contributions
izing-0.111
ning-0.107
bing-0.105
yles-0.105
rily-0.104
Token
Token ID220
Feature activation+2.98e+00

Pos logit contributions
 am+0.004
 done+0.003
 story+0.003
 bad+0.002
 time+0.002
Neg logit contributions
izing-0.008
rily-0.007
ning-0.007
yles-0.007
ivating-0.007
Token
Token ID198
Feature activation+7.52e-01

Pos logit contributions
 done+0.022
 am+0.022
 story+0.017
 bad+0.017
 learned+0.014
Neg logit contributions
yles-0.101
izing-0.099
ants-0.098
ning-0.098
rily-0.096
Token
Token ID198
Feature activation-1.52e+00

Pos logit contributions
 am+0.006
 done+0.006
 bad+0.004
 story+0.004
 consequences+0.004
Neg logit contributions
izing-0.025
yles-0.025
ning-0.024
ants-0.024
shadow-0.024
Tokenâ
Token ID22940
Feature activation-4.47e+00

Pos logit contributions
izing+0.034
yles+0.031
king+0.030
ellery+0.030
ning+0.030
Neg logit contributions
 am-0.034
 done-0.031
 story-0.029
-0.029
 to-0.028
Token
Token ID26391
Feature activation-1.48e+00

Pos logit contributions
izing+0.102
king+0.093
ning+0.093
bing+0.092
yles+0.091
Neg logit contributions
 am-0.094
 big-0.089
-0.088
 story-0.088
 done-0.086
Token
Token ID129
Feature activation-5.42e+00

Pos logit contributions
izing+0.038
yles+0.038
king+0.037
etti+0.037
ning+0.037
Neg logit contributions
 am-0.024
 story-0.022
 done-0.021
 bad-0.021
 lesson-0.021
Token in
Token ID287
Feature activation+5.70e-01

Pos logit contributions
izing+0.062
yles+0.060
ning+0.059
king+0.059
rily+0.058
Neg logit contributions
 am-0.020
 done-0.018
-0.017
 story-0.016
 big-0.015
Token the
Token ID262
Feature activation+9.03e-01

Pos logit contributions
 am+0.007
 done+0.006
+0.006
 story+0.005
 big+0.005
Neg logit contributions
izing-0.019
yles-0.018
ning-0.018
king-0.018
ellery-0.018
Token town
Token ID3240
Feature activation+5.12e-01

Pos logit contributions
 am+0.015
 done+0.014
 to+0.012
 lesson+0.011
 story+0.011
Neg logit contributions
izing-0.023
ning-0.022
yles-0.022
king-0.022
ivating-0.021
Token were
Token ID547
Feature activation-1.68e-02

Pos logit contributions
 am+0.006
 story+0.005
 done+0.004
+0.004
 bad+0.004
Neg logit contributions
izing-0.017
yles-0.016
ning-0.016
king-0.016
bing-0.015
Token scared
Token ID12008
Feature activation-1.26e-01

Pos logit contributions
izing+0.001
yles+0.000
ning+0.000
king+0.000
ellery+0.000
Neg logit contributions
 am-0.000
-0.000
 done-0.000
 story-0.000
 big-0.000
Token when
Token ID618
Feature activation+2.38e+00

Pos logit contributions
izing+0.004
yles+0.004
ning+0.004
king+0.004
ellery+0.004
Neg logit contributions
 am-0.001
 done-0.001
-0.001
 story-0.001
 big-0.001
Token they
Token ID484
Feature activation+1.65e+00

Pos logit contributions
 am+0.042
 done+0.040
 story+0.037
ossible+0.037
+0.036
Neg logit contributions
izing-0.061
yles-0.058
ning-0.056
king-0.055
bing-0.054
Token saw
Token ID2497
Feature activation-4.67e-01

Pos logit contributions
 am+0.017
 story+0.014
 done+0.014
+0.013
 lesson+0.012
Neg logit contributions
yles-0.053
izing-0.052
king-0.052
ning-0.051
ting-0.050
Token the
Token ID262
Feature activation+8.70e-01

Pos logit contributions
izing+0.015
yles+0.015
ning+0.014
king+0.014
ellery+0.014
Neg logit contributions
 am-0.006
 done-0.005
-0.005
 big-0.005
 story-0.005
Token tank
Token ID6873
Feature activation-9.36e-02

Pos logit contributions
 am+0.017
 done+0.015
+0.014
ossible+0.014
 to+0.014
Neg logit contributions
izing-0.021
king-0.020
ning-0.020
yles-0.019
rily-0.019
Token.
Token ID13
Feature activation+5.98e-01

Pos logit contributions
izing+0.003
ning+0.003
king+0.003
rily+0.003
bing+0.003
Neg logit contributions
 am-0.001
 done-0.001
-0.001
ossible-0.001
 story-0.001
Token."
Token ID526
Feature activation+1.27e+00

Pos logit contributions
izing+0.001
yles+0.001
ning+0.001
rily+0.001
king+0.001
Neg logit contributions
 am-0.001
 done-0.000
 story-0.000
-0.000
 bad-0.000
Token Mom
Token ID11254
Feature activation+7.25e-02

Pos logit contributions
 done+0.013
 am+0.012
 story+0.009
 whole+0.008
 bad+0.008
Neg logit contributions
yles-0.041
izing-0.039
rily-0.039
burn-0.038
ants-0.038
Token said
Token ID531
Feature activation-1.29e-01

Pos logit contributions
+0.000
 am+0.000
 done+0.000
 to+0.000
 was+0.000
Neg logit contributions
izing-0.003
yles-0.003
ellery-0.003
king-0.003
ning-0.003
Token.
Token ID13
Feature activation+4.65e-01

Pos logit contributions
izing+0.005
rily+0.005
king+0.005
yles+0.005
ning+0.005
Neg logit contributions
 am-0.001
 done-0.001
 story-0.001
-0.001
 big-0.001
Token
Token ID198
Feature activation+6.59e-01

Pos logit contributions
 done+0.003
 am+0.003
 story+0.002
 bad+0.002
 time+0.001
Neg logit contributions
izing-0.017
yles-0.017
ning-0.016
king-0.016
rily-0.016
Token
Token ID198
Feature activation-1.20e+00

Pos logit contributions
 done+0.006
 am+0.005
 way+0.004
 story+0.004
 bad+0.004
Neg logit contributions
izing-0.021
yles-0.021
bing-0.020
ang-0.020
ants-0.020
TokenThey
Token ID2990
Feature activation+2.08e+00

Pos logit contributions
izing+0.029
yles+0.028
ning+0.028
king+0.027
rily+0.027
Neg logit contributions
 am-0.024
-0.023
 done-0.022
 story-0.021
 big-0.021
Token closed
Token ID4838
Feature activation-2.09e+00

Pos logit contributions
 am+0.028
 done+0.026
+0.025
 story+0.023
 big+0.023
Neg logit contributions
izing-0.064
yles-0.062
ning-0.061
king-0.061
ellery-0.060
Token the
Token ID262
Feature activation+2.07e+00

Pos logit contributions
izing+0.068
yles+0.066
ning+0.065
king+0.065
ellery+0.065
Neg logit contributions
 am-0.023
-0.022
 done-0.021
 big-0.019
 to-0.019
Token book
Token ID1492
Feature activation+1.40e+00

Pos logit contributions
 am+0.038
 done+0.037
+0.036
'm+0.034
 felt+0.031
Neg logit contributions
izing-0.046
ning-0.046
rily-0.045
ries-0.044
bul-0.044
Token and
Token ID290
Feature activation-1.59e+00

Pos logit contributions
 am+0.018
 done+0.016
+0.015
 story+0.014
 bad+0.013
Neg logit contributions
izing-0.044
rily-0.041
ning-0.041
yles-0.041
king-0.041
Token Annie
Token ID25860
Feature activation-1.24e-01

Pos logit contributions
izing+0.067
yles+0.064
ning+0.064
king+0.063
rily+0.062
Neg logit contributions
 am-0.044
-0.042
 done-0.041
 to-0.039
 big-0.039
Token.
Token ID13
Feature activation+2.58e-01

Pos logit contributions
izing+0.005
yles+0.005
ning+0.004
king+0.004
ellery+0.004
Neg logit contributions
 am-0.001
 done-0.001
-0.001
 story-0.000
 big-0.000
Token She
Token ID1375
Feature activation+8.84e-01

Pos logit contributions
 am+0.004
 done+0.004
 bad+0.003
 story+0.003
 big+0.003
Neg logit contributions
izing-0.007
yles-0.007
rily-0.007
ellery-0.007
ning-0.007
Token loved
Token ID6151
Feature activation+4.73e-01

Pos logit contributions
 am+0.013
 done+0.012
 story+0.012
ossible+0.011
+0.011
Neg logit contributions
izing-0.022
ning-0.021
ellery-0.021
 pian-0.021
yles-0.021
Token going
Token ID1016
Feature activation-1.40e+00

Pos logit contributions
 am+0.002
 done+0.002
+0.002
 to+0.002
 big+0.001
Neg logit contributions
izing-0.019
rily-0.018
king-0.018
yles-0.018
ning-0.018
Token to
Token ID284
Feature activation+9.31e-01

Pos logit contributions
ning+0.044
burn+0.041
izing+0.041
yles+0.041
king+0.041
Neg logit contributions
 am-0.017
 done-0.014
-0.013
 story-0.013
 bad-0.013
Token the
Token ID262
Feature activation+8.09e-01

Pos logit contributions
 am+0.010
+0.009
 done+0.008
 big+0.008
 story+0.008
Neg logit contributions
izing-0.032
king-0.031
rily-0.031
yles-0.031
ning-0.030
Token beach
Token ID10481
Feature activation-1.33e+00

Pos logit contributions
 am+0.009
+0.009
 big+0.008
 done+0.008
 story+0.008
Neg logit contributions
izing-0.026
yles-0.026
rily-0.025
king-0.025
ning-0.025
Token,
Token ID11
Feature activation-3.41e+00

Pos logit contributions
izing+0.036
ning+0.035
ellery+0.034
yles+0.034
king+0.034
Neg logit contributions
 am-0.022
 done-0.020
-0.019
 story-0.019
 bad-0.018
Token playing
Token ID2712
Feature activation-7.83e-01

Pos logit contributions
izing+0.084
yles+0.082
ning+0.080
king+0.079
ellery+0.079
Neg logit contributions
 am-0.064
 done-0.060
-0.058
 story-0.057
 big-0.054
Token with
Token ID351
Feature activation-2.00e+00

Pos logit contributions
izing+0.021
bing+0.020
ning+0.020
rily+0.020
yles+0.019
Neg logit contributions
 am-0.013
 done-0.012
 story-0.011
-0.011
 bad-0.011
TokenThe
Token ID464
Feature activation-9.12e-01

Pos logit contributions
yles+0.030
izing+0.030
ning+0.030
ellery+0.029
rily+0.029
Neg logit contributions
-0.017
 am-0.017
 done-0.015
 big-0.015
 story-0.014
Token fox
Token ID21831
Feature activation-4.89e-01

Pos logit contributions
izing+0.023
yles+0.022
ellery+0.021
rily+0.021
ning+0.021
Neg logit contributions
 am-0.018
-0.017
 done-0.017
 story-0.016
 big-0.016
Token worked
Token ID3111
Feature activation+5.11e-01

Pos logit contributions
izing+0.017
yles+0.016
ning+0.016
king+0.016
ellery+0.016
Neg logit contributions
 am-0.005
 done-0.004
-0.004
 story-0.004
 big-0.004
Token hard
Token ID1327
Feature activation+1.88e+00

Pos logit contributions
 am+0.008
 story+0.007
+0.007
ossible+0.006
'm+0.006
Neg logit contributions
izing-0.015
bing-0.014
ning-0.014
rily-0.014
king-0.014
Token,
Token ID11
Feature activation-1.93e+00

Pos logit contributions
 am+0.027
 story+0.022
ossible+0.020
 done+0.020
+0.020
Neg logit contributions
izing-0.059
ning-0.055
bing-0.054
king-0.053
rily-0.053
Token and
Token ID290
Feature activation-1.08e+00

Pos logit contributions
izing+0.059
yles+0.058
ants+0.057
ning+0.057
ellery+0.057
Neg logit contributions
 am-0.024
 done-0.024
-0.024
 to-0.023
 big-0.022
Token when
Token ID618
Feature activation+2.05e+00

Pos logit contributions
izing+0.031
yles+0.030
ants+0.029
king+0.029
ellery+0.029
Neg logit contributions
 done-0.017
 am-0.017
-0.016
 to-0.015
 big-0.015
Token he
Token ID339
Feature activation+2.71e+00

Pos logit contributions
 am+0.025
 done+0.023
+0.021
 story+0.020
ossible+0.019
Neg logit contributions
izing-0.064
yles-0.062
ning-0.061
bing-0.059
ellery-0.059
Token was
Token ID373
Feature activation+1.90e+00

Pos logit contributions
 am+0.029
+0.025
 story+0.024
 done+0.024
 big+0.022
Neg logit contributions
izing-0.088
yles-0.086
ning-0.085
ellery-0.084
rily-0.083
Token done
Token ID1760
Feature activation+3.08e+00

Pos logit contributions
 am+0.019
 story+0.015
+0.014
+0.012
ossible+0.011
Neg logit contributions
izing-0.062
yles-0.062
ning-0.061
king-0.061
shadow-0.060
Token,
Token ID11
Feature activation-1.10e+00

Pos logit contributions
 am+0.033
 done+0.027
+0.026
 story+0.026
ossible+0.024
Neg logit contributions
izing-0.103
yles-0.098
ning-0.098
bing-0.098
rily-0.096
Token
Token ID198
Feature activation-1.65e+00

Pos logit contributions
izing+0.001
yles+0.001
bing+0.001
ants+0.001
shadow+0.001
Neg logit contributions
 done-0.000
 am-0.000
 story-0.000
 way-0.000
 time-0.000
Token"
Token ID1
Feature activation-5.78e+00

Pos logit contributions
izing+0.038
yles+0.036
ning+0.035
king+0.035
ellery+0.035
Neg logit contributions
 am-0.035
 done-0.033
-0.032
 story-0.031
 big-0.031
TokenL
Token ID43
Feature activation-3.65e+00

Pos logit contributions
izing+0.159
rily+0.157
ning+0.154
ellery+0.153
yles+0.152
Neg logit contributions
 am-0.102
-0.097
 done-0.086
 big-0.085
 to-0.083
Tokenila
Token ID10102
Feature activation+1.05e-02

Pos logit contributions
izing+0.095
yles+0.091
ning+0.090
ellery+0.089
king+0.089
Neg logit contributions
 am-0.065
 done-0.061
-0.060
 story-0.058
 big-0.057
Token,
Token ID11
Feature activation-5.26e+00

Pos logit contributions
 am+0.000
 story+0.000
 done+0.000
+0.000
 big+0.000
Neg logit contributions
izing-0.000
ning-0.000
king-0.000
rily-0.000
ellery-0.000
Token you
Token ID345
Feature activation+7.51e-01

Pos logit contributions
izing+0.139
yles+0.136
ning+0.132
ellery+0.132
king+0.130
Neg logit contributions
 am-0.084
 done-0.078
-0.078
 story-0.073
 big-0.071
Token know
Token ID760
Feature activation+1.25e+00

Pos logit contributions
 am+0.007
+0.007
 story+0.007
 done+0.007
 day+0.006
Neg logit contributions
yles-0.023
izing-0.022
ellery-0.022
ning-0.022
ants-0.022
Token you
Token ID345
Feature activation+1.21e+00

Pos logit contributions
 am+0.014
+0.012
 done+0.012
 story+0.011
 big+0.010
Neg logit contributions
izing-0.041
yles-0.040
ning-0.039
ellery-0.039
king-0.039
Token are
Token ID389
Feature activation+8.17e-01

Pos logit contributions
+0.012
 story+0.012
 am+0.012
 done+0.010
 big+0.010
Neg logit contributions
yles-0.037
izing-0.036
ellery-0.036
ning-0.035
king-0.035
Token not
Token ID407
Feature activation+4.24e-02

Pos logit contributions
 am+0.010
+0.009
 done+0.008
 story+0.008
 big+0.007
Neg logit contributions
izing-0.026
yles-0.026
ning-0.025
king-0.025
ellery-0.025
Token allowed
Token ID3142
Feature activation+5.45e-01

Pos logit contributions
 am+0.001
+0.001
 story+0.001
 done+0.001
 big+0.001
Neg logit contributions
izing-0.001
ning-0.001
ellery-0.001
king-0.001
yles-0.001
Token bright
Token ID6016
Feature activation-1.80e+00

Pos logit contributions
 am+0.007
 done+0.006
+0.006
 story+0.006
 big+0.005
Neg logit contributions
izing-0.016
yles-0.015
ning-0.015
king-0.015
ellery-0.015
Token light
Token ID1657
Feature activation-1.45e+00

Pos logit contributions
yles+0.051
izing+0.051
ellery+0.050
ants+0.049
king+0.049
Neg logit contributions
 am-0.028
-0.026
 done-0.026
 big-0.026
 story-0.025
Token shone
Token ID44193
Feature activation-3.06e+00

Pos logit contributions
izing+0.037
ning+0.035
yles+0.035
king+0.034
rily+0.034
Neg logit contributions
 am-0.027
 done-0.025
-0.025
 story-0.024
 big-0.023
Token!
Token ID0
Feature activation+1.24e+00

Pos logit contributions
izing+0.091
yles+0.091
ellery+0.088
ants+0.088
ning+0.086
Neg logit contributions
 am-0.042
-0.039
 done-0.039
 to-0.039
 big-0.039
Token She
Token ID1375
Feature activation+1.98e+00

Pos logit contributions
 am+0.020
 done+0.019
 story+0.017
 bad+0.017
 big+0.016
Neg logit contributions
izing-0.033
yles-0.033
ning-0.032
ellery-0.032
rily-0.031
Token was
Token ID373
Feature activation+2.81e-01

Pos logit contributions
 am+0.022
 done+0.019
+0.019
 story+0.017
 big+0.017
Neg logit contributions
izing-0.066
yles-0.064
ning-0.063
king-0.062
ellery-0.062
Token so
Token ID523
Feature activation+1.12e+00

Pos logit contributions
 am+0.004
+0.004
 done+0.004
 story+0.004
 big+0.004
Neg logit contributions
izing-0.008
yles-0.008
ning-0.008
king-0.008
ellery-0.007
Token surprised
Token ID6655
Feature activation+9.87e-01

Pos logit contributions
 am+0.020
 story+0.018
 done+0.017
 time+0.017
ossible+0.017
Neg logit contributions
izing-0.028
yles-0.027
rily-0.026
king-0.026
bing-0.026
Token that
Token ID326
Feature activation+4.92e-01

Pos logit contributions
 am+0.015
 done+0.013
 story+0.013
ossible+0.012
+0.012
Neg logit contributions
izing-0.030
ning-0.028
king-0.028
yles-0.027
bing-0.027
Token she
Token ID673
Feature activation+1.28e+00

Pos logit contributions
 am+0.008
 done+0.007
+0.007
 story+0.007
 big+0.006
Neg logit contributions
izing-0.014
yles-0.013
ning-0.013
ellery-0.013
king-0.013
Token jumped
Token ID11687
Feature activation-1.44e+00

Pos logit contributions
 am+0.018
 done+0.016
+0.016
 story+0.015
 big+0.014
Neg logit contributions
izing-0.039
yles-0.038
ning-0.037
king-0.037
ellery-0.037
Token smiled
Token ID13541
Feature activation+2.15e+00

Pos logit contributions
 am+0.014
 done+0.013
+0.013
 story+0.012
 big+0.011
Neg logit contributions
izing-0.042
yles-0.040
ning-0.040
king-0.039
ellery-0.039
Token and
Token ID290
Feature activation-1.11e+00

Pos logit contributions
 am+0.029
 done+0.026
+0.024
 story+0.024
 big+0.022
Neg logit contributions
izing-0.066
ning-0.064
king-0.064
yles-0.063
rily-0.063
Token said
Token ID531
Feature activation+2.46e-01

Pos logit contributions
izing+0.041
yles+0.039
king+0.039
ants+0.039
rily+0.038
Neg logit contributions
 am-0.009
-0.009
 done-0.008
 to-0.007
 big-0.007
Token,
Token ID11
Feature activation-9.19e-01

Pos logit contributions
 am+0.002
 done+0.002
+0.002
 story+0.002
 time+0.001
Neg logit contributions
izing-0.009
yles-0.008
rily-0.008
ning-0.008
king-0.008
Token "
Token ID366
Feature activation-5.77e+00

Pos logit contributions
izing+0.031
ellery+0.031
yles+0.031
ning+0.030
burn+0.030
Neg logit contributions
-0.011
 to-0.009
 am-0.008
 big-0.008
 was-0.007
TokenL
Token ID43
Feature activation-3.79e+00

Pos logit contributions
izing+0.142
yles+0.140
rily+0.139
ants+0.139
ellery+0.137
Neg logit contributions
-0.114
 am-0.113
 to-0.101
 was-0.099
 done-0.098
Tokenily
Token ID813
Feature activation+1.66e+00

Pos logit contributions
izing+0.122
yles+0.118
ning+0.117
king+0.116
ellery+0.116
Neg logit contributions
 am-0.045
 done-0.040
-0.040
 story-0.036
 big-0.036
Token,
Token ID11
Feature activation-3.42e+00

Pos logit contributions
 am+0.014
+0.012
 done+0.012
 story+0.011
 big+0.010
Neg logit contributions
izing-0.057
ning-0.056
king-0.054
yles-0.054
ellery-0.054
Token I
Token ID314
Feature activation+9.53e-01

Pos logit contributions
izing+0.098
yles+0.097
king+0.095
rily+0.095
ning+0.094
Neg logit contributions
 am-0.054
 to-0.051
-0.050
 done-0.050
 story-0.048
Token think
Token ID892
Feature activation+4.57e-01

Pos logit contributions
+0.009
 big+0.009
 story+0.009
 done+0.009
 bad+0.008
Neg logit contributions
yles-0.027
bul-0.026
burn-0.026
izing-0.025
istent-0.025
Token that
Token ID326
Feature activation-7.98e-01

Pos logit contributions
 am+0.007
 done+0.007
+0.007
 to+0.007
 big+0.007
Neg logit contributions
izing-0.013
king-0.013
rily-0.012
yles-0.012
ning-0.012
Token magic
Token ID5536
Feature activation-6.57e-02

Pos logit contributions
 am+0.038
 done+0.035
+0.035
 story+0.032
 to+0.032
Neg logit contributions
izing-0.058
yles-0.055
ning-0.055
king-0.055
rily-0.054
Token word
Token ID1573
Feature activation+1.22e+00

Pos logit contributions
izing+0.002
ning+0.001
rily+0.001
bul+0.001
king+0.001
Neg logit contributions
 am-0.001
 done-0.001
-0.001
 story-0.001
 big-0.001
Token."
Token ID526
Feature activation+1.42e+00

Pos logit contributions
 am+0.014
 done+0.013
+0.013
 story+0.012
 big+0.011
Neg logit contributions
izing-0.039
yles-0.037
ning-0.037
king-0.037
rily-0.036
Token
Token ID198
Feature activation+4.92e-01

Pos logit contributions
 am+0.011
 done+0.010
 story+0.008
 bad+0.008
 big+0.008
Neg logit contributions
yles-0.049
izing-0.049
rily-0.048
ning-0.048
ants-0.047
Token
Token ID198
Feature activation-1.02e+00

Pos logit contributions
 am+0.002
 done+0.002
 bad+0.001
 story+0.001
 big+0.001
Neg logit contributions
izing-0.019
yles-0.019
ning-0.018
ants-0.018
rily-0.018
Token"
Token ID1
Feature activation-5.96e+00

Pos logit contributions
izing+0.026
ning+0.025
yles+0.025
rily+0.024
king+0.024
Neg logit contributions
-0.020
 am-0.020
 story-0.018
 done-0.017
 big-0.017
TokenLet
Token ID5756
Feature activation-4.39e-01

Pos logit contributions
rily+0.156
ning+0.156
ellery+0.154
izing+0.152
ants+0.149
Neg logit contributions
 am-0.114
-0.113
 big-0.093
 was-0.089
'm-0.089
Token's
Token ID338
Feature activation+8.91e-01

Pos logit contributions
izing+0.013
yles+0.013
ning+0.013
king+0.013
ellery+0.013
Neg logit contributions
 am-0.006
 done-0.005
-0.005
 story-0.005
 big-0.005
Token try
Token ID1949
Feature activation+1.84e+00

Pos logit contributions
 am+0.011
+0.010
 done+0.010
 big+0.009
 story+0.009
Neg logit contributions
izing-0.029
yles-0.028
king-0.028
ning-0.028
rily-0.028
Token,"
Token ID553
Feature activation-1.01e+00

Pos logit contributions
 am+0.021
+0.020
 to+0.020
 done+0.019
 big+0.018
Neg logit contributions
izing-0.061
yles-0.059
king-0.058
rily-0.058
ellery-0.057
Token Ben
Token ID3932
Feature activation-3.23e-01

Pos logit contributions
izing+0.029
yles+0.028
ning+0.028
rily+0.027
king+0.027
Neg logit contributions
 am-0.015
 done-0.014
-0.013
 story-0.013
 big-0.012
Token,
Token ID11
Feature activation-1.65e+00

Pos logit contributions
 am+0.012
 done+0.012
 own+0.010
+0.009
 time+0.009
Neg logit contributions
izing-0.033
rily-0.033
ants-0.032
ning-0.031
king-0.031
Token "
Token ID366
Feature activation-4.91e+00

Pos logit contributions
izing+0.056
ellery+0.054
yles+0.054
ning+0.053
ants+0.052
Neg logit contributions
-0.020
 am-0.018
 to-0.016
 big-0.016
 done-0.015
TokenYou
Token ID1639
Feature activation+1.75e+00

Pos logit contributions
izing+0.137
yles+0.136
ning+0.135
ellery+0.135
ants+0.135
Neg logit contributions
 am-0.085
-0.084
 He-0.068
 was-0.067
 whole-0.066
Token are
Token ID389
Feature activation+2.27e+00

Pos logit contributions
 am+0.022
+0.021
 to+0.021
 story+0.020
 lesson+0.018
Neg logit contributions
yles-0.044
etti-0.043
burn-0.043
izing-0.043
pper-0.043
Token welcome
Token ID7062
Feature activation+1.86e+00

Pos logit contributions
 am+0.021
 done+0.018
+0.017
 story+0.017
 to+0.016
Neg logit contributions
izing-0.077
yles-0.074
ning-0.074
ellery-0.073
king-0.073
Token,
Token ID11
Feature activation-4.92e+00

Pos logit contributions
 am+0.016
 done+0.014
+0.012
 story+0.011
 big+0.010
Neg logit contributions
izing-0.065
ning-0.063
yles-0.062
king-0.062
ellery-0.062
Token animals
Token ID4695
Feature activation-3.93e-01

Pos logit contributions
izing+0.147
yles+0.143
ning+0.141
bing+0.140
king+0.139
Neg logit contributions
 am-0.073
-0.072
 big-0.069
 done-0.069
 story-0.068
Token!
Token ID0
Feature activation-2.67e-01

Pos logit contributions
izing+0.013
king+0.012
ning+0.012
ting+0.012
yles+0.012
Neg logit contributions
 am-0.003
 done-0.003
 story-0.003
-0.003
 big-0.003
Token I
Token ID314
Feature activation+5.89e-01

Pos logit contributions
izing+0.007
yles+0.007
king+0.007
ning+0.007
ellery+0.007
Neg logit contributions
 am-0.005
-0.005
 to-0.004
 He-0.004
 story-0.004
Token love
Token ID1842
Feature activation+8.52e-01

Pos logit contributions
 story+0.006
 done+0.006
+0.006
 big+0.006
 to+0.006
Neg logit contributions
 spe-0.015
burn-0.015
ples-0.015
king-0.015
pper-0.015
Token you
Token ID345
Feature activation+1.43e+00

Pos logit contributions
 am+0.016
 done+0.014
+0.014
 story+0.013
 big+0.013
Neg logit contributions
izing-0.022
yles-0.021
ning-0.021
ellery-0.020
king-0.020
Token She
Token ID1375
Feature activation+1.56e+00

Pos logit contributions
 done+0.012
 am+0.011
 bad+0.010
 story+0.009
 whole+0.008
Neg logit contributions
ning-0.038
yles-0.038
izing-0.038
bing-0.036
ellery-0.036
Token got
Token ID1392
Feature activation-2.03e+00

Pos logit contributions
 am+0.020
 done+0.018
+0.018
 story+0.017
 big+0.016
Neg logit contributions
izing-0.049
yles-0.047
ning-0.047
king-0.046
ellery-0.046
Token her
Token ID607
Feature activation+2.58e+00

Pos logit contributions
izing+0.059
yles+0.058
ning+0.058
king+0.056
ellery+0.056
Neg logit contributions
 am-0.027
 done-0.025
 story-0.024
-0.024
 time-0.022
Token rain
Token ID6290
Feature activation-2.19e+00

Pos logit contributions
 am+0.046
+0.043
 done+0.041
 He+0.039
 story+0.039
Neg logit contributions
burn-0.063
ning-0.063
izing-0.063
bul-0.061
yles-0.061
Tokencoat
Token ID31434
Feature activation-3.10e+00

Pos logit contributions
izing+0.047
ning+0.045
king+0.045
yles+0.044
burn+0.044
Neg logit contributions
 am-0.049
-0.046
 done-0.045
 story-0.045
 big-0.042
Token and
Token ID290
Feature activation-3.24e+00

Pos logit contributions
izing+0.106
yles+0.103
ellery+0.101
ning+0.101
rily+0.100
Neg logit contributions
 am-0.031
 done-0.028
-0.027
 big-0.025
 to-0.024
Token boots
Token ID14412
Feature activation-3.08e+00

Pos logit contributions
izing+0.099
yles+0.096
ning+0.095
king+0.094
ellery+0.094
Neg logit contributions
 am-0.043
 done-0.040
-0.039
 story-0.036
 big-0.036
Token ready
Token ID3492
Feature activation+2.51e+00

Pos logit contributions
izing+0.098
ning+0.095
king+0.095
yles+0.093
burn+0.093
Neg logit contributions
 am-0.036
 story-0.032
 done-0.030
-0.030
 big-0.027
Token.
Token ID13
Feature activation+1.49e+00

Pos logit contributions
 am+0.020
 story+0.015
+0.014
 done+0.014
ossible+0.013
Neg logit contributions
izing-0.089
ning-0.086
king-0.085
rily-0.085
bing-0.084
Token
Token ID198
Feature activation+1.04e+00

Pos logit contributions
 am+0.012
 done+0.012
 story+0.010
 bad+0.009
 big+0.007
Neg logit contributions
yles-0.051
izing-0.051
ning-0.050
bing-0.049
rily-0.048
Token
Token ID198
Feature activation-1.73e+00

Pos logit contributions
 done+0.009
 am+0.008
 consequences+0.007
 bad+0.007
 grown+0.006
Neg logit contributions
yles-0.032
izing-0.032
ning-0.031
ants-0.031
ang-0.031
Token said
Token ID531
Feature activation-5.35e-01

Pos logit contributions
+0.013
 am+0.013
 done+0.012
 was+0.011
 big+0.011
Neg logit contributions
izing-0.055
yles-0.053
rily-0.052
ellery-0.052
king-0.051
Token,
Token ID11
Feature activation-1.75e+00

Pos logit contributions
izing+0.020
yles+0.019
ning+0.019
king+0.019
ellery+0.019
Neg logit contributions
 am-0.004
 done-0.003
-0.003
 story-0.003
 big-0.002
Token
Token ID6184
Feature activation-4.71e+00

Pos logit contributions
izing+0.056
yles+0.055
ellery+0.055
ning+0.054
rily+0.053
Neg logit contributions
-0.022
 am-0.021
 to-0.019
 done-0.019
 big-0.018
Token
Token ID95
Feature activation-5.50e+00

Pos logit contributions
yles+0.101
ning+0.097
burn+0.095
rily+0.094
ellery+0.092
Neg logit contributions
 am-0.112
-0.103
 done-0.097
 bad-0.095
 own-0.094
Token
Token ID26391
Feature activation-1.72e+00

Pos logit contributions
yles+0.129
izing+0.127
rily+0.122
ning+0.122
ants+0.120
Neg logit contributions
 am-0.118
-0.112
 done-0.109
 story-0.101
 time-0.099
Token
Token ID129
Feature activation-6.48e+00

Pos logit contributions
izing+0.038
yles+0.036
ning+0.036
king+0.035
ellery+0.035
Neg logit contributions
 am-0.037
 done-0.035
-0.034
 story-0.034
 big-0.033
Token
Token ID241
Feature activation-1.20e+00

Pos logit contributions
yles+0.140
izing+0.138
bul+0.133
ning+0.132
ellery+0.130
Neg logit contributions
 am-0.140
-0.139
 done-0.138
 big-0.130
 to-0.129
TokenWe
Token ID1135
Feature activation-1.22e-01

Pos logit contributions
izing+0.028
yles+0.027
ning+0.026
king+0.026
ellery+0.026
Neg logit contributions
 am-0.024
 done-0.023
 story-0.022
-0.022
 big-0.021
Token need
Token ID761
Feature activation+1.02e+00

Pos logit contributions
yles+0.003
izing+0.003
bul+0.003
ning+0.003
burn+0.003
Neg logit contributions
 am-0.001
-0.001
 story-0.001
 done-0.001
 to-0.001
Token to
Token ID284
Feature activation-1.54e+00

Pos logit contributions
 am+0.006
 story+0.005
 done+0.005
+0.005
 big+0.003
Neg logit contributions
izing-0.036
ning-0.035
bul-0.035
yles-0.034
burn-0.034
Token find
Token ID1064
Feature activation-1.79e+00

Pos logit contributions
izing+0.048
yles+0.046
ning+0.046
king+0.045
ellery+0.045
Neg logit contributions
 am-0.021
 done-0.019
-0.018
 story-0.017
 big-0.017
Token and
Token ID290
Feature activation-8.35e-01

Pos logit contributions
 am+0.012
 done+0.010
+0.009
 story+0.009
 bad+0.009
Neg logit contributions
izing-0.028
ning-0.027
rily-0.026
king-0.026
yles-0.026
Token started
Token ID2067
Feature activation+2.18e+00

Pos logit contributions
izing+0.025
yles+0.025
ning+0.024
rily+0.024
ellery+0.024
Neg logit contributions
 am-0.011
 done-0.010
-0.010
 story-0.010
 big-0.009
Token eating
Token ID6600
Feature activation-1.46e-01

Pos logit contributions
 am+0.017
 done+0.013
+0.013
 story+0.012
 bad+0.010
Neg logit contributions
izing-0.078
yles-0.077
ning-0.077
ellery-0.076
king-0.075
Token the
Token ID262
Feature activation+1.24e+00

Pos logit contributions
izing+0.005
yles+0.004
rily+0.004
ning+0.004
ellery+0.004
Neg logit contributions
 am-0.002
 done-0.002
-0.002
 story-0.002
 big-0.001
Token ch
Token ID442
Feature activation-4.36e+00

Pos logit contributions
 am+0.021
+0.020
 done+0.019
ossible+0.017
 story+0.017
Neg logit contributions
izing-0.033
ning-0.031
rily-0.031
yles-0.030
ellery-0.030
Tokenocol
Token ID4668
Feature activation-9.10e+00

Pos logit contributions
izing+0.035
yles+0.032
ning+0.030
king+0.028
ellery+0.028
Neg logit contributions
 am-0.158
 done-0.152
-0.151
 story-0.148
 big-0.147
Tokenates
Token ID689
Feature activation-5.11e-01

Pos logit contributions
izing+0.193
yles+0.180
ning+0.174
rily+0.174
king+0.174
Neg logit contributions
 am-0.210
 done-0.202
-0.197
 story-0.189
 to-0.185
Token.
Token ID13
Feature activation+5.91e-01

Pos logit contributions
izing+0.019
yles+0.018
ning+0.018
king+0.018
ellery+0.018
Neg logit contributions
 am-0.004
 done-0.003
-0.003
 story-0.003
 big-0.003
Token The
Token ID383
Feature activation+4.92e-01

Pos logit contributions
 am+0.007
 done+0.006
 story+0.005
+0.005
 bad+0.005
Neg logit contributions
izing-0.019
yles-0.019
rily-0.019
ning-0.018
ellery-0.018
Token shop
Token ID6128
Feature activation-1.26e+00

Pos logit contributions
 am+0.011
+0.010
 done+0.010
 to+0.010
 story+0.009
Neg logit contributions
izing-0.010
ning-0.010
rily-0.009
king-0.009
ender-0.009
Tokenkeeper
Token ID13884
Feature activation-3.83e-01

Pos logit contributions
izing+0.033
ning+0.032
yles+0.032
king+0.031
rily+0.031
Neg logit contributions
 am-0.022
 done-0.020
-0.020
 story-0.019
 big-0.018
Token and
Token ID290
Feature activation-2.99e+00

Pos logit contributions
izing+0.073
yles+0.072
ellery+0.071
ning+0.069
ants+0.069
Neg logit contributions
 am-0.026
 done-0.024
-0.024
 to-0.023
 big-0.023
Token tw
Token ID665
Feature activation-4.87e+00

Pos logit contributions
izing+0.103
king+0.097
rily+0.097
yles+0.096
ants+0.096
Neg logit contributions
 am-0.031
-0.030
 big-0.030
 done-0.029
 to-0.029
Tokeninkle
Token ID19894
Feature activation-1.19e+00

Pos logit contributions
izing+0.089
ning+0.083
king+0.082
yles+0.081
ting+0.079
Neg logit contributions
 am-0.125
 done-0.120
-0.118
 big-0.112
 to-0.110
Token.
Token ID13
Feature activation+7.27e-01

Pos logit contributions
yles+0.043
izing+0.042
ellery+0.042
shadow+0.041
ning+0.040
Neg logit contributions
-0.009
 big-0.009
 am-0.008
 to-0.008
 done-0.008
Token The
Token ID383
Feature activation-1.19e+00

Pos logit contributions
 am+0.004
+0.004
 done+0.003
 story+0.003
 big+0.002
Neg logit contributions
izing-0.028
yles-0.027
ning-0.027
king-0.027
ellery-0.027
Token par
Token ID1582
Feature activation-9.07e+00

Pos logit contributions
izing+0.023
king+0.022
yles+0.021
ning+0.021
ellery+0.021
Neg logit contributions
 am-0.029
 done-0.027
-0.026
 to-0.025
 story-0.025
Tokenrot
Token ID10599
Feature activation-1.21e+00

Pos logit contributions
izing+0.142
yles+0.133
rily+0.132
ning+0.131
burn+0.124
Neg logit contributions
 am-0.254
-0.248
 story-0.242
 done-0.240
 big-0.233
Token felt
Token ID2936
Feature activation-1.32e+00

Pos logit contributions
izing+0.040
yles+0.039
ning+0.039
ellery+0.038
king+0.038
Neg logit contributions
 am-0.012
 done-0.010
-0.010
 story-0.009
 big-0.009
Token peaceful
Token ID12309
Feature activation+1.34e+00

Pos logit contributions
izing+0.035
rily+0.033
bly+0.032
ivating+0.032
yles+0.032
Neg logit contributions
 am-0.021
 story-0.020
 done-0.019
ossible-0.019
-0.017
Token while
Token ID981
Feature activation+1.27e+00

Pos logit contributions
 am+0.019
 done+0.016
+0.016
 story+0.016
 big+0.014
Neg logit contributions
izing-0.041
ning-0.039
yles-0.039
king-0.039
rily-0.039
Token it
Token ID340
Feature activation+1.20e+00

Pos logit contributions
+0.017
 am+0.016
 big+0.016
 to+0.016
 done+0.015
Neg logit contributions
izing-0.039
ellery-0.037
rily-0.037
yles-0.037
ksh-0.037
TokenBut
Token ID1537
Feature activation+5.27e-01

Pos logit contributions
izing+0.012
yles+0.012
ning+0.012
king+0.011
ellery+0.011
Neg logit contributions
 am-0.011
 done-0.011
-0.011
 story-0.010
 big-0.010
Token then
Token ID788
Feature activation+1.08e+00

Pos logit contributions
 am+0.010
+0.009
 done+0.009
 to+0.009
 story+0.008
Neg logit contributions
izing-0.014
yles-0.013
ning-0.013
king-0.013
ellery-0.013
Token one
Token ID530
Feature activation+3.11e+00

Pos logit contributions
 am+0.017
 done+0.016
 story+0.015
+0.015
 big+0.014
Neg logit contributions
izing-0.029
yles-0.028
ning-0.028
rily-0.028
ellery-0.027
Token of
Token ID286
Feature activation-9.75e-01

Pos logit contributions
 am+0.036
+0.031
 done+0.030
 story+0.026
+0.024
Neg logit contributions
izing-0.096
ning-0.094
bul-0.092
king-0.091
rily-0.091
Token the
Token ID262
Feature activation+3.12e+00

Pos logit contributions
izing+0.031
yles+0.030
king+0.029
ning+0.029
ellery+0.029
Neg logit contributions
 am-0.012
-0.012
 done-0.011
 story-0.010
 big-0.010
Token se
Token ID384
Feature activation-8.39e+00

Pos logit contributions
 am+0.052
+0.048
 done+0.046
 to+0.040
+0.039
Neg logit contributions
izing-0.082
ning-0.079
yles-0.078
king-0.077
bul-0.076
Tokenag
Token ID363
Feature activation-8.04e-01

Pos logit contributions
izing+0.223
ning+0.212
yles+0.212
king+0.210
rily+0.208
Neg logit contributions
 am-0.146
-0.137
 done-0.130
 big-0.130
 story-0.126
Tokenull
Token ID724
Feature activation-2.76e+00

Pos logit contributions
izing+0.014
ning+0.014
rily+0.013
king+0.013
ants+0.013
Neg logit contributions
 am-0.021
 done-0.020
 bad-0.019
-0.019
 story-0.019
Tokens
Token ID82
Feature activation+2.37e+00

Pos logit contributions
izing+0.079
yles+0.076
ning+0.075
king+0.075
ellery+0.075
Neg logit contributions
 am-0.042
 done-0.039
-0.039
 story-0.036
 big-0.036
Token suddenly
Token ID6451
Feature activation+1.49e+00

Pos logit contributions
 am+0.039
+0.034
 done+0.033
 story+0.033
 big+0.030
Neg logit contributions
izing-0.064
king-0.063
ning-0.063
rily-0.061
yles-0.060
Token became
Token ID2627
Feature activation+1.33e+00

Pos logit contributions
 am+0.024
 story+0.021
+0.020
 done+0.019
 own+0.019
Neg logit contributions
izing-0.040
king-0.040
ning-0.039
rily-0.038
yles-0.038
Token,
Token ID11
Feature activation-2.16e+00

Pos logit contributions
izing+0.020
yles+0.019
ning+0.019
king+0.019
ellery+0.019
Neg logit contributions
 am-0.003
-0.003
 done-0.003
 story-0.002
 big-0.002
Token "
Token ID366
Feature activation-6.15e+00

Pos logit contributions
izing+0.075
ellery+0.073
yles+0.073
ning+0.070
burn+0.069
Neg logit contributions
-0.025
 to-0.021
 am-0.020
 big-0.018
 done-0.017
TokenThat
Token ID2504
Feature activation-4.08e-01

Pos logit contributions
rily+0.177
izing+0.170
ellery+0.170
yles+0.165
arians+0.163
Neg logit contributions
-0.111
 am-0.100
 was-0.089
-0.086
 to-0.086
Token is
Token ID318
Feature activation-6.58e-02

Pos logit contributions
izing+0.011
yles+0.010
king+0.010
ellery+0.010
ning+0.010
Neg logit contributions
 am-0.007
-0.007
 done-0.007
 story-0.006
 big-0.006
Token an
Token ID281
Feature activation-2.16e+00

Pos logit contributions
yles+0.002
izing+0.002
rily+0.002
king+0.002
ellery+0.002
Neg logit contributions
 am-0.001
 done-0.001
-0.001
 big-0.001
 to-0.001
Token aer
Token ID9551
Feature activation-8.19e+00

Pos logit contributions
yles+0.050
king+0.049
izing+0.047
ning+0.045
ellery+0.045
Neg logit contributions
 big-0.047
 done-0.046
 bad-0.045
 am-0.045
 story-0.044
Tokenopl
Token ID20106
Feature activation-6.91e+00

Pos logit contributions
izing+0.157
yles+0.155
rily+0.152
ning+0.149
king+0.148
Neg logit contributions
 am-0.200
 done-0.195
-0.193
 story-0.189
 big-0.182
Tokenane
Token ID1531
Feature activation-2.89e+00

Pos logit contributions
izing+0.153
rily+0.151
ellery+0.142
king+0.141
yles+0.139
Neg logit contributions
 am-0.162
-0.152
 to-0.144
 story-0.141
 done-0.137
Token!
Token ID0
Feature activation-2.73e-01

Pos logit contributions
yles+0.104
izing+0.103
rily+0.100
ellery+0.100
king+0.099
Neg logit contributions
 am-0.025
 done-0.021
-0.021
 to-0.021
 story-0.019
Token It
Token ID632
Feature activation-1.30e+00

Pos logit contributions
izing+0.009
ellery+0.009
cking+0.009
yles+0.009
rily+0.008
Neg logit contributions
-0.004
 He-0.004
 am-0.004
 to-0.003
 is-0.003
Token's
Token ID338
Feature activation+1.59e-02

Pos logit contributions
izing+0.046
yles+0.045
king+0.044
ellery+0.044
rily+0.044
Neg logit contributions
 am-0.012
-0.010
 done-0.010
 story-0.008
 big-0.008
Token an
Token ID281
Feature activation-1.60e+00

Pos logit contributions
izing+0.075
ning+0.073
yles+0.073
rily+0.071
king+0.071
Neg logit contributions
 am-0.027
 done-0.025
 story-0.023
-0.023
 big-0.020
Token orange
Token ID10912
Feature activation-5.12e-01

Pos logit contributions
yles+0.048
izing+0.046
king+0.046
etti+0.044
ants+0.044
Neg logit contributions
 big-0.024
 am-0.023
 done-0.022
 bad-0.022
 own-0.022
Token rope
Token ID17182
Feature activation-2.00e+00

Pos logit contributions
izing+0.013
yles+0.012
ning+0.012
king+0.012
ellery+0.012
Neg logit contributions
 am-0.010
-0.009
 done-0.009
 story-0.009
 big-0.008
Token to
Token ID284
Feature activation-7.13e-01

Pos logit contributions
izing+0.065
ning+0.064
king+0.063
rily+0.063
yles+0.062
Neg logit contributions
 am-0.021
 done-0.019
 story-0.018
-0.017
 bad-0.016
Token the
Token ID262
Feature activation+1.04e+00

Pos logit contributions
izing+0.022
yles+0.022
king+0.021
ellery+0.021
ning+0.021
Neg logit contributions
 am-0.010
-0.010
 big-0.009
 done-0.009
 to-0.009
Token kay
Token ID34681
Feature activation-8.72e+00

Pos logit contributions
 am+0.016
 big+0.016
+0.015
 done+0.014
 to+0.014
Neg logit contributions
izing-0.030
yles-0.030
ellery-0.029
rily-0.029
king-0.029
Tokenak
Token ID461
Feature activation+8.62e-01

Pos logit contributions
izing+0.217
yles+0.206
ning+0.205
king+0.203
ellery+0.200
Neg logit contributions
 am-0.166
 done-0.155
-0.153
 story-0.148
 big-0.145
Token for
Token ID329
Feature activation+1.43e+00

Pos logit contributions
 am+0.006
 done+0.005
 story+0.005
+0.005
 bad+0.004
Neg logit contributions
izing-0.031
ning-0.030
king-0.030
rily-0.030
yles-0.030
Token him
Token ID683
Feature activation+2.81e+00

Pos logit contributions
 am+0.016
 done+0.015
+0.015
 big+0.013
 to+0.013
Neg logit contributions
izing-0.047
yles-0.046
ning-0.045
king-0.045
rily-0.045
Token.
Token ID13
Feature activation+4.85e-01

Pos logit contributions
 am+0.020
 done+0.017
 story+0.016
+0.015
 bad+0.013
Neg logit contributions
izing-0.099
ning-0.098
yles-0.096
king-0.095
ellery-0.095
Token His
Token ID2399
Feature activation+2.42e+00

Pos logit contributions
 am+0.004
+0.003
 done+0.003
 story+0.003
 big+0.002
Neg logit contributions
izing-0.018
yles-0.017
ning-0.017
king-0.017
ellery-0.017