TOP ACTIVATIONS
MAX = 5.802

a sign that says " P izza ". Sara and Ben
this rope ?" P ete replied , " Yes
!" Ben says . " P ill ows are fun !"
runs away . P oppy sees Roc co and
forgive us ?" P andy smiled . He said
our toys ." P apa says : " You
your heart ." P oppy nodded . He said
" Yes !" P ete then took the rope
a sign that said " P izza ". They liked pizza
! â P ete ran to the shore
Ben says . P olly nods . He likes
them all !" P oppy is angry and sad
to help . P apa showed Tommy how to
with coins ! P ete and Paul looked at
!" Ben says . " P ill ows are fun !"
in your bag ?" P olly smiled proudly and said
join him . P enny said ,
. She said , " P inky , how can you
says . " P ray ing is like talking
to do ." P oppy smiled and said ,

MIN ACTIVATIONS
MIN = -7.861

The snake his ses . L ila and Tom
claws and bites and his ses at the bars . He
scare it . It his ses and shows its teeth .
nose . The cat his ses and scratches his face .
strangers . The cat his ses at Tom and Sue .
angry snake . It his ses and snaps at Ben .
a cat . She his ses and scratches at the dog
and angry . It his ses and fl aps its wings
like that . It his ses and fl aps its wings
ked tongue . It his ses and swim s near the
is afraid . It his ses and scratches Tom 's hand
snake sees Tom and his ses . It opens its mouth
is mean . He his ses and runs away . He
it . The cat his ses and scratches him . Ben
kitten is scared and his ses at Tom . Tom is
of the web and his ses at Ben . Ben drops
is afraid . It his ses and scratches Tom 's hand
is angry . It his ses . It scratches . It
slide . The cat his ses at him . Tom is
of Tom . It his ses and scratches . It hurts

INTERVAL 2.386 - 5.802
CONTAINS 0.973%

soon !" L ily hung up the phone and
, more evil than the devil , the poor have it
very happy ." J essa smiled , and they
him . She smiled and p atted his head . Max
't find one . She decided to go to the store

INTERVAL -1.030 - 2.386
CONTAINS 87.774%

big hill with many rocks and dirt . They want to
splash water everywhere . After they finished , Lily 's mom
inter was happy to help . She put the paper into
that she had put it in the kitchen drawer . She
fire man for being so kind and helpful . They hugged

INTERVAL -4.445 - -1.030
CONTAINS 11.239%

wet and red ! That is not nice !"
big cord and hang on tight ! <|endoftext|> Once upon a
, and sometimes they fought over them . "
saw a little boy handing out muff ins . The bear
loved to run around . She loved adventure and being outside

INTERVAL -7.861 - -4.445
CONTAINS 0.014%

. One day , Wh isk ers saw a bird in
No , it is your fault , you drove too fast
and quickly started to m unch it all up . He
it was Tim my 's fault but Tim my felt guilty
, Riley saw a bird soaring through the sky and realised
Token a
Token ID257
Feature activation-2.19e-01

Pos logit contributions
 water+0.152
 p+0.124
 was+0.114
 cool+0.112
 other+0.112
Neg logit contributions
istent-0.371
osity-0.338
urance-0.330
istence-0.317
 Majesty-0.314
Token sign
Token ID1051
Feature activation+3.25e-01

Pos logit contributions
istent+0.027
osity+0.025
urance+0.024
istence+0.023
aries+0.023
Neg logit contributions
 water-0.010
 p-0.009
 cool-0.008
 other-0.008
 sw-0.007
Token that
Token ID326
Feature activation-4.71e-01

Pos logit contributions
 water+0.012
 p+0.010
 cool+0.009
 other+0.008
 sw+0.008
Neg logit contributions
istent-0.040
osity-0.037
urance-0.036
 fault-0.035
istence-0.034
Token says
Token ID1139
Feature activation-6.83e-01

Pos logit contributions
istent+0.063
osity+0.058
urance+0.057
istence+0.055
 Majesty+0.055
Neg logit contributions
 water-0.013
 p-0.009
 cool-0.008
 other-0.008
 sw-0.007
Token "
Token ID366
Feature activation-7.38e-01

Pos logit contributions
istent+0.084
osity+0.076
urance+0.075
istence+0.073
 Majesty+0.072
Neg logit contributions
 water-0.031
 p-0.024
.-0.024
 was-0.024
 other-0.023
TokenP
Token ID47
Feature activation+5.20e+00

Pos logit contributions
istent+0.076
osity+0.068
urance+0.067
 Majesty+0.066
 fault+0.064
Neg logit contributions
 water-0.046
 p-0.038
 other-0.037
 was-0.036
 cool-0.036
Tokenizza
Token ID9990
Feature activation-1.16e+00

Pos logit contributions
 water+0.457
.+0.410
 other+0.405
 p+0.401
 cool+0.401
Neg logit contributions
istent-0.375
osity-0.346
urance-0.329
istence-0.302
sing-0.290
Token".
Token ID1911
Feature activation-9.51e-01

Pos logit contributions
istent+0.135
osity+0.125
urance+0.121
istence+0.117
 Majesty+0.116
Neg logit contributions
 water-0.059
.-0.048
 p-0.046
 was-0.045
 other-0.044
Token Sara
Token ID24799
Feature activation+1.38e+00

Pos logit contributions
istent+0.106
osity+0.098
urance+0.094
 fault+0.093
 Majesty+0.093
Neg logit contributions
 water-0.054
 p-0.045
.-0.045
 other-0.042
 was-0.042
Token and
Token ID290
Feature activation+4.44e-02

Pos logit contributions
 water+0.068
 p+0.059
 was+0.055
 cool+0.052
 sw+0.051
Neg logit contributions
istent-0.161
osity-0.150
urance-0.145
 fault-0.140
istence-0.139
Token Ben
Token ID3932
Feature activation-7.28e-01

Pos logit contributions
 water+0.003
 p+0.003
 other+0.002
 cool+0.002
 pe+0.002
Neg logit contributions
istent-0.005
osity-0.004
urance-0.004
istence-0.004
aries-0.004
Token this
Token ID428
Feature activation-8.25e-01

Pos logit contributions
istent+0.019
osity+0.018
urance+0.017
istence+0.017
 Majesty+0.016
Neg logit contributions
 water-0.007
 p-0.005
 other-0.005
 cool-0.005
.-0.005
Token rope
Token ID17182
Feature activation-7.03e-01

Pos logit contributions
istent+0.094
osity+0.086
urance+0.084
istence+0.081
 Majesty+0.081
Neg logit contributions
 water-0.042
 p-0.034
 cool-0.032
 other-0.032
 sw-0.030
Token?"
Token ID1701
Feature activation+2.70e-01

Pos logit contributions
istent+0.085
osity+0.078
urance+0.077
 Majesty+0.074
istence+0.074
Neg logit contributions
 water-0.032
 p-0.026
.-0.023
 cool-0.023
 was-0.023
Token
Token ID198
Feature activation+1.96e-01

Pos logit contributions
 water+0.015
 p+0.012
 cool+0.012
 other+0.012
 sw+0.011
Neg logit contributions
istent-0.029
osity-0.026
urance-0.025
 Majesty-0.025
istence-0.025
Token
Token ID198
Feature activation+1.09e-01

Pos logit contributions
 water+0.010
 p+0.008
 cool+0.007
 away+0.007
 cream+0.007
Neg logit contributions
istent-0.021
osity-0.019
urance-0.019
istence-0.018
 Majesty-0.018
TokenP
Token ID47
Feature activation+5.20e+00

Pos logit contributions
 water+0.006
 p+0.005
 away+0.004
 cool+0.004
 other+0.004
Neg logit contributions
istent-0.012
osity-0.011
istence-0.010
urance-0.010
 Majesty-0.010
Tokenete
Token ID14471
Feature activation+1.26e-01

Pos logit contributions
 water+0.444
 p+0.406
.+0.398
 was+0.390
P+0.388
Neg logit contributions
istent-0.386
osity-0.341
urance-0.340
 Majesty-0.302
istence-0.301
Token replied
Token ID8712
Feature activation-5.50e-03

Pos logit contributions
 water+0.005
 p+0.005
 was+0.004
 sw+0.004
 cool+0.004
Neg logit contributions
istent-0.015
osity-0.014
urance-0.014
 fault-0.013
istence-0.013
Token,
Token ID11
Feature activation-3.77e-01

Pos logit contributions
istent+0.001
osity+0.001
urance+0.001
istence+0.001
aries+0.001
Neg logit contributions
 water-0.000
 p-0.000
.-0.000
 was-0.000
 cool-0.000
Token "
Token ID366
Feature activation-7.27e-01

Pos logit contributions
istent+0.034
 fault+0.030
osity+0.030
urance+0.030
aries+0.030
Neg logit contributions
 water-0.028
 p-0.026
.-0.025
 was-0.025
 sw-0.024
TokenYes
Token ID5297
Feature activation+6.19e-01

Pos logit contributions
istent+0.079
osity+0.073
istence+0.068
urance+0.067
 Majesty+0.065
Neg logit contributions
 water-0.039
 p-0.032
 cool-0.029
 other-0.029
 away-0.029
Token!"
Token ID2474
Feature activation-1.23e+00

Pos logit contributions
 water+0.014
.+0.006
 p+0.003
 was+0.001
 other+0.000
Neg logit contributions
istent-0.212
osity-0.200
urance-0.196
istence-0.191
 Majesty-0.187
Token Ben
Token ID3932
Feature activation-7.71e-01

Pos logit contributions
istent+0.149
osity+0.137
urance+0.133
istence+0.129
 fault+0.128
Neg logit contributions
 water-0.057
 p-0.047
 other-0.043
 cool-0.042
.-0.042
Token says
Token ID1139
Feature activation-6.27e-01

Pos logit contributions
istent+0.104
osity+0.098
urance+0.095
istence+0.092
 Majesty+0.091
Neg logit contributions
 water-0.024
 p-0.019
 was-0.015
 cool-0.015
 other-0.015
Token.
Token ID13
Feature activation+2.09e-01

Pos logit contributions
istent+0.095
osity+0.089
urance+0.087
istence+0.085
 Majesty+0.085
Neg logit contributions
 water-0.009
 p-0.003
.-0.003
 cool-0.002
 was-0.002
Token "
Token ID366
Feature activation-6.06e-01

Pos logit contributions
 water+0.010
 p+0.008
 cool+0.007
 other+0.007
.+0.007
Neg logit contributions
istent-0.025
osity-0.023
urance-0.023
 fault-0.022
 Majesty-0.022
TokenP
Token ID47
Feature activation+5.19e+00

Pos logit contributions
istent+0.068
osity+0.062
urance+0.060
istence+0.059
 Majesty+0.058
Neg logit contributions
 water-0.029
 p-0.025
 sw-0.021
 pe-0.021
 cool-0.021
Tokenill
Token ID359
Feature activation-1.45e-01

Pos logit contributions
 water+0.409
.+0.365
 p+0.364
 cool+0.345
 other+0.338
Neg logit contributions
istent-0.441
osity-0.416
urance-0.388
istence-0.357
 Majesty-0.348
Tokenows
Token ID1666
Feature activation-2.77e+00

Pos logit contributions
istent+0.019
osity+0.017
urance+0.017
istence+0.016
aries+0.016
Neg logit contributions
 water-0.006
 p-0.005
.-0.005
 was-0.004
 cool-0.004
Token are
Token ID389
Feature activation-1.44e-01

Pos logit contributions
istent+0.352
osity+0.323
urance+0.318
istence+0.304
 Majesty+0.303
Neg logit contributions
 water-0.120
 p-0.095
 cool-0.085
.-0.082
 was-0.081
Token fun
Token ID1257
Feature activation+7.92e-01

Pos logit contributions
istent+0.018
osity+0.017
urance+0.016
istence+0.016
 Majesty+0.016
Neg logit contributions
 water-0.006
 p-0.005
 cool-0.005
 other-0.005
.-0.004
Token!"
Token ID2474
Feature activation-1.16e+00

Pos logit contributions
 water+0.024
 p+0.017
.+0.015
 cool+0.014
 other+0.014
Neg logit contributions
istent-0.110
osity-0.102
urance-0.100
istence-0.097
 Majesty-0.096
Token runs
Token ID4539
Feature activation-1.29e+00

Pos logit contributions
 water+0.006
 p+0.005
 cool+0.005
 other+0.005
 sw+0.005
Neg logit contributions
istent-0.008
osity-0.007
urance-0.007
 Majesty-0.007
istence-0.007
Token away
Token ID1497
Feature activation+2.62e+00

Pos logit contributions
istent+0.135
osity+0.128
urance+0.126
 fault+0.123
istence+0.120
Neg logit contributions
 water-0.054
 cool-0.043
 p-0.043
 other-0.042
P-0.042
Token.
Token ID13
Feature activation+1.93e-01

Pos logit contributions
 water+0.061
 p+0.035
 cool+0.032
 other+0.030
 sw+0.027
Neg logit contributions
istent-0.359
osity-0.336
urance-0.328
 fault-0.319
istence-0.319
Token
Token ID198
Feature activation+2.86e-01

Pos logit contributions
 water+0.009
 p+0.008
 other+0.007
 cool+0.007
 was+0.007
Neg logit contributions
istent-0.023
osity-0.021
urance-0.021
istence-0.020
 Majesty-0.020
Token
Token ID198
Feature activation+2.55e-01

Pos logit contributions
 water+0.013
 p+0.010
 cool+0.009
 other+0.009
 sw+0.009
Neg logit contributions
istent-0.033
osity-0.031
urance-0.030
istence-0.029
 Majesty-0.029
TokenP
Token ID47
Feature activation+5.17e+00

Pos logit contributions
 water+0.012
 p+0.010
 cool+0.009
 cream+0.009
 pe+0.009
Neg logit contributions
istent-0.028
osity-0.025
istence-0.025
urance-0.024
 Majesty-0.024
Tokenoppy
Token ID26696
Feature activation-1.61e+00

Pos logit contributions
 water+0.464
P+0.422
.+0.416
 p+0.416
 was+0.409
Neg logit contributions
istent-0.377
osity-0.333
urance-0.324
istence-0.288
sing-0.272
Token sees
Token ID7224
Feature activation-8.66e-01

Pos logit contributions
istent+0.192
osity+0.178
urance+0.170
istence+0.164
arsh+0.158
Neg logit contributions
 water-0.085
 p-0.075
 was-0.070
 sw-0.066
 went-0.065
Token Roc
Token ID13545
Feature activation+1.27e+00

Pos logit contributions
istent+0.093
osity+0.085
urance+0.083
 Majesty+0.080
istence+0.079
Neg logit contributions
 water-0.047
 p-0.040
 cool-0.037
 other-0.037
 sw-0.036
Tokenco
Token ID1073
Feature activation+1.88e+00

Pos logit contributions
 water+0.106
 p+0.099
 other+0.093
.+0.093
 cool+0.093
Neg logit contributions
istent-0.098
osity-0.089
urance-0.082
istence-0.082
 Majesty-0.077
Token and
Token ID290
Feature activation+1.41e-01

Pos logit contributions
 water+0.110
 p+0.093
 other+0.091
 was+0.087
.+0.087
Neg logit contributions
istent-0.199
osity-0.184
urance-0.177
 Majesty-0.173
istence-0.171
Token forgive
Token ID20927
Feature activation+1.84e+00

Pos logit contributions
istent+0.047
osity+0.041
urance+0.041
istence+0.039
 Majesty+0.038
Neg logit contributions
 water-0.028
 p-0.023
 other-0.022
 sw-0.022
 cream-0.022
Token us
Token ID514
Feature activation-9.78e-01

Pos logit contributions
 water+0.094
 p+0.079
 cre+0.075
 sw+0.075
 cool+0.074
Neg logit contributions
istent-0.187
isdom-0.168
osity-0.166
urance-0.165
aries-0.163
Token?"
Token ID1701
Feature activation+3.41e-01

Pos logit contributions
istent+0.107
osity+0.097
urance+0.095
 fault+0.091
istence+0.091
Neg logit contributions
 water-0.051
 p-0.042
 cool-0.040
 sw-0.039
 other-0.039
Token
Token ID198
Feature activation+3.50e-01

Pos logit contributions
 water+0.016
 p+0.013
 cool+0.012
 other+0.012
 sw+0.011
Neg logit contributions
istent-0.040
osity-0.036
urance-0.036
istence-0.034
 Majesty-0.034
Token
Token ID198
Feature activation+3.03e-01

Pos logit contributions
 water+0.018
 p+0.015
 away+0.014
 cool+0.014
 cream+0.014
Neg logit contributions
istent-0.037
osity-0.033
urance-0.033
istence-0.032
 Majesty-0.032
TokenP
Token ID47
Feature activation+5.16e+00

Pos logit contributions
 water+0.014
 away+0.011
 cool+0.011
 p+0.011
 inside+0.011
Neg logit contributions
istent-0.033
osity-0.029
istence-0.028
urance-0.028
arsh-0.028
Tokenandy
Token ID10757
Feature activation-1.10e+00

Pos logit contributions
 water+0.472
 p+0.429
 sw+0.409
 cool+0.407
 was+0.406
Neg logit contributions
istent-0.378
osity-0.327
urance-0.323
istence-0.293
 Majesty-0.286
Token smiled
Token ID13541
Feature activation+3.21e-01

Pos logit contributions
istent+0.134
osity+0.123
urance+0.121
istence+0.116
 Majesty+0.116
Neg logit contributions
 water-0.047
 p-0.037
 cool-0.034
 other-0.034
 sw-0.033
Token.
Token ID13
Feature activation+2.61e-01

Pos logit contributions
 water+0.013
 p+0.009
 other+0.009
 sw+0.008
 cool+0.008
Neg logit contributions
istent-0.039
osity-0.036
urance-0.035
 fault-0.034
istence-0.034
Token He
Token ID679
Feature activation+1.65e-01

Pos logit contributions
 water+0.016
 p+0.015
.+0.014
 was+0.013
 sw+0.013
Neg logit contributions
istent-0.028
urance-0.024
aries-0.023
osity-0.023
 fault-0.023
Token said
Token ID531
Feature activation-3.17e-02

Pos logit contributions
 water+0.006
 other+0.004
 away+0.004
 sand+0.004
P+0.004
Neg logit contributions
istent-0.019
osity-0.017
urance-0.017
istence-0.017
isdom-0.017
Token our
Token ID674
Feature activation-3.89e-01

Pos logit contributions
 water+0.029
 p+0.024
 sw+0.023
 cool+0.022
 went+0.022
Neg logit contributions
istent-0.069
osity-0.063
urance-0.062
 fault-0.060
 Majesty-0.060
Token toys
Token ID14958
Feature activation+9.21e-01

Pos logit contributions
istent+0.043
osity+0.039
urance+0.039
 Majesty+0.037
 fault+0.037
Neg logit contributions
 water-0.020
 p-0.016
 cool-0.015
 other-0.015
 sw-0.015
Token."
Token ID526
Feature activation-3.64e-01

Pos logit contributions
 water+0.030
 p+0.022
 cool+0.019
 sw+0.019
 other+0.019
Neg logit contributions
istent-0.119
osity-0.109
urance-0.108
 fault-0.105
 Majesty-0.104
Token
Token ID198
Feature activation+1.78e-01

Pos logit contributions
istent+0.045
osity+0.041
urance+0.040
istence+0.039
 Majesty+0.039
Neg logit contributions
 water-0.016
 p-0.012
 other-0.011
 cool-0.011
 sw-0.011
Token
Token ID198
Feature activation+8.82e-02

Pos logit contributions
 water+0.008
 p+0.007
 cool+0.006
 away+0.006
 sw+0.006
Neg logit contributions
istent-0.020
osity-0.018
urance-0.018
 Majesty-0.017
istence-0.017
TokenP
Token ID47
Feature activation+5.16e+00

Pos logit contributions
 water+0.004
 p+0.003
 cool+0.003
 away+0.003
 other+0.003
Neg logit contributions
istent-0.010
osity-0.009
urance-0.009
istence-0.009
 Majesty-0.009
Tokenapa
Token ID32678
Feature activation-9.70e-01

Pos logit contributions
 water+0.468
 p+0.419
.+0.419
P+0.417
 said+0.410
Neg logit contributions
istent-0.353
osity-0.329
urance-0.320
istence-0.282
aries-0.275
Token says
Token ID1139
Feature activation-6.46e-01

Pos logit contributions
istent+0.122
osity+0.113
urance+0.111
istence+0.107
 Majesty+0.107
Neg logit contributions
 water-0.038
 p-0.030
 cool-0.026
 was-0.025
 sw-0.025
Token:
Token ID25
Feature activation+1.34e+00

Pos logit contributions
istent+0.078
osity+0.071
urance+0.070
istence+0.068
 Majesty+0.067
Neg logit contributions
 water-0.029
 p-0.024
 cool-0.022
 other-0.021
 was-0.021
Token "
Token ID366
Feature activation-7.08e-01

Pos logit contributions
 water+0.076
 p+0.066
.+0.065
 was+0.064
 cool+0.061
Neg logit contributions
istent-0.147
osity-0.131
urance-0.129
aries-0.127
 fault-0.126
TokenYou
Token ID1639
Feature activation+4.51e-01

Pos logit contributions
istent+0.077
osity+0.070
istence+0.065
urance+0.065
arsh+0.064
Neg logit contributions
 water-0.037
 p-0.031
 cool-0.029
 away-0.029
 pe-0.028
Token your
Token ID534
Feature activation-3.75e-01

Pos logit contributions
 water+0.033
 other+0.025
 p+0.024
.+0.023
 cool+0.023
Neg logit contributions
istent-0.102
osity-0.095
urance-0.091
istence-0.089
 Majesty-0.089
Token heart
Token ID2612
Feature activation-4.30e-01

Pos logit contributions
istent+0.041
osity+0.037
urance+0.035
istence+0.034
arsh+0.033
Neg logit contributions
 water-0.024
 p-0.021
 other-0.019
 cool-0.019
 sw-0.018
Token."
Token ID526
Feature activation-3.41e-01

Pos logit contributions
istent+0.061
osity+0.057
urance+0.056
istence+0.054
 Majesty+0.053
Neg logit contributions
 water-0.011
.-0.008
 p-0.007
 other-0.007
 cool-0.006
Token
Token ID198
Feature activation+2.00e-01

Pos logit contributions
istent+0.045
osity+0.041
urance+0.040
istence+0.039
 Majesty+0.039
Neg logit contributions
 water-0.012
 p-0.010
.-0.009
 other-0.009
 was-0.009
Token
Token ID198
Feature activation+1.60e-01

Pos logit contributions
 water+0.008
 p+0.006
 cool+0.006
 other+0.006
 sw+0.005
Neg logit contributions
istent-0.025
osity-0.023
urance-0.022
 Majesty-0.022
istence-0.022
TokenP
Token ID47
Feature activation+5.15e+00

Pos logit contributions
 water+0.007
 p+0.006
 cool+0.005
 other+0.005
 sw+0.005
Neg logit contributions
istent-0.019
osity-0.017
urance-0.017
istence-0.016
 Majesty-0.016
Tokenoppy
Token ID26696
Feature activation-1.82e+00

Pos logit contributions
 water+0.411
P+0.384
 p+0.378
.+0.375
 was+0.374
Neg logit contributions
istent-0.398
osity-0.364
urance-0.355
istence-0.318
sing-0.307
Token nodded
Token ID14464
Feature activation+1.88e+00

Pos logit contributions
istent+0.232
osity+0.218
urance+0.209
istence+0.202
 fault+0.200
Neg logit contributions
 water-0.073
 p-0.060
 was-0.058
 went-0.052
 sw-0.051
Token.
Token ID13
Feature activation+1.88e-01

Pos logit contributions
 water+0.074
 p+0.053
 other+0.050
 cool+0.050
P+0.047
Neg logit contributions
istent-0.229
urance-0.209
osity-0.209
 Majesty-0.199
istence-0.197
Token He
Token ID679
Feature activation+1.15e-01

Pos logit contributions
 water+0.007
.+0.007
 p+0.007
 was+0.006
 his+0.005
Neg logit contributions
istent-0.024
aries-0.021
urance-0.021
osity-0.020
 fault-0.020
Token said
Token ID531
Feature activation-1.04e-01

Pos logit contributions
 water+0.005
 p+0.004
 other+0.004
 cool+0.003
 away+0.003
Neg logit contributions
istent-0.013
osity-0.012
urance-0.012
 Majesty-0.012
istence-0.012
Token "
Token ID366
Feature activation-7.27e-01

Pos logit contributions
istent+0.034
 fault+0.030
osity+0.030
urance+0.030
aries+0.030
Neg logit contributions
 water-0.028
 p-0.026
.-0.025
 was-0.025
 sw-0.024
TokenYes
Token ID5297
Feature activation+6.19e-01

Pos logit contributions
istent+0.079
osity+0.073
istence+0.068
urance+0.067
 Majesty+0.065
Neg logit contributions
 water-0.039
 p-0.032
 cool-0.029
 other-0.029
 away-0.029
Token!"
Token ID2474
Feature activation-1.07e+00

Pos logit contributions
 water+0.027
 p+0.022
 cool+0.020
 other+0.020
.+0.020
Neg logit contributions
istent-0.075
osity-0.070
urance-0.068
istence-0.066
 Majesty-0.065
Token
Token ID198
Feature activation+1.53e-01

Pos logit contributions
istent+0.120
osity+0.110
urance+0.107
 Majesty+0.103
istence+0.103
Neg logit contributions
 water-0.055
 p-0.046
 cool-0.043
 other-0.043
 sw-0.041
Token
Token ID198
Feature activation+1.26e-01

Pos logit contributions
 water+0.008
 p+0.006
 away+0.006
 cool+0.006
 sw+0.006
Neg logit contributions
istent-0.017
osity-0.015
urance-0.015
istence-0.014
arsh-0.014
TokenP
Token ID47
Feature activation+5.13e+00

Pos logit contributions
 water+0.007
 p+0.005
 cool+0.005
 away+0.005
 other+0.005
Neg logit contributions
istent-0.014
osity-0.012
urance-0.012
istence-0.012
arsh-0.011
Tokenete
Token ID14471
Feature activation+1.33e-01

Pos logit contributions
 water+0.496
 p+0.452
P+0.437
 was+0.434
 cool+0.434
Neg logit contributions
istent-0.334
osity-0.291
urance-0.286
 Majesty-0.259
 fault-0.256
Token then
Token ID788
Feature activation+7.50e-01

Pos logit contributions
 water+0.004
 p+0.004
 was+0.003
 sw+0.003
 cool+0.003
Neg logit contributions
istent-0.017
osity-0.016
urance-0.016
 fault-0.016
 Majesty-0.015
Token took
Token ID1718
Feature activation+2.20e-01

Pos logit contributions
 water+0.028
 p+0.022
 cool+0.019
 other+0.019
 sw+0.019
Neg logit contributions
istent-0.096
osity-0.088
urance-0.087
istence-0.083
 Majesty-0.083
Token the
Token ID262
Feature activation-2.98e-01

Pos logit contributions
 water+0.009
 p+0.008
 sw+0.007
 other+0.007
 cool+0.007
Neg logit contributions
istent-0.025
osity-0.023
urance-0.023
 fault-0.022
istence-0.022
Token rope
Token ID17182
Feature activation-6.21e-01

Pos logit contributions
istent+0.032
osity+0.029
urance+0.029
 Majesty+0.028
istence+0.027
Neg logit contributions
 water-0.017
 p-0.014
 cool-0.013
 other-0.013
 sw-0.013
Token a
Token ID257
Feature activation-7.38e-02

Pos logit contributions
 water+0.017
 p+0.013
 cool+0.012
 other+0.012
 sw+0.011
Neg logit contributions
istent-0.054
osity-0.050
urance-0.049
 Majesty-0.048
 fault-0.047
Token sign
Token ID1051
Feature activation+4.97e-01

Pos logit contributions
istent+0.009
osity+0.008
urance+0.008
 Majesty+0.008
 fault+0.008
Neg logit contributions
 water-0.003
 p-0.002
 decided-0.002
 other-0.002
 cool-0.002
Token that
Token ID326
Feature activation-1.54e-01

Pos logit contributions
 water+0.023
 p+0.019
P+0.017
 sw+0.017
 cool+0.017
Neg logit contributions
istent-0.055
osity-0.050
urance-0.049
istence-0.047
 fault-0.047
Token said
Token ID531
Feature activation-2.46e-01

Pos logit contributions
istent+0.020
osity+0.018
urance+0.018
istence+0.017
aries+0.017
Neg logit contributions
 water-0.004
 p-0.003
 away-0.002
P-0.002
 other-0.002
Token "
Token ID366
Feature activation-6.16e-01

Pos logit contributions
istent+0.024
osity+0.021
urance+0.021
istence+0.020
 Majesty+0.020
Neg logit contributions
 water-0.017
 was-0.015
 p-0.015
.-0.015
 other-0.015
TokenP
Token ID47
Feature activation+5.13e+00

Pos logit contributions
istent+0.061
osity+0.055
urance+0.054
istence+0.051
aries+0.051
Neg logit contributions
 water-0.039
 p-0.034
 cool-0.032
 other-0.031
 sw-0.031
Tokenizza
Token ID9990
Feature activation-1.13e+00

Pos logit contributions
 water+0.455
 cool+0.404
.+0.403
 p+0.400
 other+0.397
Neg logit contributions
istent-0.367
osity-0.326
urance-0.314
istence-0.289
 Majesty-0.277
Token".
Token ID1911
Feature activation-8.54e-01

Pos logit contributions
istent+0.127
osity+0.116
urance+0.113
 fault+0.110
 Majesty+0.110
Neg logit contributions
 water-0.062
.-0.051
 p-0.049
 was-0.049
 other-0.048
Token They
Token ID1119
Feature activation+6.05e-01

Pos logit contributions
istent+0.095
osity+0.087
urance+0.082
 Majesty+0.082
istence+0.080
Neg logit contributions
 water-0.050
 p-0.042
 other-0.039
.-0.039
 was-0.039
Token liked
Token ID8288
Feature activation+2.21e+00

Pos logit contributions
 water+0.024
 p+0.018
 cool+0.017
 other+0.016
 away+0.016
Neg logit contributions
istent-0.073
osity-0.066
urance-0.065
istence-0.062
 Majesty-0.062
Token pizza
Token ID14256
Feature activation+2.43e-01

Pos logit contributions
 water+0.121
 p+0.098
 other+0.095
 cool+0.093
 was+0.089
Neg logit contributions
istent-0.253
osity-0.230
urance-0.224
istence-0.217
 Majesty-0.213
Token!
Token ID0
Feature activation-2.09e+00

Pos logit contributions
 water+0.020
.+0.018
 in+0.008
 was+0.007
 p+0.006
Neg logit contributions
istent-0.202
osity-0.193
urance-0.189
istence-0.188
 Majesty-0.186
Tokenâ
Token ID22940
Feature activation+1.34e+00

Pos logit contributions
istent+0.194
osity+0.180
urance+0.176
 fault+0.176
 Majesty+0.170
Neg logit contributions
 water-0.143
 p-0.129
 other-0.121
.-0.120
 cool-0.118
Token
Token ID26391
Feature activation-2.32e-01

Pos logit contributions
 water+0.122
 p+0.110
 other+0.108
 cool+0.105
 sw+0.104
Neg logit contributions
istent-0.099
osity-0.084
urance-0.083
istence-0.078
 Majesty-0.074
Token
Token ID198
Feature activation+2.92e-01

Pos logit contributions
istent+0.025
osity+0.024
urance+0.022
 fault+0.022
sing+0.022
Neg logit contributions
 water-0.012
.-0.012
 was-0.011
 p-0.011
 went-0.010
Token
Token ID198
Feature activation+2.76e-01

Pos logit contributions
 water+0.013
 p+0.011
 cool+0.010
 other+0.010
 sw+0.009
Neg logit contributions
istent-0.034
osity-0.031
urance-0.031
istence-0.030
 Majesty-0.029
TokenP
Token ID47
Feature activation+5.11e+00

Pos logit contributions
 water+0.012
 p+0.009
 cool+0.009
 pe+0.008
 other+0.008
Neg logit contributions
istent-0.033
osity-0.030
urance-0.029
istence-0.029
aries-0.028
Tokenete
Token ID14471
Feature activation+4.57e-02

Pos logit contributions
 water+0.455
P+0.417
 p+0.410
 went+0.397
.+0.396
Neg logit contributions
istent-0.361
osity-0.332
urance-0.324
sing-0.307
ses-0.292
Token ran
Token ID4966
Feature activation+7.79e-01

Pos logit contributions
 water+0.001
 p+0.001
 was+0.001
 sw+0.001
 went+0.001
Neg logit contributions
istent-0.006
osity-0.006
urance-0.006
 fault-0.006
istence-0.005
Token to
Token ID284
Feature activation+2.65e-01

Pos logit contributions
 water+0.038
 p+0.031
 other+0.030
 cool+0.030
 sw+0.030
Neg logit contributions
istent-0.082
osity-0.075
urance-0.073
istence-0.071
 fault-0.070
Token the
Token ID262
Feature activation-1.07e-01

Pos logit contributions
 water+0.010
 p+0.007
 other+0.006
 cool+0.006
 sw+0.006
Neg logit contributions
istent-0.035
osity-0.033
urance-0.032
istence-0.031
 Majesty-0.031
Token shore
Token ID15191
Feature activation+1.04e+00

Pos logit contributions
istent+0.009
osity+0.009
 Majesty+0.009
urance+0.008
istence+0.008
Neg logit contributions
 water-0.006
S-0.006
 was-0.006
 p-0.006
P-0.006
Token Ben
Token ID3932
Feature activation-5.03e-01

Pos logit contributions
 water+0.023
 p+0.020
 other+0.019
 cool+0.019
 sw+0.019
Neg logit contributions
istent-0.027
osity-0.025
urance-0.024
istence-0.023
 Majesty-0.023
Token says
Token ID1139
Feature activation-5.15e-01

Pos logit contributions
istent+0.053
osity+0.048
urance+0.047
istence+0.045
 Majesty+0.045
Neg logit contributions
 water-0.030
 p-0.026
 other-0.024
 cool-0.024
 was-0.024
Token.
Token ID13
Feature activation+3.26e-01

Pos logit contributions
istent+0.079
osity+0.074
urance+0.072
 Majesty+0.071
istence+0.071
Neg logit contributions
 water-0.006
 p-0.002
 other-0.001
 cool-0.000
.-0.000
Token
Token ID198
Feature activation+3.43e-01

Pos logit contributions
 water+0.013
 p+0.010
 other+0.009
 cool+0.009
 sw+0.009
Neg logit contributions
istent-0.041
osity-0.037
urance-0.037
 Majesty-0.035
istence-0.035
Token
Token ID198
Feature activation+3.22e-01

Pos logit contributions
 water+0.016
 p+0.013
 cool+0.012
 sw+0.012
 pe+0.011
Neg logit contributions
istent-0.039
osity-0.036
urance-0.035
istence-0.034
 Majesty-0.034
TokenP
Token ID47
Feature activation+5.10e+00

Pos logit contributions
 water+0.017
 p+0.014
 cool+0.014
 pe+0.013
 sw+0.013
Neg logit contributions
istent-0.034
osity-0.031
urance-0.030
 Majesty-0.029
istence-0.029
Tokenolly
Token ID5098
Feature activation-3.73e-01

Pos logit contributions
 water+0.411
.+0.386
P+0.368
 p+0.349
 went+0.345
Neg logit contributions
istent-0.422
osity-0.376
urance-0.366
sing-0.338
istence-0.334
Token nods
Token ID34833
Feature activation+1.28e-01

Pos logit contributions
istent+0.046
osity+0.043
urance+0.041
istence+0.040
arsh+0.039
Neg logit contributions
 water-0.018
 p-0.016
 was-0.014
.-0.013
 sw-0.013
Token.
Token ID13
Feature activation+3.56e-01

Pos logit contributions
 water+0.005
 p+0.003
 cool+0.003
 sw+0.003
 other+0.003
Neg logit contributions
istent-0.015
urance-0.014
osity-0.014
isdom-0.013
arsh-0.013
Token He
Token ID679
Feature activation+1.29e-01

Pos logit contributions
 water+0.021
.+0.019
 p+0.018
 other+0.017
 went+0.016
Neg logit contributions
istent-0.039
urance-0.035
osity-0.034
aries-0.033
 fault-0.033
Token likes
Token ID7832
Feature activation+1.69e-01

Pos logit contributions
 water+0.008
 p+0.007
 cool+0.007
 was+0.007
 sw+0.007
Neg logit contributions
istent-0.014
osity-0.012
urance-0.012
istence-0.011
 fault-0.011
Token them
Token ID606
Feature activation+1.43e+00

Pos logit contributions
 water+0.010
 p+0.008
 cool+0.008
 sw+0.008
 other+0.008
Neg logit contributions
istent-0.023
osity-0.021
urance-0.021
 Majesty-0.021
 fault-0.020
Token all
Token ID477
Feature activation+4.50e-01

Pos logit contributions
 water+0.064
 p+0.051
 cool+0.047
 other+0.047
 sw+0.045
Neg logit contributions
istent-0.171
osity-0.157
urance-0.154
istence-0.148
 Majesty-0.148
Token!"
Token ID2474
Feature activation-9.92e-01

Pos logit contributions
 water+0.022
 p+0.018
 cool+0.017
 sw+0.017
 other+0.016
Neg logit contributions
istent-0.050
osity-0.046
urance-0.045
 fault-0.044
 Majesty-0.043
Token
Token ID198
Feature activation+3.12e-01

Pos logit contributions
istent+0.117
osity+0.106
urance+0.105
 Majesty+0.101
istence+0.101
Neg logit contributions
 water-0.044
 p-0.035
 cool-0.033
 other-0.032
 sw-0.032
Token
Token ID198
Feature activation+2.94e-01

Pos logit contributions
 water+0.016
 p+0.014
 away+0.013
 cream+0.013
 sw+0.013
Neg logit contributions
istent-0.032
urance-0.029
osity-0.028
arsh-0.028
 Majesty-0.027
TokenP
Token ID47
Feature activation+5.10e+00

Pos logit contributions
 water+0.015
 cool+0.012
 away+0.011
 inside+0.011
 p+0.011
Neg logit contributions
istent-0.029
 Majesty-0.026
osity-0.026
istence-0.026
arsh-0.026
Tokenoppy
Token ID26696
Feature activation-1.70e+00

Pos logit contributions
 water+0.471
 p+0.437
 was+0.419
.+0.416
P+0.414
Neg logit contributions
istent-0.358
osity-0.322
urance-0.306
istence-0.273
 fault-0.259
Token is
Token ID318
Feature activation-1.15e+00

Pos logit contributions
istent+0.199
osity+0.185
urance+0.177
istence+0.170
arsh+0.167
Neg logit contributions
 water-0.090
 p-0.079
 was-0.073
 sw-0.069
 went-0.068
Token angry
Token ID7954
Feature activation+7.62e-01

Pos logit contributions
istent+0.122
osity+0.110
urance+0.107
istence+0.103
 Majesty+0.102
Neg logit contributions
 water-0.071
 p-0.061
 cool-0.059
 other-0.058
 was-0.056
Token and
Token ID290
Feature activation+1.45e-01

Pos logit contributions
 water+0.021
 p+0.014
 cool+0.012
 other+0.012
 sw+0.011
Neg logit contributions
istent-0.105
osity-0.097
urance-0.096
 Majesty-0.093
istence-0.093
Token sad
Token ID6507
Feature activation-6.82e-01

Pos logit contributions
 water+0.009
 p+0.007
 cool+0.007
 other+0.007
 sw+0.007
Neg logit contributions
istent-0.015
osity-0.014
urance-0.013
 Majesty-0.013
istence-0.013
Token to
Token ID284
Feature activation+2.27e-01

Pos logit contributions
 water+0.005
.+0.005
 was+0.004
 in+0.004
 other+0.004
Neg logit contributions
istent-0.015
urance-0.014
osity-0.013
istence-0.013
ses-0.013
Token help
Token ID1037
Feature activation+1.41e+00

Pos logit contributions
 water+0.011
 p+0.009
 cool+0.009
 other+0.009
 sw+0.008
Neg logit contributions
istent-0.026
osity-0.024
urance-0.023
 Majesty-0.023
 fault-0.023
Token.
Token ID13
Feature activation+2.58e-01

Pos logit contributions
 water+0.051
 p+0.040
 cool+0.036
 sw+0.035
 other+0.035
Neg logit contributions
istent-0.178
osity-0.160
urance-0.160
istence-0.152
 Majesty-0.151
Token
Token ID198
Feature activation+3.76e-01

Pos logit contributions
 water+0.014
 p+0.011
 was+0.011
.+0.011
 other+0.011
Neg logit contributions
istent-0.029
osity-0.027
urance-0.026
 fault-0.026
 Majesty-0.025
Token
Token ID198
Feature activation+3.50e-01

Pos logit contributions
 water+0.015
 p+0.012
 cool+0.011
 other+0.011
 sw+0.010
Neg logit contributions
istent-0.046
osity-0.043
urance-0.042
istence-0.040
 Majesty-0.040
TokenP
Token ID47
Feature activation+5.09e+00

Pos logit contributions
 water+0.017
 p+0.015
 cool+0.013
 other+0.013
 sw+0.013
Neg logit contributions
istent-0.040
osity-0.036
urance-0.035
istence-0.034
 Majesty-0.034
Tokenapa
Token ID32678
Feature activation-1.10e+00

Pos logit contributions
 water+0.468
P+0.423
.+0.412
 was+0.412
 p+0.410
Neg logit contributions
istent-0.330
osity-0.314
urance-0.302
ses-0.274
 fault-0.269
Token showed
Token ID3751
Feature activation-2.26e-01

Pos logit contributions
istent+0.142
osity+0.133
urance+0.131
 fault+0.127
 Majesty+0.126
Neg logit contributions
 water-0.039
 p-0.031
 was-0.028
 sw-0.027
 went-0.025
Token Tommy
Token ID19919
Feature activation-4.62e-02

Pos logit contributions
istent+0.025
osity+0.023
urance+0.022
istence+0.021
 Majesty+0.021
Neg logit contributions
 water-0.012
 p-0.010
 other-0.010
 cool-0.010
 sw-0.009
Token how
Token ID703
Feature activation+6.50e-01

Pos logit contributions
istent+0.006
urance+0.005
osity+0.005
istence+0.005
 Majesty+0.005
Neg logit contributions
 water-0.002
.-0.002
 was-0.002
 in-0.002
 p-0.002
Token to
Token ID284
Feature activation+2.27e-01

Pos logit contributions
 water+0.029
 p+0.024
 cool+0.022
 other+0.021
 sw+0.021
Neg logit contributions
istent-0.077
osity-0.071
urance-0.068
istence-0.066
 fault-0.066
Token with
Token ID351
Feature activation-3.84e-01

Pos logit contributions
 water+0.002
 p+0.001
 other+0.001
 sw+0.001
 cool+0.001
Neg logit contributions
istent-0.005
urance-0.004
osity-0.004
 fault-0.004
isdom-0.004
Token coins
Token ID10796
Feature activation+1.47e+00

Pos logit contributions
istent+0.044
osity+0.040
urance+0.039
 fault+0.039
 Majesty+0.038
Neg logit contributions
 water-0.016
 p-0.013
P-0.012
 sw-0.012
 cool-0.012
Token!
Token ID0
Feature activation-2.20e+00

Pos logit contributions
 water+0.041
 p+0.030
 cool+0.025
P+0.025
 other+0.025
Neg logit contributions
istent-0.193
osity-0.179
urance-0.173
 fault-0.172
 Majesty-0.168
Token
Token ID198
Feature activation+2.27e-02

Pos logit contributions
istent+0.244
osity+0.224
urance+0.216
 Majesty+0.212
 fault+0.211
Neg logit contributions
 water-0.122
 p-0.105
 was-0.102
.-0.099
 other-0.098
Token
Token ID198
Feature activation-1.11e-02

Pos logit contributions
 water+0.001
 p+0.001
 other+0.001
 cool+0.001
 was+0.001
Neg logit contributions
istent-0.003
osity-0.003
urance-0.003
 Majesty-0.002
istence-0.002
TokenP
Token ID47
Feature activation+5.08e+00

Pos logit contributions
istent+0.001
osity+0.001
urance+0.001
 fault+0.001
 Majesty+0.001
Neg logit contributions
 water-0.001
 p-0.000
 other-0.000
 cool-0.000
 sw-0.000
Tokenete
Token ID14471
Feature activation+5.97e-02

Pos logit contributions
 water+0.453
 p+0.411
 was+0.406
P+0.401
 other+0.400
Neg logit contributions
istent-0.360
osity-0.329
urance-0.313
istence-0.289
 Majesty-0.284
Token and
Token ID290
Feature activation+5.25e-02

Pos logit contributions
 water+0.002
 p+0.001
 was+0.001
 sw+0.001
 went+0.001
Neg logit contributions
istent-0.008
osity-0.008
urance-0.007
 fault-0.007
istence-0.007
Token Paul
Token ID3362
Feature activation-5.54e-01

Pos logit contributions
 water+0.004
 p+0.003
 other+0.003
 was+0.003
 cool+0.003
Neg logit contributions
istent-0.005
osity-0.004
urance-0.004
istence-0.004
 fault-0.004
Token looked
Token ID3114
Feature activation+4.30e-01

Pos logit contributions
istent+0.070
osity+0.064
urance+0.063
istence+0.061
 Majesty+0.061
Neg logit contributions
 water-0.021
 p-0.016
 cool-0.015
 other-0.014
 sw-0.014
Token at
Token ID379
Feature activation-3.40e-01

Pos logit contributions
 water+0.022
P+0.019
 p+0.018
B+0.018
S+0.018
Neg logit contributions
istent-0.044
osity-0.040
 Majesty-0.039
urance-0.038
istence-0.037
Token!"
Token ID2474
Feature activation-1.05e+00

Pos logit contributions
 water+0.052
.+0.046
 p+0.040
 was+0.035
 cool+0.035
Neg logit contributions
istent-0.208
osity-0.198
urance-0.191
istence-0.185
aries-0.182
Token Ben
Token ID3932
Feature activation-5.48e-01

Pos logit contributions
istent+0.090
osity+0.081
urance+0.077
istence+0.073
 Majesty+0.073
Neg logit contributions
 water-0.086
 p-0.077
 other-0.074
 cool-0.073
 sw-0.072
Token says
Token ID1139
Feature activation-5.86e-01

Pos logit contributions
istent+0.061
osity+0.056
urance+0.055
istence+0.052
 Majesty+0.052
Neg logit contributions
 water-0.030
 p-0.025
 cool-0.023
 other-0.023
 sw-0.022
Token.
Token ID13
Feature activation+3.07e-01

Pos logit contributions
istent+0.088
osity+0.082
urance+0.081
 Majesty+0.078
istence+0.078
Neg logit contributions
 water-0.009
 p-0.003
 cool-0.002
 other-0.002
 sw-0.001
Token "
Token ID366
Feature activation-6.51e-01

Pos logit contributions
 water+0.023
 p+0.021
 cool+0.020
 other+0.020
 sw+0.019
Neg logit contributions
istent-0.027
osity-0.024
urance-0.024
 Majesty-0.022
istence-0.022
TokenP
Token ID47
Feature activation+5.08e+00

Pos logit contributions
istent+0.070
osity+0.062
urance+0.062
istence+0.060
arsh+0.059
Neg logit contributions
 water-0.033
 p-0.028
 sw-0.026
 cool-0.025
 away-0.024
Tokenill
Token ID359
Feature activation-5.13e-02

Pos logit contributions
 water+0.447
 p+0.400
.+0.394
 cool+0.385
P+0.374
Neg logit contributions
istent-0.389
osity-0.356
urance-0.333
istence-0.305
 Majesty-0.288
Tokenows
Token ID1666
Feature activation-2.68e+00

Pos logit contributions
istent+0.006
osity+0.006
urance+0.006
istence+0.006
aries+0.006
Neg logit contributions
 water-0.002
 p-0.002
.-0.002
 was-0.002
 cool-0.002
Token are
Token ID389
Feature activation-3.14e-02

Pos logit contributions
istent+0.321
osity+0.295
urance+0.289
 Majesty+0.277
istence+0.277
Neg logit contributions
 water-0.123
 p-0.098
 cool-0.091
 other-0.089
 sw-0.085
Token fun
Token ID1257
Feature activation+7.39e-01

Pos logit contributions
istent+0.004
osity+0.003
urance+0.003
istence+0.003
 Majesty+0.003
Neg logit contributions
 water-0.001
 p-0.001
 cool-0.001
 other-0.001
 sw-0.001
Token!"
Token ID2474
Feature activation-1.05e+00

Pos logit contributions
 water+0.027
 p+0.021
.+0.020
 cool+0.018
 other+0.017
Neg logit contributions
istent-0.097
osity-0.091
urance-0.088
istence-0.086
 Majesty-0.085
Token in
Token ID287
Feature activation+7.79e-01

Pos logit contributions
 water+0.001
 p+0.001
 cool+0.001
 other+0.001
 was+0.001
Neg logit contributions
istent-0.005
osity-0.004
urance-0.004
istence-0.004
 Majesty-0.004
Token your
Token ID534
Feature activation-4.29e-01

Pos logit contributions
 water+0.027
 p+0.020
 cool+0.016
 other+0.016
 pe+0.016
Neg logit contributions
istent-0.111
osity-0.101
urance-0.099
istence-0.095
 Majesty-0.095
Token bag
Token ID6131
Feature activation+2.94e-01

Pos logit contributions
istent+0.047
osity+0.042
urance+0.040
istence+0.039
arsh+0.038
Neg logit contributions
 water-0.028
 p-0.025
 cool-0.023
 other-0.022
 was-0.021
Token?"
Token ID1701
Feature activation+2.66e-01

Pos logit contributions
 water+0.013
 p+0.010
 was+0.010
 cool+0.010
.+0.010
Neg logit contributions
istent-0.036
osity-0.033
urance-0.032
 Majesty-0.032
istence-0.031
Token
Token ID198
Feature activation+2.12e-01

Pos logit contributions
 water+0.009
 p+0.007
 was+0.007
.+0.007
 other+0.006
Neg logit contributions
istent-0.035
osity-0.033
urance-0.032
 Majesty-0.031
 fault-0.031
TokenP
Token ID47
Feature activation+5.07e+00

Pos logit contributions
 water+0.009
 p+0.008
 other+0.007
 cool+0.007
 was+0.007
Neg logit contributions
istent-0.025
osity-0.023
urance-0.023
 fault-0.022
 Majesty-0.022
Tokenolly
Token ID5098
Feature activation-2.88e-01

Pos logit contributions
 water+0.417
 p+0.388
 was+0.378
.+0.375
P+0.374
Neg logit contributions
istent-0.371
osity-0.340
urance-0.332
 Majesty-0.313
istence-0.299
Token smiled
Token ID13541
Feature activation+3.05e-01

Pos logit contributions
istent+0.037
osity+0.034
urance+0.033
 fault+0.033
istence+0.032
Neg logit contributions
 water-0.011
 p-0.009
 was-0.008
 sw-0.008
 cool-0.007
Token proudly
Token ID23017
Feature activation-4.27e-01

Pos logit contributions
 water+0.012
 p+0.009
 other+0.008
 cool+0.008
 sw+0.008
Neg logit contributions
istent-0.038
osity-0.035
urance-0.034
 Majesty-0.033
istence-0.033
Token and
Token ID290
Feature activation+9.19e-02

Pos logit contributions
istent+0.055
osity+0.050
urance+0.050
istence+0.048
 Majesty+0.048
Neg logit contributions
 water-0.015
 p-0.011
 other-0.010
 cool-0.010
 sw-0.009
Token said
Token ID531
Feature activation-1.07e-01

Pos logit contributions
 water+0.002
 p+0.001
 cool+0.001
 other+0.001
 sw+0.001
Neg logit contributions
istent-0.013
osity-0.012
urance-0.012
 Majesty-0.011
istence-0.011
Token join
Token ID4654
Feature activation+2.17e-01

Pos logit contributions
istent+0.160
osity+0.148
urance+0.144
 Majesty+0.140
istence+0.139
Neg logit contributions
 water-0.058
 p-0.046
 other-0.042
 sw-0.041
 cool-0.040
Token him
Token ID683
Feature activation-1.08e-01

Pos logit contributions
 water+0.006
 p+0.004
 cool+0.004
 other+0.004
 sw+0.004
Neg logit contributions
istent-0.028
osity-0.026
urance-0.026
istence-0.025
aries-0.024
Token.
Token ID13
Feature activation+1.74e-02

Pos logit contributions
istent+0.016
osity+0.015
urance+0.015
istence+0.015
 Majesty+0.014
Neg logit contributions
 water-0.002
 p-0.001
.-0.001
 other-0.000
 cool-0.000
Token
Token ID198
Feature activation+1.58e-01

Pos logit contributions
 water+0.001
 p+0.001
.+0.001
 was+0.001
 other+0.001
Neg logit contributions
istent-0.002
osity-0.002
urance-0.002
 fault-0.002
istence-0.002
Token
Token ID198
Feature activation+1.16e-01

Pos logit contributions
 water+0.007
 p+0.005
 cool+0.005
 other+0.005
 sw+0.004
Neg logit contributions
istent-0.019
osity-0.018
urance-0.017
istence-0.017
 Majesty-0.017
TokenP
Token ID47
Feature activation+5.07e+00

Pos logit contributions
 water+0.005
 p+0.004
 cool+0.004
 other+0.004
 sw+0.004
Neg logit contributions
istent-0.014
osity-0.013
urance-0.012
istence-0.012
 Majesty-0.012
Tokenenny
Token ID11870
Feature activation-5.89e-01

Pos logit contributions
 water+0.449
P+0.422
 p+0.404
 was+0.403
.+0.401
Neg logit contributions
istent-0.345
osity-0.315
urance-0.304
ses-0.283
sing-0.281
Token said
Token ID531
Feature activation-2.25e-01

Pos logit contributions
istent+0.079
osity+0.076
urance+0.073
 fault+0.072
istence+0.071
Neg logit contributions
 water-0.018
 was-0.015
 p-0.015
 went-0.013
 decided-0.013
Token,
Token ID11
Feature activation-4.20e-01

Pos logit contributions
istent+0.028
osity+0.025
urance+0.025
aries+0.024
istence+0.024
Neg logit contributions
 water-0.010
 p-0.008
.-0.008
 was-0.008
 in-0.008
Token
Token ID6184
Feature activation+7.94e-01

Pos logit contributions
istent+0.041
 fault+0.037
urance+0.037
osity+0.036
 Majesty+0.036
Neg logit contributions
 water-0.028
.-0.027
 was-0.026
 in-0.026
 p-0.025
Token
Token ID95
Feature activation+1.57e+00

Pos logit contributions
 water+0.069
 p+0.063
 cool+0.062
.+0.061
 sw+0.060
Neg logit contributions
istent-0.058
osity-0.052
 fault-0.052
urance-0.051
aries-0.048
Token.
Token ID13
Feature activation+1.94e-01

Pos logit contributions
istent+0.047
osity+0.044
urance+0.043
 Majesty+0.042
 fault+0.042
Neg logit contributions
 water-0.008
 p-0.004
 cool-0.004
 other-0.004
 sw-0.003
Token She
Token ID1375
Feature activation-1.21e+00

Pos logit contributions
 water+0.009
.+0.009
 p+0.008
 was+0.007
 went+0.007
Neg logit contributions
istent-0.024
urance-0.020
 fault-0.020
 Majesty-0.020
osity-0.020
Token said
Token ID531
Feature activation-1.12e-01

Pos logit contributions
istent+0.133
osity+0.120
 Majesty+0.119
urance+0.118
istence+0.116
Neg logit contributions
 water-0.052
 other-0.041
P-0.038
 away-0.038
 cream-0.038
Token,
Token ID11
Feature activation-4.76e-01

Pos logit contributions
istent+0.015
urance+0.014
osity+0.013
istence+0.013
aries+0.013
Neg logit contributions
 water-0.004
 p-0.003
.-0.003
 other-0.003
 in-0.003
Token "
Token ID366
Feature activation-7.21e-01

Pos logit contributions
istent+0.049
 fault+0.044
urance+0.043
osity+0.043
 Majesty+0.042
Neg logit contributions
 water-0.030
 p-0.028
.-0.027
 was-0.027
 in-0.026
TokenP
Token ID47
Feature activation+5.07e+00

Pos logit contributions
istent+0.081
osity+0.075
urance+0.072
istence+0.070
 Majesty+0.069
Neg logit contributions
 water-0.036
 p-0.030
 cool-0.028
 sw-0.027
 other-0.027
Tokeninky
Token ID29246
Feature activation-1.01e+00

Pos logit contributions
 water+0.400
 p+0.361
.+0.349
 cool+0.346
P+0.341
Neg logit contributions
istent-0.423
urance-0.371
osity-0.369
istence-0.338
sing-0.329
Token,
Token ID11
Feature activation-4.75e-01

Pos logit contributions
istent+0.129
osity+0.117
urance+0.115
istence+0.111
arsh+0.108
Neg logit contributions
 water-0.045
 p-0.036
 was-0.033
.-0.032
 cool-0.032
Token how
Token ID703
Feature activation+5.94e-01

Pos logit contributions
istent+0.053
urance+0.046
osity+0.046
istence+0.043
arsh+0.043
Neg logit contributions
 water-0.031
 p-0.028
 cool-0.026
 other-0.025
 pe-0.025
Token can
Token ID460
Feature activation+2.52e-01

Pos logit contributions
 water+0.031
 cool+0.024
 other+0.024
 p+0.024
 was+0.023
Neg logit contributions
istent-0.069
osity-0.062
urance-0.062
istence-0.060
 Majesty-0.059
Token you
Token ID345
Feature activation-5.45e-01

Pos logit contributions
 water+0.018
 p+0.016
 other+0.015
 cool+0.015
 was+0.015
Neg logit contributions
istent-0.024
osity-0.021
urance-0.021
 fault-0.020
istence-0.020
Token says
Token ID1139
Feature activation-6.66e-01

Pos logit contributions
istent+0.071
osity+0.067
urance+0.064
 Majesty+0.062
istence+0.062
Neg logit contributions
 water-0.029
 p-0.025
.-0.022
 cool-0.022
 other-0.022
Token.
Token ID13
Feature activation+2.41e-01

Pos logit contributions
istent+0.103
osity+0.097
urance+0.095
 Majesty+0.094
istence+0.093
Neg logit contributions
 water-0.007
 p-0.001
.-0.000
 other+0.001
 cool+0.001
Token
Token ID198
Feature activation+2.25e-01

Pos logit contributions
 water+0.010
 p+0.008
 cool+0.007
 other+0.007
 was+0.007
Neg logit contributions
istent-0.030
osity-0.028
urance-0.027
 Majesty-0.026
istence-0.026
Token
Token ID198
Feature activation+1.99e-01

Pos logit contributions
 water+0.011
 p+0.009
 sw+0.008
 cool+0.008
 pe+0.008
Neg logit contributions
istent-0.026
osity-0.023
urance-0.023
istence-0.022
 fault-0.022
Token"
Token ID1
Feature activation+1.21e-01

Pos logit contributions
 water+0.011
 p+0.009
 cool+0.009
 sw+0.008
 pe+0.008
Neg logit contributions
istent-0.020
osity-0.019
urance-0.018
 Majesty-0.018
istence-0.018
TokenP
Token ID47
Feature activation+5.07e+00

Pos logit contributions
 water+0.007
 away+0.006
 p+0.006
 cool+0.006
 sw+0.006
Neg logit contributions
istent-0.011
osity-0.010
istence-0.009
urance-0.009
ses-0.009
Tokenray
Token ID2433
Feature activation+7.78e-01

Pos logit contributions
 water+0.432
.+0.394
 p+0.387
 cool+0.370
 was+0.368
Neg logit contributions
istent-0.384
osity-0.353
urance-0.341
istence-0.307
 Majesty-0.293
Tokening
Token ID278
Feature activation-2.59e+00

Pos logit contributions
 water+0.033
 p+0.026
 was+0.024
.+0.024
 other+0.024
Neg logit contributions
istent-0.096
osity-0.089
urance-0.088
istence-0.084
 Majesty-0.084
Token is
Token ID318
Feature activation-1.27e+00

Pos logit contributions
istent+0.322
osity+0.299
urance+0.293
istence+0.280
 Majesty+0.279
Neg logit contributions
 water-0.115
 p-0.089
 other-0.082
 cool-0.081
.-0.081
Token like
Token ID588
Feature activation+1.53e-01

Pos logit contributions
istent+0.150
osity+0.138
urance+0.135
istence+0.128
 Majesty+0.128
Neg logit contributions
 water-0.065
 p-0.053
 cool-0.052
 other-0.050
.-0.048
Token talking
Token ID3375
Feature activation-8.99e-01

Pos logit contributions
 water+0.007
 p+0.005
 other+0.005
 cool+0.005
.+0.004
Neg logit contributions
istent-0.020
osity-0.018
urance-0.018
istence-0.017
arsh-0.017
Token to
Token ID284
Feature activation+1.40e-01

Pos logit contributions
 water+0.067
 p+0.054
 was+0.053
 other+0.053
 cool+0.051
Neg logit contributions
istent-0.184
osity-0.169
urance-0.166
istence-0.161
 Majesty-0.158
Token do
Token ID466
Feature activation-5.14e-02

Pos logit contributions
 water+0.007
 p+0.005
 cool+0.005
 other+0.005
 sw+0.005
Neg logit contributions
istent-0.016
osity-0.015
urance-0.015
 Majesty-0.014
istence-0.014
Token."
Token ID526
Feature activation-4.12e-01

Pos logit contributions
istent+0.007
osity+0.007
urance+0.006
istence+0.006
 Majesty+0.006
Neg logit contributions
 water-0.001
 p-0.001
 other-0.001
.-0.001
 cool-0.001
Token
Token ID198
Feature activation+9.99e-02

Pos logit contributions
istent+0.051
osity+0.047
urance+0.044
 Majesty+0.044
istence+0.044
Neg logit contributions
 water-0.018
 p-0.016
.-0.015
 was-0.015
 other-0.014
Token
Token ID198
Feature activation+5.22e-02

Pos logit contributions
 water+0.004
 p+0.003
 other+0.003
 cool+0.003
 was+0.002
Neg logit contributions
istent-0.013
osity-0.012
urance-0.012
 Majesty-0.011
istence-0.011
TokenP
Token ID47
Feature activation+5.07e+00

Pos logit contributions
 water+0.002
 p+0.002
 cool+0.002
 other+0.002
 sw+0.001
Neg logit contributions
istent-0.006
osity-0.006
urance-0.006
 Majesty-0.006
istence-0.006
Tokenoppy
Token ID26696
Feature activation-1.84e+00

Pos logit contributions
 water+0.433
 p+0.402
P+0.402
 was+0.396
 other+0.389
Neg logit contributions
istent-0.364
osity-0.338
urance-0.323
istence-0.293
 Majesty-0.287
Token smiled
Token ID13541
Feature activation+1.82e-01

Pos logit contributions
istent+0.251
osity+0.237
urance+0.229
 fault+0.223
istence+0.222
Neg logit contributions
 water-0.054
 p-0.041
 was-0.036
 sw-0.033
 cool-0.032
Token and
Token ID290
Feature activation+3.32e-02

Pos logit contributions
 water+0.007
 p+0.005
 other+0.004
 cool+0.004
 sw+0.004
Neg logit contributions
istent-0.023
osity-0.022
urance-0.021
 Majesty-0.020
istence-0.020
Token said
Token ID531
Feature activation-1.94e-01

Pos logit contributions
 water+0.001
 p+0.001
 other+0.001
 cool+0.001
 sw+0.001
Neg logit contributions
istent-0.004
osity-0.004
urance-0.004
 Majesty-0.004
istence-0.004
Token,
Token ID11
Feature activation-5.26e-01

Pos logit contributions
istent+0.025
osity+0.022
urance+0.022
istence+0.022
aries+0.021
Neg logit contributions
 water-0.007
 p-0.006
.-0.006
 was-0.006
 cool-0.005
Token
Token ID198
Feature activation+2.02e-01

Pos logit contributions
 water+0.011
 p+0.009
 cool+0.009
 other+0.009
 sw+0.009
Neg logit contributions
istent-0.013
osity-0.012
urance-0.011
istence-0.011
 Majesty-0.011
Token
Token ID198
Feature activation+1.93e-01

Pos logit contributions
 water+0.012
 p+0.010
 away+0.009
 cream+0.009
 sw+0.009
Neg logit contributions
istent-0.020
urance-0.018
osity-0.017
arsh-0.017
istence-0.017
TokenThe
Token ID464
Feature activation+8.68e-01

Pos logit contributions
 water+0.011
 pe+0.009
 away+0.009
 p+0.009
 inside+0.008
Neg logit contributions
istent-0.019
istence-0.016
osity-0.016
urance-0.016
arsh-0.015
Token snake
Token ID17522
Feature activation-2.93e-01

Pos logit contributions
 water+0.062
 decided+0.058
P+0.056
 away+0.056
 p+0.056
Neg logit contributions
istent-0.063
osity-0.059
urance-0.059
 Majesty-0.058
ses-0.056
Token his
Token ID465
Feature activation+9.32e-01

Pos logit contributions
istent+0.031
osity+0.028
urance+0.027
istence+0.026
 Majesty+0.026
Neg logit contributions
 water-0.018
 p-0.016
 other-0.015
 was-0.014
 sw-0.014
Tokenses
Token ID8448
Feature activation-7.86e+00

Pos logit contributions
 water+0.094
 p+0.085
 cool+0.083
 other+0.082
 sw+0.081
Neg logit contributions
istent-0.064
osity-0.054
urance-0.050
istence-0.048
aries-0.046
Token.
Token ID13
Feature activation+1.42e-01

Pos logit contributions
istent+0.963
osity+0.867
urance+0.864
istence+0.829
 fault+0.824
Neg logit contributions
 water-0.293
 p-0.216
 cool-0.202
 other-0.201
 cream-0.189
Token L
Token ID406
Feature activation+7.54e-01

Pos logit contributions
 water+0.011
 p+0.009
 cool+0.009
 other+0.009
 was+0.009
Neg logit contributions
istent-0.013
osity-0.012
urance-0.011
 Majesty-0.011
 fault-0.011
Tokenila
Token ID10102
Feature activation+1.82e+00

Pos logit contributions
 water+0.043
 p+0.036
 cool+0.034
 other+0.034
 sw+0.033
Neg logit contributions
istent-0.081
osity-0.073
urance-0.071
 fault-0.068
 Majesty-0.068
Token and
Token ID290
Feature activation+4.23e-02

Pos logit contributions
 water+0.050
 p+0.040
 was+0.033
 pe+0.029
.+0.029
Neg logit contributions
istent-0.259
osity-0.252
urance-0.242
istence-0.234
 Majesty-0.232
Token Tom
Token ID4186
Feature activation-3.05e-01

Pos logit contributions
 water+0.003
 p+0.002
 other+0.002
 cool+0.002
 pe+0.002
Neg logit contributions
istent-0.005
osity-0.004
urance-0.004
 Majesty-0.004
aries-0.004
Token claws
Token ID28421
Feature activation-1.31e+00

Pos logit contributions
istent+0.001
osity+0.001
urance+0.001
istence+0.001
arsh+0.001
Neg logit contributions
 water-0.001
 p-0.001
 was-0.001
 pe-0.001
 other-0.001
Token and
Token ID290
Feature activation+9.99e-02

Pos logit contributions
istent+0.161
osity+0.149
urance+0.146
 Majesty+0.143
istence+0.140
Neg logit contributions
 water-0.056
 p-0.044
 cool-0.041
 was-0.040
 other-0.040
Token bites
Token ID26081
Feature activation-9.22e-01

Pos logit contributions
 water+0.006
 p+0.005
 other+0.005
 cool+0.005
 sw+0.005
Neg logit contributions
istent-0.011
osity-0.010
urance-0.009
istence-0.009
 Majesty-0.009
Token and
Token ID290
Feature activation+1.01e-01

Pos logit contributions
istent+0.089
osity+0.080
urance+0.078
 fault+0.076
arsh+0.073
Neg logit contributions
P-0.043
 water-0.043
 cool-0.037
 sw-0.036
 cream-0.036
Token his
Token ID465
Feature activation+1.06e+00

Pos logit contributions
 water+0.006
 p+0.005
 cool+0.005
 other+0.004
 sw+0.004
Neg logit contributions
istent-0.011
osity-0.010
urance-0.010
 Majesty-0.009
istence-0.009
Tokenses
Token ID8448
Feature activation-7.82e+00

Pos logit contributions
 water+0.089
 p+0.079
 cool+0.076
 other+0.076
 sw+0.074
Neg logit contributions
istent-0.087
osity-0.077
urance-0.074
istence-0.070
 Majesty-0.069
Token at
Token ID379
Feature activation-3.19e-01

Pos logit contributions
istent+1.026
osity+0.933
urance+0.927
istence+0.893
 fault+0.885
Neg logit contributions
 water-0.232
 p-0.153
 other-0.137
 cool-0.136
P-0.127
Token the
Token ID262
Feature activation-9.84e-02

Pos logit contributions
istent+0.033
urance+0.030
osity+0.030
 fault+0.028
istence+0.028
Neg logit contributions
 water-0.016
 p-0.014
P-0.013
 sw-0.013
 cool-0.013
Token bars
Token ID9210
Feature activation-3.58e-01

Pos logit contributions
istent+0.011
osity+0.010
urance+0.009
istence+0.009
 Majesty+0.009
Neg logit contributions
 water-0.006
 p-0.005
 other-0.005
 cool-0.005
 sw-0.004
Token.
Token ID13
Feature activation+1.42e-01

Pos logit contributions
istent+0.054
osity+0.050
urance+0.049
 Majesty+0.048
istence+0.048
Neg logit contributions
 water-0.005
 p-0.002
 other-0.001
 cool-0.001
 sw-0.000
Token He
Token ID679
Feature activation-2.21e-02

Pos logit contributions
 water+0.010
 p+0.009
 cool+0.008
 other+0.008
 was+0.008
Neg logit contributions
istent-0.014
osity-0.012
urance-0.012
 Majesty-0.011
istence-0.011
Token scare
Token ID19437
Feature activation+5.81e-01

Pos logit contributions
 water+0.012
 p+0.010
P+0.010
 other+0.010
 sw+0.010
Neg logit contributions
istent-0.021
urance-0.018
osity-0.018
istence-0.017
 Majesty-0.017
Token it
Token ID340
Feature activation+1.15e+00

Pos logit contributions
 water+0.027
 p+0.023
 cool+0.022
 sw+0.020
 was+0.020
Neg logit contributions
istent-0.065
osity-0.059
urance-0.059
 Majesty-0.056
 fault-0.056
Token.
Token ID13
Feature activation+1.50e-01

Pos logit contributions
 water+0.033
 p+0.022
 cool+0.019
 other+0.019
 sw+0.017
Neg logit contributions
istent-0.157
osity-0.145
urance-0.143
 Majesty-0.138
istence-0.138
Token It
Token ID632
Feature activation-1.14e-01

Pos logit contributions
 water+0.010
 p+0.009
 other+0.008
.+0.008
 cool+0.008
Neg logit contributions
istent-0.016
osity-0.015
urance-0.014
aries-0.014
istence-0.013
Token his
Token ID465
Feature activation+9.83e-01

Pos logit contributions
istent+0.010
osity+0.009
urance+0.009
 Majesty+0.009
istence+0.009
Neg logit contributions
 water-0.008
 p-0.007
 other-0.007
 cool-0.007
 sw-0.006
Tokenses
Token ID8448
Feature activation-7.80e+00

Pos logit contributions
 water+0.081
 p+0.071
 other+0.070
 cool+0.069
 sw+0.067
Neg logit contributions
istent-0.087
osity-0.077
urance-0.072
istence-0.071
arsh-0.069
Token and
Token ID290
Feature activation+9.19e-02

Pos logit contributions
istent+0.992
osity+0.914
urance+0.897
istence+0.866
 Majesty+0.864
Neg logit contributions
 water-0.283
 p-0.211
 cool-0.191
 other-0.189
 sw-0.178
Token shows
Token ID2523
Feature activation-3.28e-01

Pos logit contributions
 water+0.006
 p+0.005
 cool+0.005
 sw+0.005
 pe+0.005
Neg logit contributions
istent-0.010
osity-0.009
urance-0.008
 fault-0.008
 Majesty-0.008
Token its
Token ID663
Feature activation+5.17e-02

Pos logit contributions
istent+0.041
osity+0.037
urance+0.036
istence+0.035
 Majesty+0.035
Neg logit contributions
 water-0.015
 p-0.011
 other-0.011
 cool-0.011
 sw-0.010
Token teeth
Token ID9941
Feature activation-1.08e+00

Pos logit contributions
 water+0.003
 p+0.003
 cool+0.003
 other+0.003
 sw+0.003
Neg logit contributions
istent-0.005
osity-0.005
urance-0.004
istence-0.004
 Majesty-0.004
Token.
Token ID13
Feature activation+1.44e-01

Pos logit contributions
istent+0.149
osity+0.138
urance+0.135
istence+0.131
 Majesty+0.131
Neg logit contributions
 water-0.028
 p-0.018
 cool-0.015
 other-0.015
 sw-0.014
Token nose
Token ID9686
Feature activation-1.36e+00

Pos logit contributions
istent+0.039
urance+0.035
osity+0.034
 Majesty+0.032
 fault+0.032
Neg logit contributions
 water-0.034
 p-0.030
 decided-0.029
 sw-0.029
 other-0.029
Token.
Token ID13
Feature activation+1.90e-01

Pos logit contributions
istent+0.181
osity+0.164
urance+0.163
 fault+0.158
istence+0.155
Neg logit contributions
 water-0.033
P-0.021
 p-0.020
 sw-0.018
 other-0.018
Token The
Token ID383
Feature activation-3.93e-01

Pos logit contributions
 water+0.010
 p+0.008
 cool+0.008
.+0.008
 was+0.008
Neg logit contributions
istent-0.023
osity-0.020
urance-0.020
 Majesty-0.019
aries-0.019
Token cat
Token ID3797
Feature activation-1.19e+00

Pos logit contributions
istent+0.036
osity+0.032
urance+0.032
 fault+0.030
 Majesty+0.030
Neg logit contributions
 water-0.027
 p-0.023
 cool-0.022
 sw-0.022
 pe-0.022
Token his
Token ID465
Feature activation+9.43e-01

Pos logit contributions
istent+0.135
osity+0.123
urance+0.120
istence+0.115
 Majesty+0.114
Neg logit contributions
 water-0.065
 p-0.055
 cool-0.050
 other-0.050
 was-0.049
Tokenses
Token ID8448
Feature activation-7.79e+00

Pos logit contributions
 water+0.084
 p+0.074
 cool+0.074
 other+0.073
.+0.070
Neg logit contributions
istent-0.077
osity-0.070
istence-0.063
urance-0.063
aries-0.062
Token and
Token ID290
Feature activation-7.23e-03

Pos logit contributions
istent+0.929
osity+0.842
urance+0.832
istence+0.804
 fault+0.795
Neg logit contributions
 water-0.311
 p-0.228
 other-0.221
 cool-0.217
P-0.205
Token scratches
Token ID37627
Feature activation-4.02e-01

Pos logit contributions
istent+0.001
osity+0.001
urance+0.001
 fault+0.001
istence+0.001
Neg logit contributions
 water-0.000
 p-0.000
 cool-0.000
 sw-0.000
 other-0.000
Token his
Token ID465
Feature activation+9.39e-01

Pos logit contributions
istent+0.045
osity+0.040
urance+0.040
istence+0.038
 fault+0.038
Neg logit contributions
 water-0.019
 p-0.016
 cool-0.015
 sw-0.014
 pe-0.014
Token face
Token ID1986
Feature activation+6.46e-01

Pos logit contributions
 water+0.077
 p+0.069
 cool+0.066
 other+0.066
 sw+0.065
Neg logit contributions
istent-0.078
osity-0.069
urance-0.066
istence-0.063
 Majesty-0.063
Token.
Token ID13
Feature activation+1.73e-01

Pos logit contributions
 water+0.014
 p+0.007
 cool+0.006
 other+0.006
 sw+0.006
Neg logit contributions
istent-0.090
osity-0.083
urance-0.082
 fault-0.079
istence-0.079
Token strangers
Token ID18981
Feature activation-3.51e-01

Pos logit contributions
 water+0.009
 other+0.007
 p+0.007
 cool+0.006
.+0.006
Neg logit contributions
istent-0.028
osity-0.025
urance-0.024
istence-0.024
 Majesty-0.023
Token.
Token ID13
Feature activation+2.25e-01

Pos logit contributions
istent+0.050
osity+0.047
urance+0.046
 fault+0.045
istence+0.044
Neg logit contributions
 water-0.007
 p-0.003
 cool-0.002
 other-0.002
 sw-0.002
Token The
Token ID383
Feature activation-3.09e-01

Pos logit contributions
 water+0.016
 p+0.014
 cool+0.014
 other+0.014
.+0.014
Neg logit contributions
istent-0.021
osity-0.020
urance-0.018
 Majesty-0.018
aries-0.018
Token cat
Token ID3797
Feature activation-1.19e+00

Pos logit contributions
istent+0.031
osity+0.028
urance+0.027
istence+0.026
 Majesty+0.026
Neg logit contributions
 water-0.021
 p-0.018
 other-0.017
 cool-0.017
 sw-0.016
Token his
Token ID465
Feature activation+1.09e+00

Pos logit contributions
istent+0.133
osity+0.122
urance+0.119
istence+0.114
 Majesty+0.111
Neg logit contributions
 water-0.068
 p-0.060
 was-0.054
 cool-0.054
 other-0.054
Tokenses
Token ID8448
Feature activation-7.78e+00

Pos logit contributions
 water+0.124
 p+0.112
 cool+0.111
 other+0.110
 sw+0.110
Neg logit contributions
istent-0.063
osity-0.053
urance-0.046
istence-0.046
aries-0.043
Token at
Token ID379
Feature activation-2.82e-01

Pos logit contributions
istent+0.916
osity+0.826
urance+0.817
 fault+0.784
istence+0.784
Neg logit contributions
 water-0.317
 p-0.235
 other-0.223
 cool-0.220
P-0.217
Token Tom
Token ID4186
Feature activation-2.90e-01

Pos logit contributions
istent+0.024
urance+0.022
osity+0.021
isdom+0.020
istence+0.020
Neg logit contributions
 water-0.019
 p-0.016
P-0.016
 cool-0.016
 sw-0.015
Token and
Token ID290
Feature activation+1.07e-01

Pos logit contributions
istent+0.045
osity+0.042
urance+0.041
 Majesty+0.041
istence+0.040
Neg logit contributions
 water-0.004
.-0.002
 p-0.002
 away-0.001
 other-0.001
Token Sue
Token ID26089
Feature activation+7.82e-01

Pos logit contributions
 water+0.006
 p+0.005
 cool+0.005
 sw+0.005
 other+0.005
Neg logit contributions
istent-0.012
osity-0.011
urance-0.011
 fault-0.010
istence-0.010
Token.
Token ID13
Feature activation+2.08e-01

Pos logit contributions
 water+0.016
 p+0.009
 cool+0.007
 other+0.007
 sw+0.006
Neg logit contributions
istent-0.113
osity-0.106
urance-0.104
istence-0.101
 Majesty-0.101
Token angry
Token ID7954
Feature activation+6.70e-01

Pos logit contributions
istent+0.066
osity+0.060
urance+0.058
istence+0.057
 fault+0.056
Neg logit contributions
 water-0.027
 p-0.022
 other-0.021
 cool-0.020
 was-0.020
Token snake
Token ID17522
Feature activation-2.76e-01

Pos logit contributions
 water+0.034
 p+0.028
 cool+0.027
 other+0.027
 sw+0.025
Neg logit contributions
istent-0.075
osity-0.068
urance-0.067
 Majesty-0.065
istence-0.064
Token.
Token ID13
Feature activation+1.73e-01

Pos logit contributions
istent+0.037
osity+0.034
urance+0.034
 Majesty+0.033
istence+0.033
Neg logit contributions
 water-0.008
 p-0.005
 cool-0.005
 other-0.005
 sw-0.004
Token It
Token ID632
Feature activation-8.00e-02

Pos logit contributions
 water+0.012
 p+0.011
 cool+0.010
 other+0.010
 was+0.010
Neg logit contributions
istent-0.016
osity-0.015
urance-0.014
 Majesty-0.014
 fault-0.014
Token his
Token ID465
Feature activation+9.29e-01

Pos logit contributions
istent+0.007
osity+0.006
 Majesty+0.006
ses+0.006
urance+0.006
Neg logit contributions
 water-0.006
P-0.005
 other-0.005
 cream-0.005
S-0.005
Tokenses
Token ID8448
Feature activation-7.78e+00

Pos logit contributions
 water+0.086
 p+0.074
 sw+0.073
 other+0.073
 cool+0.073
Neg logit contributions
istent-0.075
osity-0.067
urance-0.062
istence-0.061
aries-0.059
Token and
Token ID290
Feature activation+4.80e-02

Pos logit contributions
istent+0.914
osity+0.832
urance+0.818
istence+0.790
 fault+0.783
Neg logit contributions
 water-0.322
 p-0.244
 other-0.237
 cool-0.232
 cream-0.219
Token snaps
Token ID23429
Feature activation-5.07e-01

Pos logit contributions
 water+0.003
 p+0.003
 cool+0.003
 sw+0.003
 other+0.003
Neg logit contributions
istent-0.005
osity-0.004
urance-0.004
 fault-0.004
 Majesty-0.004
Token at
Token ID379
Feature activation-3.28e-01

Pos logit contributions
istent+0.057
osity+0.052
urance+0.051
 fault+0.050
istence+0.049
Neg logit contributions
 water-0.024
 p-0.020
 cool-0.019
 other-0.019
P-0.018
Token Ben
Token ID3932
Feature activation-5.10e-01

Pos logit contributions
istent+0.032
osity+0.029
urance+0.028
 Majesty+0.027
istence+0.027
Neg logit contributions
 water-0.021
 p-0.018
 cool-0.018
 other-0.017
 sw-0.017
Token.
Token ID13
Feature activation+1.60e-01

Pos logit contributions
istent+0.080
osity+0.077
 Majesty+0.074
urance+0.074
istence+0.074
Neg logit contributions
 water-0.005
.-0.004
 p-0.001
 away-0.001
 in-0.001
Token a
Token ID257
Feature activation-8.83e-02

Pos logit contributions
 water+0.008
 p+0.007
 other+0.007
 cool+0.006
.+0.006
Neg logit contributions
istent-0.019
osity-0.018
urance-0.017
istence-0.017
 Majesty-0.017
Token cat
Token ID3797
Feature activation-1.19e+00

Pos logit contributions
istent+0.009
osity+0.008
urance+0.008
 Majesty+0.008
 fault+0.008
Neg logit contributions
 water-0.005
 p-0.004
 cool-0.004
 other-0.004
 sw-0.004
Token.
Token ID13
Feature activation+1.51e-01

Pos logit contributions
istent+0.166
osity+0.155
urance+0.152
 Majesty+0.147
istence+0.147
Neg logit contributions
 water-0.030
 p-0.020
 cool-0.016
 other-0.016
 sw-0.015
Token She
Token ID1375
Feature activation-1.19e+00

Pos logit contributions
 water+0.011
 p+0.009
 other+0.009
 cool+0.009
 was+0.009
Neg logit contributions
istent-0.015
osity-0.013
urance-0.013
istence-0.012
 Majesty-0.012
Token his
Token ID465
Feature activation+1.06e+00

Pos logit contributions
istent+0.123
osity+0.113
urance+0.110
istence+0.102
arsh+0.102
Neg logit contributions
 water-0.079
 p-0.072
 sw-0.065
 pe-0.065
 was-0.064
Tokenses
Token ID8448
Feature activation-7.77e+00

Pos logit contributions
 water+0.102
 other+0.092
 p+0.091
 cool+0.090
 big+0.086
Neg logit contributions
istent-0.090
osity-0.079
istence-0.073
aries-0.069
urance-0.068
Token and
Token ID290
Feature activation+8.09e-02

Pos logit contributions
istent+0.940
osity+0.861
urance+0.844
istence+0.814
 Majesty+0.811
Neg logit contributions
 water-0.322
 p-0.245
 other-0.229
 cool-0.227
 sw-0.212
Token scratches
Token ID37627
Feature activation-4.27e-01

Pos logit contributions
 water+0.005
 p+0.005
 cool+0.004
 sw+0.004
 pe+0.004
Neg logit contributions
istent-0.008
osity-0.008
urance-0.007
 fault-0.007
aries-0.007
Token at
Token ID379
Feature activation-2.93e-01

Pos logit contributions
istent+0.048
urance+0.043
osity+0.043
istence+0.040
arsh+0.040
Neg logit contributions
 water-0.020
 p-0.016
 cool-0.016
 sw-0.015
 cream-0.014
Token the
Token ID262
Feature activation-9.42e-02

Pos logit contributions
istent+0.035
osity+0.032
urance+0.031
istence+0.030
 Majesty+0.030
Neg logit contributions
 water-0.014
 p-0.011
 other-0.011
 cool-0.010
 sw-0.010
Token dog
Token ID3290
Feature activation-8.13e-01

Pos logit contributions
istent+0.010
osity+0.009
urance+0.009
 Majesty+0.008
 fault+0.008
Neg logit contributions
 water-0.006
 p-0.005
 cool-0.005
 other-0.004
 sw-0.004
Token and
Token ID290
Feature activation+4.94e-02

Pos logit contributions
 water+0.053
P+0.047
 p+0.044
 sw+0.043
 cream+0.043
Neg logit contributions
istent-0.135
osity-0.122
urance-0.119
 fault-0.116
istence-0.113
Token angry
Token ID7954
Feature activation+7.32e-01

Pos logit contributions
 water+0.003
 p+0.002
 cool+0.002
 other+0.002
 sw+0.002
Neg logit contributions
istent-0.005
osity-0.005
urance-0.005
 Majesty-0.004
istence-0.004
Token.
Token ID13
Feature activation+2.22e-01

Pos logit contributions
 water+0.016
 p+0.010
 cool+0.009
P+0.008
 other+0.008
Neg logit contributions
istent-0.100
osity-0.093
urance-0.092
 fault-0.089
 Majesty-0.089
Token It
Token ID632
Feature activation-2.01e-02

Pos logit contributions
 water+0.018
 p+0.016
 cool+0.015
 other+0.015
 sw+0.015
Neg logit contributions
istent-0.019
osity-0.017
urance-0.016
 Majesty-0.016
istence-0.015
Token his
Token ID465
Feature activation+1.01e+00

Pos logit contributions
istent+0.002
 Majesty+0.001
ses+0.001
osity+0.001
 fault+0.001
Neg logit contributions
 water-0.001
P-0.001
B-0.001
 cream-0.001
 other-0.001
Tokenses
Token ID8448
Feature activation-7.77e+00

Pos logit contributions
 water+0.108
 p+0.097
 cool+0.095
 other+0.095
 sw+0.094
Neg logit contributions
istent-0.067
osity-0.057
urance-0.052
istence-0.050
aries-0.048
Token and
Token ID290
Feature activation+3.45e-02

Pos logit contributions
istent+0.911
osity+0.829
urance+0.816
istence+0.789
 fault+0.785
Neg logit contributions
 water-0.317
 p-0.238
 other-0.227
 cool-0.225
P-0.217
Token fl
Token ID781
Feature activation-1.36e+00

Pos logit contributions
 water+0.002
 p+0.002
 cool+0.002
 sw+0.002
 other+0.002
Neg logit contributions
istent-0.003
osity-0.003
urance-0.003
 fault-0.003
istence-0.003
Tokenaps
Token ID1686
Feature activation-2.69e+00

Pos logit contributions
istent+0.101
urance+0.088
osity+0.084
 Majesty+0.082
istence+0.080
Neg logit contributions
 water-0.121
 p-0.108
 sw-0.105
 cool-0.105
.-0.105
Token its
Token ID663
Feature activation+5.26e-02

Pos logit contributions
istent+0.290
osity+0.264
urance+0.258
 fault+0.251
istence+0.248
Neg logit contributions
 water-0.139
 p-0.118
 cool-0.108
 other-0.106
 pe-0.105
Token wings
Token ID12098
Feature activation-1.77e+00

Pos logit contributions
 water+0.005
 p+0.004
 decided+0.004
 cool+0.004
 other+0.004
Neg logit contributions
istent-0.004
osity-0.003
urance-0.003
 fault-0.003
ses-0.003
Token like
Token ID588
Feature activation+4.84e-02

Pos logit contributions
istent+0.110
osity+0.099
urance+0.097
 fault+0.093
istence+0.093
Neg logit contributions
 water-0.057
 p-0.048
 other-0.045
 cool-0.044
 was-0.043
Token that
Token ID326
Feature activation-3.61e-01

Pos logit contributions
 water+0.002
 p+0.002
 other+0.001
 cool+0.001
 sw+0.001
Neg logit contributions
istent-0.006
osity-0.006
urance-0.006
istence-0.005
 Majesty-0.005
Token.
Token ID13
Feature activation-1.43e-02

Pos logit contributions
istent+0.049
osity+0.046
urance+0.045
istence+0.043
 Majesty+0.043
Neg logit contributions
 water-0.010
 p-0.006
 cool-0.005
 other-0.005
 sw-0.005
Token It
Token ID632
Feature activation-1.62e-01

Pos logit contributions
istent+0.001
osity+0.001
urance+0.001
 Majesty+0.001
aries+0.001
Neg logit contributions
 water-0.001
 p-0.001
.-0.001
 cool-0.001
 was-0.001
Token his
Token ID465
Feature activation+1.06e+00

Pos logit contributions
istent+0.017
osity+0.015
urance+0.015
 fault+0.014
 Majesty+0.014
Neg logit contributions
 water-0.009
 p-0.007
 cool-0.007
 other-0.007
 cream-0.007
Tokenses
Token ID8448
Feature activation-7.76e+00

Pos logit contributions
 water+0.079
 p+0.069
 cool+0.067
 other+0.067
 sw+0.066
Neg logit contributions
istent-0.097
osity-0.086
urance-0.083
istence-0.080
 Majesty-0.078
Token and
Token ID290
Feature activation-1.03e-01

Pos logit contributions
istent+1.013
osity+0.937
urance+0.920
 Majesty+0.890
istence+0.888
Neg logit contributions
 water-0.266
 p-0.197
 cool-0.174
 other-0.173
 sw-0.165
Token fl
Token ID781
Feature activation-1.45e+00

Pos logit contributions
istent+0.011
osity+0.010
urance+0.010
istence+0.009
 Majesty+0.009
Neg logit contributions
 water-0.006
 p-0.005
 cool-0.005
 other-0.005
 sw-0.005
Tokenaps
Token ID1686
Feature activation-2.68e+00

Pos logit contributions
istent+0.099
urance+0.087
osity+0.083
 Majesty+0.078
istence+0.078
Neg logit contributions
 water-0.136
 p-0.122
 sw-0.121
 cool-0.120
.-0.118
Token its
Token ID663
Feature activation-7.59e-02

Pos logit contributions
istent+0.304
osity+0.277
urance+0.271
 fault+0.263
istence+0.261
Neg logit contributions
 water-0.126
 p-0.104
 cool-0.094
 other-0.092
 pe-0.091
Token wings
Token ID12098
Feature activation-1.78e+00

Pos logit contributions
istent+0.006
osity+0.005
urance+0.005
 Majesty+0.005
 fault+0.004
Neg logit contributions
 water-0.007
 p-0.006
 cool-0.006
 other-0.006
 sw-0.006
Tokenked
Token ID9091
Feature activation-9.87e-01

Pos logit contributions
istent+0.266
osity+0.247
urance+0.233
istence+0.233
 fault+0.230
Neg logit contributions
 water-0.083
 p-0.061
 other-0.061
 cool-0.054
.-0.049
Token tongue
Token ID11880
Feature activation-2.42e+00

Pos logit contributions
istent+0.099
osity+0.089
urance+0.086
istence+0.083
 Majesty+0.082
Neg logit contributions
 water-0.066
 p-0.056
 other-0.053
 cool-0.053
 sw-0.052
Token.
Token ID13
Feature activation+1.81e-01

Pos logit contributions
istent+0.346
osity+0.322
urance+0.317
 fault+0.307
istence+0.306
Neg logit contributions
 water-0.044
 p-0.023
 cool-0.018
 other-0.017
 sw-0.014
Token It
Token ID632
Feature activation-9.18e-02

Pos logit contributions
 water+0.013
 p+0.011
 other+0.010
 was+0.010
 cool+0.010
Neg logit contributions
istent-0.018
osity-0.017
urance-0.016
istence-0.016
aries-0.015
Token his
Token ID465
Feature activation+1.04e+00

Pos logit contributions
istent+0.009
osity+0.008
urance+0.008
 Majesty+0.008
istence+0.008
Neg logit contributions
 water-0.006
 p-0.005
 other-0.005
 cool-0.005
 sw-0.004
Tokenses
Token ID8448
Feature activation-7.76e+00

Pos logit contributions
 water+0.123
 p+0.112
 cool+0.110
 sw+0.109
 other+0.108
Neg logit contributions
istent-0.057
osity-0.048
urance-0.042
istence-0.041
aries-0.040
Token and
Token ID290
Feature activation+7.91e-02

Pos logit contributions
istent+0.950
osity+0.868
urance+0.855
istence+0.825
 fault+0.816
Neg logit contributions
 water-0.299
 p-0.223
 other-0.212
 cool-0.207
 sw-0.192
Token swim
Token ID9422
Feature activation+1.62e+00

Pos logit contributions
 water+0.005
 p+0.004
 cool+0.004
 sw+0.004
 pe+0.004
Neg logit contributions
istent-0.009
osity-0.008
urance-0.008
 fault-0.007
aries-0.007
Tokens
Token ID82
Feature activation-4.61e-01

Pos logit contributions
 water+0.068
P+0.056
 other+0.055
 p+0.055
 cool+0.051
Neg logit contributions
istent-0.176
osity-0.163
urance-0.155
 fault-0.154
ses-0.154
Token near
Token ID1474
Feature activation-3.07e-02

Pos logit contributions
istent+0.057
osity+0.052
urance+0.051
 fault+0.050
istence+0.049
Neg logit contributions
 water-0.018
 p-0.014
 cool-0.013
 other-0.013
 sw-0.012
Token the
Token ID262
Feature activation-1.05e-01

Pos logit contributions
istent+0.004
osity+0.004
urance+0.004
istence+0.004
 Majesty+0.004
Neg logit contributions
 water-0.001
 p-0.001
 other-0.001
.-0.000
 cool-0.000
Token is
Token ID318
Feature activation-1.27e+00

Pos logit contributions
istent+0.113
osity+0.101
urance+0.099
istence+0.094
 Majesty+0.093
Neg logit contributions
 water-0.078
 p-0.068
 cool-0.064
 other-0.063
 sw-0.062
Token afraid
Token ID7787
Feature activation+2.01e-01

Pos logit contributions
istent+0.142
osity+0.130
urance+0.127
istence+0.122
 Majesty+0.122
Neg logit contributions
 water-0.068
 p-0.056
 cool-0.053
 other-0.053
 sw-0.051
Token.
Token ID13
Feature activation+2.72e-01

Pos logit contributions
 water+0.006
 p+0.004
P+0.004
 cool+0.003
 sw+0.003
Neg logit contributions
istent-0.026
osity-0.024
urance-0.024
 fault-0.023
istence-0.023
Token It
Token ID632
Feature activation-2.83e-02

Pos logit contributions
 water+0.017
 p+0.015
 cool+0.015
.+0.015
 was+0.014
Neg logit contributions
istent-0.029
osity-0.027
aries-0.026
 Majesty-0.025
urance-0.025
Token his
Token ID465
Feature activation+9.98e-01

Pos logit contributions
istent+0.002
osity+0.002
urance+0.002
 Majesty+0.002
 fault+0.002
Neg logit contributions
 water-0.002
 p-0.002
 other-0.002
 cool-0.002
P-0.002
Tokenses
Token ID8448
Feature activation-7.73e+00

Pos logit contributions
 water+0.115
 p+0.107
 other+0.105
 cool+0.104
.+0.102
Neg logit contributions
istent-0.058
osity-0.049
istence-0.041
urance-0.041
aries-0.039
Token and
Token ID290
Feature activation+3.83e-02

Pos logit contributions
istent+0.940
osity+0.862
urance+0.846
istence+0.818
 fault+0.816
Neg logit contributions
 water-0.300
 p-0.226
 cool-0.209
 other-0.207
 sw-0.190
Token scratches
Token ID37627
Feature activation-4.23e-01

Pos logit contributions
 water+0.002
 p+0.002
 cool+0.002
 sw+0.002
 pe+0.002
Neg logit contributions
istent-0.004
osity-0.004
urance-0.004
 fault-0.004
arsh-0.003
Token Tom
Token ID4186
Feature activation-3.44e-01

Pos logit contributions
istent+0.049
urance+0.045
osity+0.044
 fault+0.042
istence+0.042
Neg logit contributions
 water-0.016
 p-0.013
 cool-0.013
 sw-0.012
 pe-0.012
Token's
Token ID338
Feature activation-2.37e+00

Pos logit contributions
istent+0.044
osity+0.042
urance+0.040
 Majesty+0.040
istence+0.039
Neg logit contributions
 water-0.013
 p-0.010
.-0.010
 away-0.010
 other-0.009
Token hand
Token ID1021
Feature activation-1.34e+00

Pos logit contributions
istent+0.221
osity+0.196
urance+0.188
istence+0.182
 Majesty+0.178
Neg logit contributions
 water-0.176
 p-0.155
 other-0.148
 cool-0.147
 sw-0.143
Token snake
Token ID17522
Feature activation-2.49e-01

Pos logit contributions
istent+0.030
osity+0.027
urance+0.026
 Majesty+0.025
 fault+0.025
Neg logit contributions
 water-0.027
 p-0.024
 cool-0.023
 decided-0.023
 sw-0.023
Token sees
Token ID7224
Feature activation-9.62e-01

Pos logit contributions
istent+0.025
osity+0.023
urance+0.022
 Majesty+0.021
istence+0.021
Neg logit contributions
 water-0.016
 p-0.013
 cool-0.013
 other-0.013
 sw-0.012
Token Tom
Token ID4186
Feature activation-3.44e-01

Pos logit contributions
istent+0.097
osity+0.090
urance+0.088
 fault+0.085
 Majesty+0.084
Neg logit contributions
 water-0.051
 p-0.043
 cool-0.041
 sw-0.041
P-0.040
Token and
Token ID290
Feature activation+3.71e-02

Pos logit contributions
istent+0.046
osity+0.043
urance+0.042
 Majesty+0.041
istence+0.041
Neg logit contributions
 water-0.011
 p-0.008
 cool-0.007
 other-0.006
.-0.006
Token his
Token ID465
Feature activation+9.36e-01

Pos logit contributions
 water+0.002
 p+0.001
 cool+0.001
 other+0.001
 sw+0.001
Neg logit contributions
istent-0.004
osity-0.004
urance-0.004
 Majesty-0.004
istence-0.004
Tokenses
Token ID8448
Feature activation-7.72e+00

Pos logit contributions
 water+0.083
 p+0.074
 cool+0.071
 other+0.071
.+0.070
Neg logit contributions
istent-0.078
osity-0.069
istence-0.064
urance-0.064
aries-0.063
Token.
Token ID13
Feature activation+1.99e-01

Pos logit contributions
istent+0.956
urance+0.863
osity+0.861
 fault+0.839
arsh+0.826
Neg logit contributions
 water-0.231
P-0.163
 cream-0.146
 p-0.146
 cool-0.144
Token It
Token ID632
Feature activation-8.15e-03

Pos logit contributions
 water+0.015
 p+0.013
 cool+0.012
 other+0.012
 was+0.012
Neg logit contributions
istent-0.018
osity-0.016
urance-0.016
 Majesty-0.015
istence-0.015
Token opens
Token ID9808
Feature activation-5.83e-01

Pos logit contributions
istent+0.001
osity+0.001
ses+0.001
 fault+0.001
urance+0.001
Neg logit contributions
 water-0.001
P-0.000
 other-0.000
 cool-0.000
 p-0.000
Token its
Token ID663
Feature activation+3.85e-02

Pos logit contributions
istent+0.059
osity+0.053
urance+0.052
 fault+0.051
 Majesty+0.050
Neg logit contributions
 water-0.033
 other-0.027
 p-0.027
 cool-0.026
P-0.026
Token mouth
Token ID5422
Feature activation-1.49e+00

Pos logit contributions
 water+0.004
 p+0.003
 cool+0.003
 other+0.003
 sw+0.003
Neg logit contributions
istent-0.003
osity-0.002
urance-0.002
istence-0.002
 Majesty-0.002
Token is
Token ID318
Feature activation-1.22e+00

Pos logit contributions
 water+0.028
 p+0.021
 was+0.020
 other+0.020
.+0.019
Neg logit contributions
istent-0.094
osity-0.088
urance-0.086
 Majesty-0.084
istence-0.083
Token mean
Token ID1612
Feature activation+4.59e-01

Pos logit contributions
istent+0.127
osity+0.116
urance+0.114
 fault+0.111
 Majesty+0.110
Neg logit contributions
 water-0.065
 p-0.055
 sw-0.052
 was-0.051
 other-0.050
Token.
Token ID13
Feature activation+2.69e-01

Pos logit contributions
 water+0.014
 p+0.010
 cool+0.009
 other+0.009
 sw+0.008
Neg logit contributions
istent-0.061
osity-0.056
urance-0.055
 fault-0.053
istence-0.053
Token He
Token ID679
Feature activation+1.22e-02

Pos logit contributions
 water+0.018
 p+0.016
 sw+0.015
 cool+0.015
 other+0.015
Neg logit contributions
istent-0.026
osity-0.023
urance-0.023
istence-0.021
 Majesty-0.021
Token his
Token ID465
Feature activation+1.04e+00

Pos logit contributions
 water+0.001
 p+0.001
 other+0.001
 cool+0.001
 sw+0.001
Neg logit contributions
istent-0.001
osity-0.001
urance-0.001
 Majesty-0.001
 fault-0.001
Tokenses
Token ID8448
Feature activation-7.69e+00

Pos logit contributions
 water+0.085
 p+0.076
 cool+0.072
 other+0.071
.+0.069
Neg logit contributions
istent-0.097
osity-0.088
urance-0.081
istence-0.080
aries-0.080
Token and
Token ID290
Feature activation+8.96e-02

Pos logit contributions
istent+0.949
osity+0.872
urance+0.858
istence+0.827
 fault+0.825
Neg logit contributions
 water-0.289
 p-0.216
 cool-0.201
 other-0.197
 sw-0.187
Token runs
Token ID4539
Feature activation-1.29e+00

Pos logit contributions
 water+0.006
 p+0.005
 cool+0.005
 other+0.005
 sw+0.005
Neg logit contributions
istent-0.009
osity-0.009
urance-0.008
 fault-0.008
istence-0.008
Token away
Token ID1497
Feature activation+2.52e+00

Pos logit contributions
istent+0.126
osity+0.118
 fault+0.117
urance+0.116
arsh+0.110
Neg logit contributions
 water-0.058
 sw-0.049
 cool-0.048
P-0.048
 se-0.046
Token.
Token ID13
Feature activation+2.53e-01

Pos logit contributions
 water+0.077
P+0.060
 sw+0.055
 cool+0.051
 decided+0.050
Neg logit contributions
istent-0.309
osity-0.291
urance-0.284
 fault-0.280
arsh-0.274
Token He
Token ID679
Feature activation+1.11e-03

Pos logit contributions
 water+0.015
 p+0.013
 cool+0.012
 other+0.012
 sw+0.012
Neg logit contributions
istent-0.027
osity-0.024
urance-0.024
istence-0.023
 Majesty-0.023
Token it
Token ID340
Feature activation+1.16e+00

Pos logit contributions
 water+0.089
 p+0.070
 cool+0.065
 other+0.061
 sw+0.061
Neg logit contributions
istent-0.276
osity-0.255
urance-0.249
 Majesty-0.240
istence-0.239
Token.
Token ID13
Feature activation+2.82e-01

Pos logit contributions
 water+0.028
 p+0.016
 other+0.014
 cool+0.013
 sw+0.012
Neg logit contributions
istent-0.161
osity-0.149
urance-0.147
istence-0.142
 Majesty-0.142
Token The
Token ID383
Feature activation-2.72e-01

Pos logit contributions
 water+0.018
 p+0.016
 cool+0.015
 other+0.015
 was+0.014
Neg logit contributions
istent-0.029
osity-0.026
urance-0.025
istence-0.024
 Majesty-0.024
Token cat
Token ID3797
Feature activation-1.21e+00

Pos logit contributions
istent+0.027
osity+0.024
urance+0.023
istence+0.022
 Majesty+0.022
Neg logit contributions
 water-0.019
 p-0.017
 other-0.016
 cool-0.016
 sw-0.015
Token his
Token ID465
Feature activation+1.13e+00

Pos logit contributions
istent+0.126
osity+0.114
urance+0.111
istence+0.106
 Majesty+0.106
Neg logit contributions
 water-0.073
 p-0.063
 cool-0.059
 other-0.059
 sw-0.058
Tokenses
Token ID8448
Feature activation-7.68e+00

Pos logit contributions
 water+0.132
 p+0.121
 cool+0.119
 other+0.118
 pe+0.117
Neg logit contributions
istent-0.066
osity-0.054
istence-0.047
urance-0.046
aries-0.045
Token and
Token ID290
Feature activation+5.68e-02

Pos logit contributions
istent+0.897
osity+0.811
urance+0.802
istence+0.775
 fault+0.767
Neg logit contributions
 water-0.319
 p-0.235
 cool-0.227
 other-0.227
P-0.217
Token scratches
Token ID37627
Feature activation-3.69e-01

Pos logit contributions
 water+0.004
 p+0.003
 cool+0.003
 other+0.003
 sw+0.003
Neg logit contributions
istent-0.006
osity-0.005
urance-0.005
 fault-0.005
istence-0.005
Token him
Token ID683
Feature activation-3.63e-02

Pos logit contributions
istent+0.040
urance+0.036
osity+0.036
arsh+0.034
 fault+0.034
Neg logit contributions
 water-0.017
 p-0.014
 cool-0.014
 cream-0.013
P-0.013
Token.
Token ID13
Feature activation+2.83e-01

Pos logit contributions
istent+0.005
osity+0.005
urance+0.005
 fault+0.004
istence+0.004
Neg logit contributions
 water-0.001
 p-0.001
 cool-0.000
 other-0.000
 sw-0.000
Token Ben
Token ID3932
Feature activation-5.17e-01

Pos logit contributions
 water+0.018
 p+0.016
 cool+0.015
 other+0.015
 was+0.014
Neg logit contributions
istent-0.030
osity-0.027
urance-0.026
aries-0.025
istence-0.025
Token kitten
Token ID42143
Feature activation-2.59e-01

Pos logit contributions
istent+0.019
urance+0.017
osity+0.017
 fault+0.016
 Majesty+0.016
Neg logit contributions
 water-0.017
 p-0.015
 decided-0.015
 cool-0.014
 sw-0.014
Token is
Token ID318
Feature activation-1.22e+00

Pos logit contributions
istent+0.032
osity+0.030
urance+0.029
istence+0.028
 fault+0.027
Neg logit contributions
 water-0.012
 p-0.010
 was-0.009
 cool-0.009
 sw-0.009
Token scared
Token ID12008
Feature activation+1.23e+00

Pos logit contributions
istent+0.133
osity+0.121
urance+0.118
istence+0.114
 Majesty+0.114
Neg logit contributions
 water-0.068
 p-0.057
 cool-0.054
 other-0.053
 sw-0.052
Token and
Token ID290
Feature activation+1.29e-01

Pos logit contributions
 water+0.038
 p+0.026
P+0.026
 sw+0.024
 cool+0.024
Neg logit contributions
istent-0.157
osity-0.144
urance-0.141
 fault-0.137
istence-0.135
Token his
Token ID465
Feature activation+1.13e+00

Pos logit contributions
 water+0.008
 p+0.007
 cool+0.006
 sw+0.006
 other+0.006
Neg logit contributions
istent-0.014
osity-0.013
urance-0.012
istence-0.012
 Majesty-0.012
Tokenses
Token ID8448
Feature activation-7.67e+00

Pos logit contributions
 water+0.104
 p+0.092
 cool+0.091
 other+0.089
.+0.088
Neg logit contributions
istent-0.092
osity-0.083
istence-0.076
aries-0.075
urance-0.073
Token at
Token ID379
Feature activation-2.78e-01

Pos logit contributions
istent+1.007
osity+0.926
urance+0.914
 fault+0.881
istence+0.879
Neg logit contributions
 water-0.221
 p-0.145
 other-0.129
 cool-0.128
P-0.121
Token Tom
Token ID4186
Feature activation-3.55e-01

Pos logit contributions
istent+0.030
osity+0.027
urance+0.027
 Majesty+0.026
istence+0.026
Neg logit contributions
 water-0.016
 p-0.013
 other-0.013
 cool-0.013
 sw-0.012
Token.
Token ID13
Feature activation+2.61e-01

Pos logit contributions
istent+0.057
osity+0.054
urance+0.052
 Majesty+0.052
istence+0.052
Neg logit contributions
 water-0.002
.-0.000
 p+0.001
 away+0.001
 was+0.002
Token Tom
Token ID4186
Feature activation-3.53e-01

Pos logit contributions
 water+0.017
 p+0.015
.+0.014
 was+0.014
 cool+0.014
Neg logit contributions
istent-0.027
osity-0.026
 Majesty-0.024
aries-0.024
urance-0.024
Token is
Token ID318
Feature activation-1.20e+00

Pos logit contributions
istent+0.037
osity+0.034
urance+0.033
istence+0.031
 fault+0.031
Neg logit contributions
 water-0.022
 p-0.020
 was-0.018
 sw-0.018
 pe-0.018
Token of
Token ID286
Feature activation+3.47e-01

Pos logit contributions
istent+0.230
osity+0.210
urance+0.205
istence+0.196
arsh+0.194
Neg logit contributions
 water-0.099
 p-0.081
 cool-0.078
P-0.075
 other-0.075
Token the
Token ID262
Feature activation-1.70e-01

Pos logit contributions
 water+0.013
 p+0.009
 other+0.008
 cool+0.008
 was+0.007
Neg logit contributions
istent-0.046
osity-0.042
urance-0.041
 Majesty-0.040
istence-0.040
Token web
Token ID3992
Feature activation-3.04e+00

Pos logit contributions
istent+0.017
osity+0.015
urance+0.015
 Majesty+0.014
istence+0.014
Neg logit contributions
 water-0.011
 p-0.009
 cool-0.009
 other-0.009
 sw-0.009
Token and
Token ID290
Feature activation+4.78e-02

Pos logit contributions
istent+0.444
osity+0.418
urance+0.406
 Majesty+0.398
istence+0.395
Neg logit contributions
 water-0.065
 p-0.040
.-0.034
 was-0.030
 other-0.029
Token his
Token ID465
Feature activation+9.75e-01

Pos logit contributions
 water+0.003
 p+0.003
 cool+0.003
 pe+0.003
 other+0.003
Neg logit contributions
istent-0.005
osity-0.004
urance-0.004
 fault-0.004
istence-0.004
Tokenses
Token ID8448
Feature activation-7.66e+00

Pos logit contributions
 water+0.083
 p+0.074
 other+0.072
 cool+0.070
.+0.070
Neg logit contributions
istent-0.091
osity-0.081
istence-0.074
urance-0.073
aries-0.069
Token at
Token ID379
Feature activation-3.05e-01

Pos logit contributions
istent+0.956
osity+0.869
urance+0.865
istence+0.831
 fault+0.829
Neg logit contributions
 water-0.257
 p-0.177
 other-0.171
 cool-0.166
P-0.162
Token Ben
Token ID3932
Feature activation-4.92e-01

Pos logit contributions
istent+0.034
osity+0.031
urance+0.030
istence+0.029
 Majesty+0.029
Neg logit contributions
 water-0.017
 p-0.014
 other-0.013
 cool-0.013
 sw-0.013
Token.
Token ID13
Feature activation+2.50e-01

Pos logit contributions
istent+0.080
osity+0.077
urance+0.074
 Majesty+0.074
istence+0.073
Neg logit contributions
 water-0.002
.-0.001
 p+0.002
 away+0.002
 in+0.003
Token Ben
Token ID3932
Feature activation-4.99e-01

Pos logit contributions
 water+0.015
 p+0.013
.+0.012
 cool+0.012
 other+0.012
Neg logit contributions
istent-0.028
osity-0.026
urance-0.024
 Majesty-0.024
aries-0.024
Token drops
Token ID10532
Feature activation-8.32e-01

Pos logit contributions
istent+0.056
osity+0.053
urance+0.050
istence+0.048
isdom+0.048
Neg logit contributions
 water-0.030
 p-0.028
 was-0.025
 pe-0.024
.-0.023
Token is
Token ID318
Feature activation-1.25e+00

Pos logit contributions
istent+0.118
osity+0.107
urance+0.104
istence+0.099
 Majesty+0.098
Neg logit contributions
 water-0.079
 p-0.069
 cool-0.065
 other-0.064
 sw-0.063
Token afraid
Token ID7787
Feature activation+2.42e-01

Pos logit contributions
istent+0.144
osity+0.132
urance+0.128
istence+0.124
 Majesty+0.124
Neg logit contributions
 water-0.065
 p-0.054
 cool-0.051
 other-0.050
 sw-0.048
Token.
Token ID13
Feature activation+2.87e-01

Pos logit contributions
 water+0.007
 p+0.005
 cool+0.004
 sw+0.004
P+0.004
Neg logit contributions
istent-0.032
osity-0.029
urance-0.029
 fault-0.028
istence-0.028
Token It
Token ID632
Feature activation+2.38e-02

Pos logit contributions
 water+0.018
 p+0.016
 cool+0.016
.+0.016
 was+0.015
Neg logit contributions
istent-0.030
osity-0.028
aries-0.026
urance-0.026
 Majesty-0.026
Token his
Token ID465
Feature activation+1.08e+00

Pos logit contributions
 water+0.002
 p+0.001
 other+0.001
 cool+0.001
 sw+0.001
Neg logit contributions
istent-0.002
osity-0.002
urance-0.002
 Majesty-0.002
 fault-0.002
Tokenses
Token ID8448
Feature activation-7.64e+00

Pos logit contributions
 water+0.122
 p+0.111
 other+0.110
 cool+0.109
.+0.108
Neg logit contributions
istent-0.069
osity-0.059
istence-0.051
urance-0.049
aries-0.048
Token and
Token ID290
Feature activation+3.47e-02

Pos logit contributions
istent+0.943
osity+0.866
urance+0.850
istence+0.822
 fault+0.819
Neg logit contributions
 water-0.290
 p-0.218
 cool-0.200
 other-0.198
 sw-0.183
Token scratches
Token ID37627
Feature activation-3.57e-01

Pos logit contributions
 water+0.002
 p+0.002
 cool+0.002
 sw+0.002
 pe+0.002
Neg logit contributions
istent-0.004
osity-0.003
urance-0.003
 fault-0.003
arsh-0.003
Token Tom
Token ID4186
Feature activation-3.52e-01

Pos logit contributions
istent+0.042
urance+0.038
osity+0.038
 fault+0.036
istence+0.036
Neg logit contributions
 water-0.014
 p-0.011
 cool-0.011
 sw-0.010
 pe-0.010
Token's
Token ID338
Feature activation-2.26e+00

Pos logit contributions
istent+0.045
osity+0.043
 Majesty+0.041
urance+0.041
istence+0.040
Neg logit contributions
 water-0.014
 p-0.011
.-0.011
 away-0.010
 other-0.009
Token hand
Token ID1021
Feature activation-1.34e+00

Pos logit contributions
istent+0.222
osity+0.197
urance+0.185
istence+0.184
 Majesty+0.177
Neg logit contributions
 water-0.166
 p-0.145
 other-0.140
 cool-0.136
.-0.136
Token is
Token ID318
Feature activation-1.18e+00

Pos logit contributions
 water+0.007
 other+0.006
P+0.006
 cool+0.006
 p+0.006
Neg logit contributions
istent-0.011
osity-0.010
 fault-0.010
urance-0.010
 Majesty-0.010
Token angry
Token ID7954
Feature activation+7.15e-01

Pos logit contributions
istent+0.136
osity+0.124
urance+0.121
 Majesty+0.117
istence+0.117
Neg logit contributions
 water-0.059
 p-0.048
 cool-0.045
 other-0.045
 sw-0.043
Token.
Token ID13
Feature activation+2.57e-01

Pos logit contributions
 water+0.022
 p+0.015
 cool+0.014
 other+0.013
 sw+0.013
Neg logit contributions
istent-0.093
osity-0.087
urance-0.085
 fault-0.082
istence-0.082
Token It
Token ID632
Feature activation+9.81e-02

Pos logit contributions
 water+0.019
 p+0.016
 cool+0.016
 other+0.016
 sw+0.015
Neg logit contributions
istent-0.023
osity-0.021
urance-0.020
istence-0.019
 Majesty-0.019
Token his
Token ID465
Feature activation+1.19e+00

Pos logit contributions
 water+0.007
P+0.006
B+0.006
 other+0.006
S+0.006
Neg logit contributions
istent-0.007
ses-0.007
 fault-0.007
osity-0.007
 Majesty-0.006
Tokenses
Token ID8448
Feature activation-7.63e+00

Pos logit contributions
 water+0.132
 p+0.121
 cool+0.117
 other+0.117
 sw+0.115
Neg logit contributions
istent-0.073
osity-0.059
urance-0.055
istence-0.052
aries-0.050
Token.
Token ID13
Feature activation+2.26e-01

Pos logit contributions
istent+0.873
osity+0.788
urance+0.777
 fault+0.764
istence+0.753
Neg logit contributions
 water-0.320
 p-0.242
 other-0.235
 cool-0.234
P-0.233
Token It
Token ID632
Feature activation+7.71e-02

Pos logit contributions
 water+0.016
 p+0.014
 cool+0.014
 other+0.013
 was+0.013
Neg logit contributions
istent-0.021
osity-0.019
urance-0.018
 Majesty-0.018
 fault-0.017
Token scratches
Token ID37627
Feature activation-2.87e-01

Pos logit contributions
 water+0.005
B+0.005
P+0.005
 other+0.005
 decided+0.005
Neg logit contributions
istent-0.006
ses-0.005
 fault-0.005
osity-0.005
 Majesty-0.005
Token.
Token ID13
Feature activation+2.52e-01

Pos logit contributions
istent+0.032
osity+0.029
urance+0.029
istence+0.028
aries+0.028
Neg logit contributions
 water-0.013
 p-0.011
 cool-0.010
 sw-0.010
 pe-0.010
Token It
Token ID632
Feature activation+1.35e-01

Pos logit contributions
 water+0.017
 p+0.014
 cool+0.014
 other+0.014
 was+0.013
Neg logit contributions
istent-0.026
osity-0.023
urance-0.022
 Majesty-0.021
istence-0.021
Token slide
Token ID10649
Feature activation+1.48e+00

Pos logit contributions
istent+0.001
urance+0.001
osity+0.001
 fault+0.001
 Majesty+0.001
Neg logit contributions
 water-0.001
 p-0.001
 sw-0.001
 decided-0.001
 cool-0.001
Token.
Token ID13
Feature activation+3.20e-01

Pos logit contributions
 water+0.034
 p+0.019
 cool+0.019
 sw+0.019
P+0.017
Neg logit contributions
istent-0.198
osity-0.181
urance-0.179
 fault-0.174
istence-0.174
Token The
Token ID383
Feature activation-1.90e-01

Pos logit contributions
 water+0.022
 p+0.019
 other+0.018
 cool+0.018
 sw+0.018
Neg logit contributions
istent-0.030
osity-0.027
urance-0.026
istence-0.025
 Majesty-0.025
Token cat
Token ID3797
Feature activation-1.17e+00

Pos logit contributions
istent+0.020
osity+0.018
urance+0.018
istence+0.017
 Majesty+0.017
Neg logit contributions
 water-0.012
 p-0.011
 other-0.010
 cool-0.010
 was-0.009
Token his
Token ID465
Feature activation+1.19e+00

Pos logit contributions
istent+0.118
osity+0.106
urance+0.104
 Majesty+0.101
 fault+0.100
Neg logit contributions
 water-0.069
 p-0.056
 other-0.055
 cool-0.055
 sw-0.053
Tokenses
Token ID8448
Feature activation-7.60e+00

Pos logit contributions
 water+0.104
 p+0.095
 cool+0.091
 other+0.089
.+0.088
Neg logit contributions
istent-0.103
osity-0.092
urance-0.083
istence-0.083
aries-0.082
Token at
Token ID379
Feature activation-2.06e-01

Pos logit contributions
istent+0.919
osity+0.833
urance+0.830
 fault+0.800
istence+0.794
Neg logit contributions
 water-0.266
 other-0.185
 p-0.185
P-0.182
 cool-0.176
Token him
Token ID683
Feature activation+3.42e-02

Pos logit contributions
istent+0.020
urance+0.018
osity+0.017
 Majesty+0.017
istence+0.017
Neg logit contributions
 water-0.012
 p-0.010
 cool-0.010
 sw-0.010
 decided-0.010
Token.
Token ID13
Feature activation+2.89e-01

Pos logit contributions
 water+0.000
 p+0.000
.+0.000
 cool-0.000
 other-0.000
Neg logit contributions
istent-0.005
osity-0.005
urance-0.005
 Majesty-0.005
istence-0.005
Token Tom
Token ID4186
Feature activation-3.34e-01

Pos logit contributions
 water+0.018
 p+0.015
 cool+0.014
 other+0.014
 was+0.014
Neg logit contributions
istent-0.031
osity-0.028
urance-0.027
 Majesty-0.026
istence-0.026
Token is
Token ID318
Feature activation-1.12e+00

Pos logit contributions
istent+0.035
osity+0.032
urance+0.031
istence+0.030
 Majesty+0.029
Neg logit contributions
 water-0.021
 p-0.018
 cool-0.016
 other-0.016
 was-0.016
Token of
Token ID286
Feature activation+4.91e-01

Pos logit contributions
 water+0.038
 sw+0.027
P+0.026
 p+0.025
 cool+0.023
Neg logit contributions
istent-0.170
osity-0.155
urance-0.153
 fault-0.149
istence-0.146
Token Tom
Token ID4186
Feature activation-1.86e-01

Pos logit contributions
 water+0.017
 other+0.013
 p+0.012
.+0.011
 cool+0.011
Neg logit contributions
istent-0.070
osity-0.065
urance-0.063
istence-0.061
 Majesty-0.061
Token.
Token ID13
Feature activation+2.25e-01

Pos logit contributions
istent+0.029
osity+0.028
urance+0.027
 Majesty+0.027
istence+0.026
Neg logit contributions
 water-0.002
.-0.000
 p-0.000
 other-0.000
 was+0.000
Token It
Token ID632
Feature activation+6.88e-02

Pos logit contributions
 water+0.016
 p+0.014
 cool+0.013
.+0.013
 was+0.013
Neg logit contributions
istent-0.022
osity-0.021
 Majesty-0.019
urance-0.019
aries-0.019
Token his
Token ID465
Feature activation+1.18e+00

Pos logit contributions
 water+0.005
P+0.004
 p+0.004
 other+0.004
 cool+0.004
Neg logit contributions
istent-0.006
osity-0.005
urance-0.005
 fault-0.005
 Majesty-0.005
Tokenses
Token ID8448
Feature activation-7.58e+00

Pos logit contributions
 water+0.132
 p+0.122
 cool+0.119
 other+0.119
.+0.116
Neg logit contributions
istent-0.074
osity-0.062
istence-0.055
urance-0.053
aries-0.052
Token and
Token ID290
Feature activation+1.78e-01

Pos logit contributions
istent+0.896
osity+0.806
urance+0.801
 fault+0.774
istence+0.772
Neg logit contributions
 water-0.309
 p-0.233
 cool-0.220
 other-0.216
 cream-0.206
Token scratches
Token ID37627
Feature activation-2.90e-01

Pos logit contributions
 water+0.012
 p+0.010
 cool+0.010
 other+0.009
 sw+0.009
Neg logit contributions
istent-0.018
osity-0.016
urance-0.016
 Majesty-0.015
 fault-0.015
Token.
Token ID13
Feature activation+2.25e-01

Pos logit contributions
istent+0.036
urance+0.033
osity+0.033
arsh+0.031
istence+0.031
Neg logit contributions
 water-0.009
 p-0.007
 cool-0.007
 sw-0.006
 pe-0.006
Token It
Token ID632
Feature activation+7.01e-02

Pos logit contributions
 water+0.016
 p+0.014
 cool+0.013
 other+0.013
.+0.013
Neg logit contributions
istent-0.022
osity-0.020
 Majesty-0.019
urance-0.019
aries-0.018
Token hurts
Token ID20406
Feature activation-8.44e-01

Pos logit contributions
 water+0.005
P+0.004
 other+0.004
B+0.004
 cool+0.004
Neg logit contributions
istent-0.006
osity-0.005
ses-0.005
 Majesty-0.005
 fault-0.005
Token soon
Token ID2582
Feature activation-6.05e-01

Pos logit contributions
istent+0.061
osity+0.056
urance+0.055
istence+0.052
 Majesty+0.052
Neg logit contributions
 water-0.026
 p-0.022
 cool-0.020
 other-0.020
 sw-0.019
Token!"
Token ID2474
Feature activation-1.07e+00

Pos logit contributions
istent+0.080
osity+0.075
urance+0.073
istence+0.071
 fault+0.070
Neg logit contributions
 water-0.021
.-0.016
 p-0.016
 cool-0.014
 was-0.014
Token
Token ID198
Feature activation+2.31e-01

Pos logit contributions
istent+0.125
osity+0.114
urance+0.112
 Majesty+0.108
istence+0.108
Neg logit contributions
 water-0.052
 p-0.043
 other-0.039
 cool-0.039
 was-0.038
Token
Token ID198
Feature activation+1.81e-01

Pos logit contributions
 water+0.011
 p+0.008
 cool+0.008
 other+0.007
 sw+0.007
Neg logit contributions
istent-0.027
osity-0.025
urance-0.024
 Majesty-0.023
istence-0.023
TokenL
Token ID43
Feature activation+1.07e+00

Pos logit contributions
 water+0.009
 p+0.007
 cool+0.006
 other+0.006
 sw+0.006
Neg logit contributions
istent-0.020
osity-0.019
urance-0.018
istence-0.018
 Majesty-0.018
Tokenily
Token ID813
Feature activation+3.17e+00

Pos logit contributions
 water+0.056
 p+0.046
 other+0.043
 cool+0.043
 was+0.042
Neg logit contributions
istent-0.121
osity-0.110
urance-0.108
istence-0.103
 Majesty-0.103
Token hung
Token ID9174
Feature activation+3.12e-02

Pos logit contributions
 water+0.103
 p+0.087
 was+0.077
 went+0.068
 sw+0.066
Neg logit contributions
istent-0.429
osity-0.403
urance-0.390
istence-0.377
 fault-0.377
Token up
Token ID510
Feature activation-8.25e-01

Pos logit contributions
 water+0.001
 p+0.001
 other+0.001
 cool+0.001
.+0.001
Neg logit contributions
istent-0.004
osity-0.004
urance-0.004
istence-0.004
 fault-0.003
Token the
Token ID262
Feature activation-1.65e-01

Pos logit contributions
istent+0.105
osity+0.097
urance+0.096
istence+0.092
 Majesty+0.092
Neg logit contributions
 water-0.029
 p-0.021
 cool-0.019
 other-0.019
 sw-0.018
Token phone
Token ID3072
Feature activation+3.74e-01

Pos logit contributions
istent+0.015
 Majesty+0.014
osity+0.014
urance+0.013
 fault+0.013
Neg logit contributions
 water-0.009
 decided-0.009
B-0.008
P-0.008
S-0.008
Token and
Token ID290
Feature activation+6.43e-02

Pos logit contributions
 water+0.011
 p+0.008
 cool+0.007
 other+0.006
.+0.006
Neg logit contributions
istent-0.050
osity-0.047
urance-0.046
 Majesty-0.045
istence-0.044
Token,
Token ID11
Feature activation-5.22e-01

Pos logit contributions
istent+0.219
osity+0.201
urance+0.200
istence+0.198
 Majesty+0.191
Neg logit contributions
 water-0.083
.-0.070
 in-0.066
 was-0.066
 p-0.063
Token more
Token ID517
Feature activation+1.48e+00

Pos logit contributions
istent+0.062
osity+0.057
urance+0.056
istence+0.054
 Majesty+0.053
Neg logit contributions
 water-0.027
 p-0.023
 cool-0.022
 other-0.022
 pe-0.020
Token evil
Token ID6181
Feature activation-1.77e+00

Pos logit contributions
 water+0.070
 p+0.057
 other+0.054
 cool+0.053
 was+0.049
Neg logit contributions
istent-0.176
osity-0.161
urance-0.158
istence-0.152
 fault-0.149
Token than
Token ID621
Feature activation-2.21e+00

Pos logit contributions
istent+0.211
osity+0.194
urance+0.188
istence+0.182
aries+0.176
Neg logit contributions
 water-0.090
 p-0.073
 other-0.069
.-0.069
 cool-0.068
Token the
Token ID262
Feature activation-2.03e-01

Pos logit contributions
istent+0.261
osity+0.234
urance+0.233
istence+0.223
 Majesty+0.221
Neg logit contributions
 water-0.116
 p-0.092
 other-0.092
 cool-0.088
.-0.084
Token devil
Token ID17118
Feature activation+2.67e+00

Pos logit contributions
istent+0.023
osity+0.021
urance+0.021
istence+0.020
 Majesty+0.020
Neg logit contributions
 water-0.011
 p-0.009
 other-0.009
 cool-0.009
 pe-0.008
Token,
Token ID11
Feature activation-5.30e-01

Pos logit contributions
 water+0.120
.+0.093
 p+0.093
 other+0.090
 cool+0.088
Neg logit contributions
istent-0.331
urance-0.304
osity-0.302
istence-0.294
 Majesty-0.286
Token the
Token ID262
Feature activation-2.03e-01

Pos logit contributions
istent+0.063
osity+0.058
urance+0.057
istence+0.054
 Majesty+0.054
Neg logit contributions
 water-0.026
 p-0.022
 cool-0.021
 other-0.020
 was-0.019
Token poor
Token ID3595
Feature activation+4.03e-01

Pos logit contributions
istent+0.022
osity+0.020
urance+0.019
istence+0.019
 Majesty+0.018
Neg logit contributions
 water-0.012
 p-0.010
 other-0.010
 cool-0.010
 sw-0.009
Token have
Token ID423
Feature activation-4.75e-02

Pos logit contributions
 water+0.026
 p+0.022
 other+0.021
 was+0.021
.+0.021
Neg logit contributions
istent-0.043
osity-0.039
urance-0.038
istence-0.037
aries-0.036
Token it
Token ID340
Feature activation+1.06e+00

Pos logit contributions
istent+0.006
osity+0.005
urance+0.005
istence+0.005
 Majesty+0.005
Neg logit contributions
 water-0.002
 p-0.002
 other-0.002
 was-0.002
 cool-0.002
Token very
Token ID845
Feature activation+1.95e+00

Pos logit contributions
 water+0.068
 p+0.061
 cool+0.060
 in+0.057
.+0.056
Neg logit contributions
istent-0.120
urance-0.108
osity-0.108
istence-0.100
aries-0.100
Token happy
Token ID3772
Feature activation-4.71e-01

Pos logit contributions
 water+0.135
 p+0.117
 other+0.112
 cool+0.111
 sw+0.109
Neg logit contributions
istent-0.184
osity-0.165
urance-0.160
 Majesty-0.154
istence-0.152
Token."
Token ID526
Feature activation-1.77e-01

Pos logit contributions
istent+0.063
urance+0.057
osity+0.056
istence+0.055
aries+0.053
Neg logit contributions
 water-0.018
.-0.015
 p-0.014
 in-0.013
 was-0.013
Token
Token ID198
Feature activation+1.70e-01

Pos logit contributions
istent+0.024
osity+0.022
urance+0.022
 fault+0.021
 Majesty+0.021
Neg logit contributions
 water-0.006
 p-0.004
.-0.004
 was-0.004
 other-0.004
Token
Token ID198
Feature activation+1.60e-01

Pos logit contributions
 water+0.007
 p+0.006
 cool+0.005
 other+0.005
 sw+0.005
Neg logit contributions
istent-0.020
osity-0.019
urance-0.018
 Majesty-0.018
istence-0.018
TokenJ
Token ID41
Feature activation+2.95e+00

Pos logit contributions
 water+0.010
 p+0.008
 cool+0.008
 other+0.008
 away+0.008
Neg logit contributions
istent-0.016
osity-0.015
urance-0.014
 Majesty-0.014
istence-0.014
Tokenessa
Token ID21411
Feature activation-6.23e-01

Pos logit contributions
 water+0.261
 p+0.235
.+0.233
 was+0.232
P+0.228
Neg logit contributions
istent-0.211
urance-0.183
osity-0.182
 Majesty-0.174
istence-0.167
Token smiled
Token ID13541
Feature activation+2.53e-01

Pos logit contributions
istent+0.078
osity+0.072
urance+0.071
 fault+0.069
istence+0.068
Neg logit contributions
 water-0.025
 p-0.021
 was-0.018
 sw-0.018
 cool-0.017
Token,
Token ID11
Feature activation-5.38e-01

Pos logit contributions
 water+0.010
 p+0.007
 other+0.007
 cool+0.006
 sw+0.006
Neg logit contributions
istent-0.032
osity-0.029
urance-0.028
 Majesty-0.028
istence-0.028
Token and
Token ID290
Feature activation+5.87e-02

Pos logit contributions
istent+0.067
urance+0.061
osity+0.061
 fault+0.060
 Majesty+0.059
Neg logit contributions
 water-0.024
 p-0.021
 was-0.019
 cool-0.018
 went-0.018
Token they
Token ID484
Feature activation+8.15e-01

Pos logit contributions
 water+0.002
 p+0.002
 cool+0.002
 other+0.002
 sw+0.002
Neg logit contributions
istent-0.007
osity-0.007
urance-0.007
istence-0.006
 Majesty-0.006
Token him
Token ID683
Feature activation-1.04e-01

Pos logit contributions
istent+0.046
osity+0.042
urance+0.041
 Majesty+0.040
istence+0.040
Neg logit contributions
 water-0.016
 p-0.012
 other-0.012
 was-0.011
 cool-0.011
Token.
Token ID13
Feature activation+2.07e-01

Pos logit contributions
istent+0.016
osity+0.015
urance+0.015
 Majesty+0.015
istence+0.015
Neg logit contributions
 water-0.001
.-0.001
 p-0.000
 was-0.000
 in-0.000
Token She
Token ID1375
Feature activation-1.25e+00

Pos logit contributions
 water+0.012
.+0.011
 was+0.011
 p+0.011
 went+0.010
Neg logit contributions
istent-0.022
 Majesty-0.021
 fault-0.021
osity-0.020
ancing-0.019
Token smiled
Token ID13541
Feature activation+3.03e-01

Pos logit contributions
istent+0.159
osity+0.146
urance+0.142
 Majesty+0.138
istence+0.138
Neg logit contributions
 water-0.044
 p-0.030
 other-0.029
 cool-0.028
 away-0.026
Token and
Token ID290
Feature activation+1.90e-01

Pos logit contributions
 water+0.011
 p+0.009
 cool+0.008
 other+0.008
 sw+0.007
Neg logit contributions
istent-0.038
osity-0.035
urance-0.035
 Majesty-0.033
istence-0.033
Token p
Token ID279
Feature activation+2.84e+00

Pos logit contributions
 water+0.006
 p+0.004
 other+0.004
 cool+0.004
 sw+0.003
Neg logit contributions
istent-0.025
osity-0.023
urance-0.022
 Majesty-0.022
istence-0.022
Tokenatted
Token ID16898
Feature activation-2.08e+00

Pos logit contributions
 water+0.299
 p+0.268
 other+0.266
 cool+0.264
 sw+0.256
Neg logit contributions
istent-0.172
osity-0.147
urance-0.134
 Majesty-0.124
 fault-0.124
Token his
Token ID465
Feature activation+1.00e+00

Pos logit contributions
istent+0.213
osity+0.193
urance+0.188
 Majesty+0.181
istence+0.179
Neg logit contributions
 water-0.130
 p-0.112
 cool-0.106
 other-0.106
 was-0.103
Token head
Token ID1182
Feature activation-1.99e+00

Pos logit contributions
 water+0.082
 p+0.072
 other+0.070
 cool+0.069
 sw+0.068
Neg logit contributions
istent-0.082
osity-0.073
urance-0.071
 Majesty-0.067
istence-0.066
Token.
Token ID13
Feature activation+2.17e-01

Pos logit contributions
istent+0.263
osity+0.240
urance+0.236
istence+0.227
 fault+0.225
Neg logit contributions
 water-0.060
 p-0.037
 other-0.035
P-0.033
 cool-0.032
Token Max
Token ID5436
Feature activation-2.50e+00

Pos logit contributions
 water+0.012
.+0.012
 was+0.012
 went+0.011
 cool+0.011
Neg logit contributions
istent-0.022
 fault-0.021
 Majesty-0.021
osity-0.020
urance-0.019
Token't
Token ID470
Feature activation-2.01e-01

Pos logit contributions
istent+0.176
osity+0.171
 Majesty+0.165
urance+0.157
sing+0.153
Neg logit contributions
 water-0.127
 was-0.120
 p-0.113
.-0.112
 other-0.110
Token find
Token ID1064
Feature activation-6.78e-01

Pos logit contributions
istent+0.020
osity+0.018
urance+0.018
istence+0.017
 Majesty+0.017
Neg logit contributions
 water-0.013
 p-0.011
 sw-0.010
 cool-0.010
 other-0.010
Token one
Token ID530
Feature activation-8.61e-01

Pos logit contributions
istent+0.082
osity+0.075
urance+0.073
istence+0.071
 Majesty+0.070
Neg logit contributions
 water-0.031
 p-0.024
 other-0.023
 cool-0.023
 was-0.021
Token.
Token ID13
Feature activation+1.24e-01

Pos logit contributions
istent+0.117
osity+0.109
urance+0.107
 fault+0.105
istence+0.103
Neg logit contributions
 water-0.022
 p-0.014
 sw-0.012
 cool-0.011
 other-0.010
Token She
Token ID1375
Feature activation-1.36e+00

Pos logit contributions
 water+0.007
 was+0.007
 p+0.006
.+0.006
 other+0.006
Neg logit contributions
istent-0.013
osity-0.012
 Majesty-0.011
urance-0.011
 fault-0.011
Token decided
Token ID3066
Feature activation+2.44e+00

Pos logit contributions
istent+0.164
osity+0.146
urance+0.145
istence+0.140
 Majesty+0.140
Neg logit contributions
 water-0.055
 cool-0.038
 p-0.038
 other-0.038
 cream-0.036
Token to
Token ID284
Feature activation+1.72e-01

Pos logit contributions
 water+0.090
 p+0.069
 was+0.064
 other+0.063
.+0.062
Neg logit contributions
istent-0.320
osity-0.292
urance-0.287
istence-0.278
 Majesty-0.277
Token go
Token ID467
Feature activation-1.43e+00

Pos logit contributions
 water+0.009
 p+0.008
 cool+0.007
 other+0.007
 was+0.007
Neg logit contributions
istent-0.019
osity-0.018
urance-0.017
 Majesty-0.016
istence-0.016
Token to
Token ID284
Feature activation+1.82e-01

Pos logit contributions
istent+0.154
osity+0.140
urance+0.138
istence+0.134
aries+0.133
Neg logit contributions
 water-0.067
 p-0.054
 sw-0.053
 other-0.053
P-0.051
Token the
Token ID262
Feature activation-2.81e-01

Pos logit contributions
 water+0.006
 p+0.004
 other+0.004
 cool+0.003
.+0.003
Neg logit contributions
istent-0.026
osity-0.025
urance-0.023
 Majesty-0.023
istence-0.023
Token store
Token ID3650
Feature activation+4.93e-01

Pos logit contributions
istent+0.028
osity+0.026
urance+0.025
 Majesty+0.024
istence+0.024
Neg logit contributions
 water-0.017
 p-0.015
 cool-0.014
 other-0.014
 sw-0.014
Token big
Token ID1263
Feature activation-2.18e-01

Pos logit contributions
istent+0.005
osity+0.004
 Majesty+0.004
urance+0.004
istence+0.004
Neg logit contributions
 water-0.002
 away-0.001
 decided-0.001
 p-0.001
 other-0.001
Token hill
Token ID12788
Feature activation-1.00e+00

Pos logit contributions
istent+0.024
osity+0.022
urance+0.022
 Majesty+0.021
istence+0.021
Neg logit contributions
 water-0.011
 p-0.009
 cool-0.009
 other-0.009
 sw-0.008
Token with
Token ID351
Feature activation-3.81e-01

Pos logit contributions
istent+0.125
osity+0.114
urance+0.109
istence+0.107
arsh+0.106
Neg logit contributions
 water-0.031
 p-0.022
 other-0.022
 cool-0.021
P-0.020
Token many
Token ID867
Feature activation+1.03e+00

Pos logit contributions
istent+0.033
 fault+0.031
osity+0.031
urance+0.030
 Majesty+0.029
Neg logit contributions
P-0.019
 away-0.019
 water-0.019
 p-0.017
B-0.017
Token rocks
Token ID12586
Feature activation+1.47e+00

Pos logit contributions
P+0.049
 away+0.048
 water+0.047
L+0.042
B+0.041
Neg logit contributions
istent-0.100
 fault-0.086
 Majesty-0.086
osity-0.085
urance-0.085
Token and
Token ID290
Feature activation+1.24e-01

Pos logit contributions
 water+0.038
 p+0.025
 cool+0.024
 other+0.022
P+0.020
Neg logit contributions
istent-0.195
osity-0.180
urance-0.174
 fault-0.173
istence-0.170
Token dirt
Token ID13647
Feature activation+1.23e+00

Pos logit contributions
 water+0.005
 away+0.005
P+0.005
 p+0.004
 cool+0.004
Neg logit contributions
istent-0.013
osity-0.012
 Majesty-0.012
urance-0.012
 fault-0.011
Token.
Token ID13
Feature activation+1.93e-01

Pos logit contributions
 water+0.027
 cool+0.018
 p+0.017
 other+0.016
P+0.015
Neg logit contributions
istent-0.163
osity-0.152
 fault-0.149
urance-0.149
istence-0.144
Token They
Token ID1119
Feature activation+5.87e-01

Pos logit contributions
 water+0.010
 p+0.008
 other+0.007
 cool+0.007
 was+0.007
Neg logit contributions
istent-0.023
osity-0.021
urance-0.020
 Majesty-0.020
istence-0.020
Token want
Token ID765
Feature activation-1.40e+00

Pos logit contributions
 water+0.037
 p+0.032
 cool+0.030
 other+0.030
 sw+0.029
Neg logit contributions
istent-0.060
osity-0.055
urance-0.054
 Majesty-0.051
 fault-0.051
Token to
Token ID284
Feature activation+2.80e-01

Pos logit contributions
istent+0.130
 fault+0.123
osity+0.121
urance+0.116
arsh+0.110
Neg logit contributions
 water-0.073
P-0.071
 p-0.064
 away-0.062
S-0.061
Token splash
Token ID22870
Feature activation+1.77e+00

Pos logit contributions
 water+0.004
 p+0.003
 other+0.003
 cool+0.003
 sw+0.003
Neg logit contributions
istent-0.008
osity-0.007
urance-0.007
istence-0.007
 Majesty-0.007
Token water
Token ID1660
Feature activation+2.70e+00

Pos logit contributions
 water+0.072
P+0.063
 pe+0.062
 sw+0.061
 decided+0.060
Neg logit contributions
istent-0.159
osity-0.139
urance-0.137
arsh-0.134
 fault-0.134
Token everywhere
Token ID8347
Feature activation-2.49e+00

Pos logit contributions
 water+0.068
 p+0.043
 other+0.040
 cool+0.040
 was+0.035
Neg logit contributions
istent-0.364
osity-0.335
urance-0.331
 fault-0.320
istence-0.319
Token.
Token ID13
Feature activation+1.11e-01

Pos logit contributions
istent+0.357
osity+0.332
urance+0.326
istence+0.316
 Majesty+0.316
Neg logit contributions
 water-0.051
 p-0.028
 cool-0.021
 other-0.021
 sw-0.019
Token After
Token ID2293
Feature activation-5.49e-01

Pos logit contributions
 water+0.007
 p+0.007
 was+0.007
 other+0.006
.+0.006
Neg logit contributions
istent-0.011
osity-0.010
urance-0.010
 Majesty-0.009
istence-0.009
Token they
Token ID484
Feature activation+9.79e-01

Pos logit contributions
istent+0.066
osity+0.060
urance+0.059
 Majesty+0.057
istence+0.057
Neg logit contributions
 water-0.026
 p-0.020
 cool-0.019
 other-0.019
 sw-0.018
Token finished
Token ID5201
Feature activation+4.37e-01

Pos logit contributions
 water+0.068
P+0.065
 cre+0.064
 sound+0.064
b+0.064
Neg logit contributions
istent-0.068
urance-0.059
osity-0.057
istence-0.054
 fault-0.052
Token,
Token ID11
Feature activation-4.24e-01

Pos logit contributions
 water+0.030
 p+0.027
 cool+0.024
.+0.024
 sw+0.024
Neg logit contributions
istent-0.045
osity-0.040
urance-0.039
istence-0.037
aries-0.037
Token Lily
Token ID20037
Feature activation+1.72e-01

Pos logit contributions
istent+0.048
osity+0.044
urance+0.043
 Majesty+0.041
istence+0.041
Neg logit contributions
 water-0.021
 p-0.017
 cool-0.016
 other-0.016
 sw-0.016
Token's
Token ID338
Feature activation-2.21e+00

Pos logit contributions
 water+0.008
 p+0.007
 cool+0.006
 other+0.006
 sw+0.006
Neg logit contributions
istent-0.020
osity-0.019
urance-0.018
istence-0.017
 Majesty-0.017
Token mom
Token ID1995
Feature activation+1.26e-01

Pos logit contributions
istent+0.248
osity+0.227
urance+0.218
istence+0.213
 Majesty+0.209
Neg logit contributions
 water-0.126
 p-0.104
 cool-0.099
 other-0.098
 was-0.094
Tokeninter
Token ID3849
Feature activation+5.92e-01

Pos logit contributions
 water+0.050
.+0.045
 p+0.043
 cool+0.041
 was+0.040
Neg logit contributions
istent-0.035
 Majesty-0.032
osity-0.032
urance-0.031
aries-0.028
Token was
Token ID373
Feature activation-1.24e-01

Pos logit contributions
 water+0.022
 p+0.017
 was+0.015
 cool+0.015
 sw+0.015
Neg logit contributions
istent-0.076
osity-0.070
urance-0.069
istence-0.067
 Majesty-0.067
Token happy
Token ID3772
Feature activation-4.99e-01

Pos logit contributions
istent+0.014
osity+0.013
urance+0.013
 Majesty+0.012
istence+0.012
Neg logit contributions
 water-0.006
 p-0.006
 cool-0.005
 was-0.005
 other-0.005
Token to
Token ID284
Feature activation+1.00e-01

Pos logit contributions
istent+0.068
osity+0.063
urance+0.062
istence+0.060
 Majesty+0.060
Neg logit contributions
 water-0.016
 p-0.012
.-0.011
 was-0.010
 cool-0.010
Token help
Token ID1037
Feature activation+1.35e+00

Pos logit contributions
 water+0.006
 p+0.005
 other+0.005
 cool+0.005
 cream+0.005
Neg logit contributions
istent-0.010
osity-0.009
urance-0.009
istence-0.008
 Majesty-0.008
Token.
Token ID13
Feature activation+1.52e-01

Pos logit contributions
 water+0.079
 p+0.067
 other+0.064
 cool+0.063
.+0.062
Neg logit contributions
istent-0.143
osity-0.131
urance-0.128
 Majesty-0.124
istence-0.122
Token She
Token ID1375
Feature activation-1.34e+00

Pos logit contributions
 water+0.008
 was+0.007
 p+0.007
.+0.006
 cool+0.006
Neg logit contributions
istent-0.017
 fault-0.016
urance-0.016
osity-0.015
aries-0.015
Token put
Token ID1234
Feature activation+1.03e+00

Pos logit contributions
istent+0.158
osity+0.144
urance+0.140
istence+0.136
 Majesty+0.135
Neg logit contributions
 water-0.058
 p-0.045
 other-0.044
 cool-0.043
 away-0.040
Token the
Token ID262
Feature activation-2.39e-01

Pos logit contributions
 water+0.037
 p+0.028
 cool+0.025
 other+0.025
 sw+0.025
Neg logit contributions
istent-0.129
osity-0.119
urance-0.116
istence-0.113
 fault-0.112
Token paper
Token ID3348
Feature activation-1.18e-01

Pos logit contributions
istent+0.025
osity+0.022
urance+0.022
 fault+0.021
istence+0.021
Neg logit contributions
 water-0.013
 p-0.012
 cool-0.011
 sw-0.011
 decided-0.011
Token into
Token ID656
Feature activation+1.38e-01

Pos logit contributions
istent+0.015
osity+0.014
urance+0.014
 Majesty+0.013
istence+0.013
Neg logit contributions
 water-0.004
 p-0.003
 cool-0.003
 other-0.003
 sw-0.002
Token that
Token ID326
Feature activation-1.93e-01

Pos logit contributions
 water+0.035
 p+0.027
 other+0.025
 cool+0.024
 was+0.024
Neg logit contributions
istent-0.105
osity-0.096
urance-0.094
istence-0.091
 Majesty-0.090
Token she
Token ID673
Feature activation+1.66e-01

Pos logit contributions
istent+0.026
osity+0.024
urance+0.023
 Majesty+0.022
istence+0.022
Neg logit contributions
 water-0.007
 p-0.006
 was-0.005
 other-0.005
.-0.005
Token had
Token ID550
Feature activation+2.15e-01

Pos logit contributions
 water+0.006
 p+0.005
 cool+0.004
 other+0.004
 sw+0.004
Neg logit contributions
istent-0.021
osity-0.019
urance-0.019
istence-0.018
 fault-0.018
Token put
Token ID1234
Feature activation+1.03e+00

Pos logit contributions
 water+0.011
 p+0.009
 cool+0.009
 other+0.009
 sw+0.008
Neg logit contributions
istent-0.023
osity-0.021
urance-0.021
 fault-0.020
istence-0.020
Token it
Token ID340
Feature activation+1.09e+00

Pos logit contributions
 water+0.037
 p+0.028
 cool+0.025
 sw+0.025
 other+0.025
Neg logit contributions
istent-0.128
osity-0.119
urance-0.116
 fault-0.113
istence-0.113
Token in
Token ID287
Feature activation+7.64e-01

Pos logit contributions
 water+0.032
 p+0.023
 other+0.019
 sw+0.019
 cool+0.019
Neg logit contributions
istent-0.142
osity-0.133
urance-0.130
 fault-0.126
istence-0.125
Token the
Token ID262
Feature activation-2.38e-01

Pos logit contributions
 water+0.027
 p+0.020
 other+0.017
 cool+0.017
 was+0.016
Neg logit contributions
istent-0.101
osity-0.093
urance-0.091
 Majesty-0.089
istence-0.088
Token kitchen
Token ID9592
Feature activation-3.03e-01

Pos logit contributions
istent+0.020
osity+0.019
urance+0.019
 fault+0.019
 Majesty+0.018
Neg logit contributions
 water-0.014
B-0.013
 p-0.013
 cre-0.013
 pe-0.012
Token drawer
Token ID33451
Feature activation-5.61e-01

Pos logit contributions
istent+0.041
osity+0.038
urance+0.037
istence+0.036
 Majesty+0.036
Neg logit contributions
 water-0.009
 p-0.006
 cool-0.005
.-0.005
 other-0.005
Token.
Token ID13
Feature activation+1.03e-01

Pos logit contributions
istent+0.082
osity+0.077
urance+0.076
 Majesty+0.075
istence+0.074
Neg logit contributions
 water-0.011
.-0.006
 p-0.006
 was-0.004
 other-0.004
Token She
Token ID1375
Feature activation-1.35e+00

Pos logit contributions
 water+0.005
 was+0.004
.+0.004
 p+0.004
 said+0.004
Neg logit contributions
istent-0.012
osity-0.011
 Majesty-0.011
urance-0.010
sing-0.010
Token fire
Token ID2046
Feature activation+1.23e+00

Pos logit contributions
istent+0.029
urance+0.026
osity+0.026
 Majesty+0.026
 fault+0.025
Neg logit contributions
 water-0.012
P-0.010
 p-0.010
 decided-0.010
 away-0.010
Tokenman
Token ID805
Feature activation-2.34e+00

Pos logit contributions
 water+0.076
 p+0.065
 cool+0.061
 other+0.061
 sw+0.060
Neg logit contributions
istent-0.126
osity-0.114
urance-0.111
istence-0.107
 Majesty-0.107
Token for
Token ID329
Feature activation-2.00e+00

Pos logit contributions
istent+0.321
osity+0.299
urance+0.292
istence+0.285
 Majesty+0.285
Neg logit contributions
 water-0.069
.-0.049
 p-0.048
 other-0.045
 was-0.042
Token being
Token ID852
Feature activation-2.28e+00

Pos logit contributions
istent+0.183
osity+0.163
urance+0.158
 Majesty+0.150
istence+0.150
Neg logit contributions
 water-0.147
 p-0.129
 cool-0.124
 other-0.124
 sw-0.121
Token so
Token ID523
Feature activation+2.48e-01

Pos logit contributions
istent+0.244
osity+0.222
urance+0.219
 Majesty+0.211
 fault+0.210
Neg logit contributions
 water-0.114
 p-0.094
 other-0.085
 was-0.085
 sw-0.083
Token kind
Token ID1611
Feature activation+6.83e-02

Pos logit contributions
 water+0.013
 p+0.011
 was+0.010
P+0.010
 other+0.010
Neg logit contributions
istent-0.026
osity-0.024
urance-0.023
istence-0.022
 Majesty-0.022
Token and
Token ID290
Feature activation-6.40e-02

Pos logit contributions
 water+0.002
 p+0.002
 cool+0.001
 other+0.001
 sw+0.001
Neg logit contributions
istent-0.009
osity-0.008
urance-0.008
 fault-0.008
istence-0.008
Token helpful
Token ID7613
Feature activation+6.90e-01

Pos logit contributions
istent+0.006
osity+0.006
urance+0.006
istence+0.005
 Majesty+0.005
Neg logit contributions
 water-0.004
 p-0.004
 cool-0.003
 other-0.003
 sw-0.003
Token.
Token ID13
Feature activation+7.86e-02

Pos logit contributions
 water+0.012
 p+0.006
 cool+0.004
 other+0.004
 sw+0.003
Neg logit contributions
istent-0.101
osity-0.094
urance-0.093
 Majesty-0.090
istence-0.090
Token They
Token ID1119
Feature activation+3.94e-01

Pos logit contributions
 water+0.004
 p+0.004
 was+0.003
.+0.003
 cool+0.003
Neg logit contributions
istent-0.009
osity-0.008
urance-0.008
 Majesty-0.007
aries-0.007
Token hugged
Token ID41130
Feature activation+6.63e-01

Pos logit contributions
 water+0.017
 p+0.013
 cool+0.013
 cream+0.013
 other+0.012
Neg logit contributions
istent-0.044
osity-0.039
urance-0.039
istence-0.038
 Majesty-0.037
Token wet
Token ID9583
Feature activation+1.06e+00

Pos logit contributions
istent+0.206
osity+0.193
urance+0.188
istence+0.182
 Majesty+0.180
Neg logit contributions
 water-0.093
 p-0.076
 cool-0.074
.-0.071
 other-0.069
Token and
Token ID290
Feature activation-1.12e-02

Pos logit contributions
 water+0.044
 other+0.034
 cool+0.033
 p+0.033
 sw+0.033
Neg logit contributions
istent-0.122
urance-0.110
osity-0.110
 Majesty-0.107
 fault-0.107
Token red
Token ID2266
Feature activation-1.34e+00

Pos logit contributions
istent+0.001
osity+0.001
urance+0.001
 fault+0.001
istence+0.001
Neg logit contributions
 water-0.000
 p-0.000
 other-0.000
 cool-0.000
 sw-0.000
Token!
Token ID0
Feature activation-2.13e+00

Pos logit contributions
istent+0.164
osity+0.148
urance+0.148
 fault+0.146
 Majesty+0.144
Neg logit contributions
 water-0.047
 cool-0.035
 other-0.034
 sw-0.034
 p-0.033
Token That
Token ID1320
Feature activation-1.73e+00

Pos logit contributions
istent+0.181
osity+0.161
urance+0.156
 Majesty+0.152
istence+0.148
Neg logit contributions
 water-0.171
 p-0.155
.-0.150
 was-0.146
 cool-0.145
Token is
Token ID318
Feature activation-1.28e+00

Pos logit contributions
istent+0.213
osity+0.194
urance+0.191
 fault+0.190
 Majesty+0.184
Neg logit contributions
 water-0.061
 p-0.046
 cool-0.043
 other-0.041
 sw-0.041
Token not
Token ID407
Feature activation-8.39e-01

Pos logit contributions
istent+0.128
osity+0.115
urance+0.112
 fault+0.108
istence+0.108
Neg logit contributions
 water-0.080
 p-0.068
 other-0.065
 cool-0.064
 sw-0.064
Token nice
Token ID3621
Feature activation+2.12e-01

Pos logit contributions
istent+0.099
osity+0.091
urance+0.088
 fault+0.086
istence+0.085
Neg logit contributions
 water-0.038
 p-0.030
 other-0.028
 cool-0.027
 sw-0.027
Token!"
Token ID2474
Feature activation-1.05e+00

Pos logit contributions
 water+0.006
 p+0.005
 cool+0.004
 other+0.004
 sw+0.004
Neg logit contributions
istent-0.028
osity-0.026
urance-0.026
 fault-0.025
 Majesty-0.025
Token
Token ID198
Feature activation+2.32e-01

Pos logit contributions
istent+0.110
osity+0.099
urance+0.098
istence+0.094
 fault+0.094
Neg logit contributions
 water-0.057
 p-0.048
 sw-0.045
 cool-0.045
 other-0.044
Token
Token ID198
Feature activation+2.07e-01

Pos logit contributions
 water+0.011
 p+0.009
 sw+0.008
 cool+0.008
 other+0.008
Neg logit contributions
istent-0.027
osity-0.024
urance-0.024
istence-0.023
 fault-0.023
Token big
Token ID1263
Feature activation-7.54e-01

Pos logit contributions
istent+0.027
osity+0.024
urance+0.024
istence+0.023
arsh+0.022
Neg logit contributions
 water-0.014
 p-0.011
 other-0.011
 cool-0.011
 sw-0.010
Token cord
Token ID15050
Feature activation-1.18e+00

Pos logit contributions
istent+0.088
osity+0.080
urance+0.077
istence+0.074
aries+0.073
Neg logit contributions
 water-0.044
 p-0.037
 other-0.033
 cool-0.032
.-0.032
Token and
Token ID290
Feature activation+2.37e-02

Pos logit contributions
istent+0.162
osity+0.151
urance+0.149
 Majesty+0.144
istence+0.144
Neg logit contributions
 water-0.034
 p-0.024
.-0.021
 was-0.021
 other-0.018
Token hang
Token ID8181
Feature activation-2.67e-01

Pos logit contributions
 water+0.001
 p+0.001
 cool+0.001
 other+0.001
 was+0.001
Neg logit contributions
istent-0.003
osity-0.003
urance-0.003
istence-0.003
 fault-0.003
Token on
Token ID319
Feature activation+1.26e-01

Pos logit contributions
istent+0.033
osity+0.030
urance+0.029
 fault+0.029
istence+0.028
Neg logit contributions
 water-0.010
 p-0.008
 other-0.007
 cool-0.007
 sw-0.007
Token tight
Token ID5381
Feature activation-1.31e+00

Pos logit contributions
 water+0.004
 p+0.003
 other+0.003
 cool+0.003
.+0.003
Neg logit contributions
istent-0.017
osity-0.016
urance-0.015
 Majesty-0.015
istence-0.015
Token!
Token ID0
Feature activation-2.25e+00

Pos logit contributions
istent+0.189
osity+0.176
urance+0.172
 Majesty+0.168
istence+0.167
Neg logit contributions
 water-0.031
 p-0.019
.-0.015
 other-0.014
 cool-0.013
Token<|endoftext|>
Token ID50256
Feature activation+6.54e-01

Pos logit contributions
istent+0.248
osity+0.228
urance+0.220
 fault+0.218
 Majesty+0.214
Neg logit contributions
 water-0.123
 p-0.108
 was-0.106
.-0.106
 other-0.101
TokenOnce
Token ID7454
Feature activation+2.49e-01

Pos logit contributions
 water+0.028
 p+0.022
 cool+0.021
 other+0.020
 sw+0.020
Neg logit contributions
istent-0.078
osity-0.072
urance-0.071
istence-0.068
 Majesty-0.068
Token upon
Token ID2402
Feature activation-2.21e-01

Pos logit contributions
 water+0.014
 other+0.012
 p+0.012
 was+0.012
.+0.012
Neg logit contributions
istent-0.027
urance-0.024
osity-0.024
istence-0.023
 Majesty-0.023
Token a
Token ID257
Feature activation-4.30e-01

Pos logit contributions
istent+0.025
osity+0.023
urance+0.023
 fault+0.022
 Majesty+0.022
Neg logit contributions
 water-0.009
 p-0.008
 sw-0.007
 away-0.007
 cre-0.007
Token,
Token ID11
Feature activation-5.12e-01

Pos logit contributions
istent+0.089
osity+0.082
urance+0.080
istence+0.078
 Majesty+0.078
Neg logit contributions
 water-0.026
 p-0.020
 cool-0.018
 other-0.018
 sw-0.017
Token and
Token ID290
Feature activation+9.34e-02

Pos logit contributions
istent+0.060
osity+0.055
urance+0.054
istence+0.052
 Majesty+0.052
Neg logit contributions
 water-0.027
 p-0.023
 other-0.021
 cool-0.021
 was-0.020
Token sometimes
Token ID3360
Feature activation-5.58e-01

Pos logit contributions
 water+0.004
 p+0.003
 other+0.003
 cool+0.003
 was+0.003
Neg logit contributions
istent-0.011
osity-0.010
urance-0.010
istence-0.010
 Majesty-0.010
Token they
Token ID484
Feature activation+8.93e-01

Pos logit contributions
istent+0.078
osity+0.071
urance+0.070
istence+0.068
 Majesty+0.066
Neg logit contributions
 water-0.019
 p-0.014
 other-0.013
 was-0.013
.-0.012
Token fought
Token ID8350
Feature activation-7.20e-02

Pos logit contributions
 water+0.041
 p+0.033
 cool+0.030
 other+0.030
 sw+0.029
Neg logit contributions
istent-0.104
osity-0.095
urance-0.093
istence-0.089
 fault-0.089
Token over
Token ID625
Feature activation-1.12e+00

Pos logit contributions
istent+0.009
osity+0.008
urance+0.008
 Majesty+0.008
istence+0.008
Neg logit contributions
 water-0.003
 p-0.002
 cool-0.002
 other-0.002
 was-0.002
Token them
Token ID606
Feature activation+1.29e+00

Pos logit contributions
istent+0.142
osity+0.131
urance+0.128
 Majesty+0.124
istence+0.124
Neg logit contributions
 water-0.042
 p-0.032
 cool-0.029
 other-0.029
 sw-0.027
Token.
Token ID13
Feature activation+1.50e-01

Pos logit contributions
 water+0.022
 p+0.011
 other+0.008
 cool+0.008
.+0.008
Neg logit contributions
istent-0.192
osity-0.180
urance-0.176
 Majesty-0.172
istence-0.171
Token
Token ID198
Feature activation+2.64e-01

Pos logit contributions
 water+0.007
 p+0.005
 other+0.005
 was+0.005
 cool+0.005
Neg logit contributions
istent-0.018
osity-0.017
urance-0.017
istence-0.016
 Majesty-0.016
Token
Token ID198
Feature activation+2.54e-01

Pos logit contributions
 water+0.013
 p+0.010
 cool+0.009
 sw+0.009
 away+0.009
Neg logit contributions
istent-0.030
osity-0.027
urance-0.027
 fault-0.026
arsh-0.025
Token"
Token ID1
Feature activation+1.86e-01

Pos logit contributions
 water+0.016
 p+0.013
 away+0.013
 cool+0.013
 pe+0.012
Neg logit contributions
istent-0.025
osity-0.022
urance-0.021
arsh-0.021
istence-0.021
Token saw
Token ID2497
Feature activation+3.38e-01

Pos logit contributions
 water+0.067
 p+0.050
 cool+0.050
 cream+0.050
 other+0.049
Neg logit contributions
istent-0.180
osity-0.164
urance-0.163
 Majesty-0.162
arsh-0.156
Token a
Token ID257
Feature activation-1.10e-01

Pos logit contributions
 water+0.015
 p+0.012
 away+0.012
 cre+0.011
 sw+0.011
Neg logit contributions
istent-0.035
osity-0.033
 Majesty-0.032
urance-0.032
 fault-0.032
Token little
Token ID1310
Feature activation-6.62e-01

Pos logit contributions
istent+0.013
osity+0.012
urance+0.012
 Majesty+0.012
istence+0.012
Neg logit contributions
 water-0.004
 p-0.003
 other-0.003
 cool-0.003
 sw-0.003
Token boy
Token ID2933
Feature activation+6.64e-02

Pos logit contributions
istent+0.078
osity+0.072
urance+0.070
 Majesty+0.068
istence+0.067
Neg logit contributions
 water-0.030
 p-0.023
 cool-0.022
 other-0.022
 sw-0.021
Token handing
Token ID22786
Feature activation-4.95e-01

Pos logit contributions
 water+0.004
 p+0.004
 cool+0.004
 other+0.004
 sw+0.003
Neg logit contributions
istent-0.006
osity-0.006
urance-0.006
istence-0.005
 Majesty-0.005
Token out
Token ID503
Feature activation-2.11e+00

Pos logit contributions
istent+0.045
urance+0.040
osity+0.040
 fault+0.038
isdom+0.038
Neg logit contributions
 water-0.029
 p-0.026
 cool-0.024
 cre-0.024
 sw-0.024
Token muff
Token ID27563
Feature activation+2.28e-01

Pos logit contributions
istent+0.260
osity+0.241
urance+0.236
 Majesty+0.228
 fault+0.227
Neg logit contributions
 water-0.080
 p-0.061
 other-0.054
 cool-0.054
 sw-0.053
Tokenins
Token ID1040
Feature activation+3.31e-01

Pos logit contributions
 water+0.016
 cool+0.014
 p+0.014
 sw+0.014
 went+0.013
Neg logit contributions
istent-0.019
osity-0.017
isdom-0.016
 fault-0.016
arsh-0.016
Token.
Token ID13
Feature activation+2.70e-01

Pos logit contributions
 water+0.011
 p+0.008
 cool+0.007
 other+0.007
 sw+0.007
Neg logit contributions
istent-0.042
osity-0.039
urance-0.038
 fault-0.037
istence-0.037
Token The
Token ID383
Feature activation-2.59e-01

Pos logit contributions
 water+0.018
 p+0.015
 was+0.015
.+0.014
 cool+0.014
Neg logit contributions
istent-0.028
osity-0.026
 Majesty-0.025
urance-0.025
 fault-0.025
Token bear
Token ID6842
Feature activation-3.97e-01

Pos logit contributions
istent+0.025
 Majesty+0.024
urance+0.023
osity+0.023
sing+0.022
Neg logit contributions
P-0.012
 water-0.011
 away-0.010
 decided-0.010
S-0.009
Token loved
Token ID6151
Feature activation+1.59e+00

Pos logit contributions
 water+0.008
 p+0.006
 other+0.006
 sw+0.005
 cool+0.005
Neg logit contributions
istent-0.018
osity-0.017
urance-0.016
istence-0.016
 Majesty-0.016
Token to
Token ID284
Feature activation+2.19e-01

Pos logit contributions
 water+0.068
 p+0.053
 other+0.048
 cool+0.048
 sw+0.046
Neg logit contributions
istent-0.197
osity-0.181
urance-0.177
istence-0.171
 Majesty-0.171
Token run
Token ID1057
Feature activation-1.21e+00

Pos logit contributions
 water+0.010
 p+0.008
 cool+0.007
 other+0.007
 sw+0.007
Neg logit contributions
istent-0.027
osity-0.025
urance-0.024
 fault-0.023
istence-0.023
Token around
Token ID1088
Feature activation+5.28e-01

Pos logit contributions
istent+0.131
urance+0.117
istence+0.114
aries+0.112
osity+0.111
Neg logit contributions
 water-0.052
 cream-0.041
 p-0.040
 sw-0.039
 pe-0.039
Token.
Token ID13
Feature activation+2.28e-01

Pos logit contributions
 water+0.013
 p+0.008
 cool+0.007
 other+0.006
 sw+0.006
Neg logit contributions
istent-0.074
osity-0.068
urance-0.067
istence-0.065
 Majesty-0.065
Token She
Token ID1375
Feature activation-1.16e+00

Pos logit contributions
 water+0.015
.+0.013
 p+0.013
 other+0.013
 was+0.013
Neg logit contributions
istent-0.024
osity-0.022
 Majesty-0.020
urance-0.020
istence-0.020
Token loved
Token ID6151
Feature activation+1.59e+00

Pos logit contributions
istent+0.146
osity+0.135
urance+0.132
istence+0.127
 Majesty+0.127
Neg logit contributions
 water-0.045
 p-0.035
 cool-0.032
 other-0.032
 sw-0.030
Token adventure
Token ID8855
Feature activation-1.22e+00

Pos logit contributions
 water+0.068
 p+0.054
 other+0.049
 cool+0.048
 was+0.046
Neg logit contributions
istent-0.208
osity-0.189
urance-0.187
 Majesty-0.180
istence-0.180
Token and
Token ID290
Feature activation+1.85e-01

Pos logit contributions
istent+0.159
osity+0.148
urance+0.144
 Majesty+0.140
istence+0.139
Neg logit contributions
 water-0.043
 p-0.032
 cool-0.029
 other-0.029
 was-0.027
Token being
Token ID852
Feature activation-2.27e+00

Pos logit contributions
 water+0.009
 p+0.007
 other+0.007
 was+0.007
 cool+0.007
Neg logit contributions
istent-0.022
osity-0.021
urance-0.020
istence-0.019
 fault-0.019
Token outside
Token ID2354
Feature activation+6.48e-01

Pos logit contributions
istent+0.270
osity+0.251
urance+0.244
 Majesty+0.237
istence+0.235
Neg logit contributions
 water-0.096
 p-0.073
 other-0.067
 cool-0.065
 sw-0.064
Token.
Token ID13
Feature activation+7.04e-02

Pos logit contributions
istent+0.083
osity+0.077
urance+0.076
istence+0.074
 Majesty+0.074
Neg logit contributions
 water-0.012
 p-0.006
 other-0.004
 cool-0.004
.-0.004
Token One
Token ID1881
Feature activation-8.45e-01

Pos logit contributions
 water+0.004
 p+0.004
 was+0.004
.+0.003
 other+0.003
Neg logit contributions
istent-0.008
osity-0.007
 fault-0.007
urance-0.007
 Majesty-0.006
Token day
Token ID1110
Feature activation+5.89e-01

Pos logit contributions
istent+0.095
osity+0.087
urance+0.084
 fault+0.081
istence+0.081
Neg logit contributions
 water-0.039
 p-0.032
 cool-0.030
 other-0.029
 sw-0.029
Token,
Token ID11
Feature activation-2.26e-01

Pos logit contributions
 water+0.028
 p+0.023
 cool+0.021
 other+0.021
 sw+0.021
Neg logit contributions
istent-0.068
osity-0.062
urance-0.061
 Majesty-0.058
istence-0.058
Token Wh
Token ID854
Feature activation-1.23e+00

Pos logit contributions
istent+0.027
osity+0.024
urance+0.024
istence+0.023
 Majesty+0.023
Neg logit contributions
 water-0.011
 p-0.009
 other-0.008
 cool-0.008
 was-0.008
Tokenisk
Token ID1984
Feature activation-5.37e+00

Pos logit contributions
istent+0.062
osity+0.051
urance+0.046
 Majesty+0.044
istence+0.042
Neg logit contributions
 water-0.139
 p-0.130
 was-0.128
.-0.126
 other-0.125
Tokeners
Token ID364
Feature activation+9.57e-01

Pos logit contributions
istent+0.561
osity+0.527
urance+0.515
aries+0.500
 Majesty+0.496
Neg logit contributions
 water-0.282
 p-0.240
 cool-0.220
 sw-0.209
 pe-0.204
Token saw
Token ID2497
Feature activation+2.54e-01

Pos logit contributions
 water+0.027
 p+0.019
 was+0.017
 went+0.016
 sw+0.016
Neg logit contributions
istent-0.133
osity-0.125
urance-0.121
istence-0.118
 fault-0.118
Token a
Token ID257
Feature activation-2.29e-01

Pos logit contributions
 water+0.009
 p+0.007
 cool+0.006
 other+0.006
 sw+0.006
Neg logit contributions
istent-0.032
osity-0.030
urance-0.029
 Majesty-0.028
istence-0.028
Token bird
Token ID6512
Feature activation-8.00e-01

Pos logit contributions
istent+0.027
osity+0.025
urance+0.024
 Majesty+0.024
istence+0.024
Neg logit contributions
 water-0.010
 p-0.008
 other-0.007
 cool-0.007
 sw-0.007
Token in
Token ID287
Feature activation+8.06e-01

Pos logit contributions
istent+0.084
osity+0.076
urance+0.073
istence+0.070
 Majesty+0.070
Neg logit contributions
 water-0.045
 p-0.036
 other-0.036
 cool-0.036
 cream-0.033
TokenNo
Token ID2949
Feature activation+8.82e-01

Pos logit contributions
 water+0.001
 p+0.001
 away+0.001
 cool+0.001
.+0.001
Neg logit contributions
istent-0.002
osity-0.002
istence-0.002
urance-0.002
 fault-0.002
Token,
Token ID11
Feature activation-6.58e-01

Pos logit contributions
 water+0.038
 p+0.031
 other+0.028
 cool+0.026
.+0.026
Neg logit contributions
istent-0.111
osity-0.104
urance-0.099
istence-0.097
aries-0.097
Token it
Token ID340
Feature activation+1.15e+00

Pos logit contributions
istent+0.073
osity+0.066
urance+0.065
istence+0.062
 Majesty+0.061
Neg logit contributions
 water-0.038
 p-0.033
 other-0.031
 cool-0.031
 sw-0.030
Token is
Token ID318
Feature activation-1.39e+00

Pos logit contributions
 water+0.060
 p+0.050
 cool+0.047
 other+0.046
 was+0.045
Neg logit contributions
istent-0.129
osity-0.118
urance-0.115
istence-0.111
 Majesty-0.111
Token your
Token ID534
Feature activation-4.40e-01

Pos logit contributions
istent+0.147
osity+0.135
urance+0.130
 Majesty+0.125
istence+0.124
Neg logit contributions
 water-0.084
 p-0.071
 cool-0.069
 other-0.067
.-0.065
Token fault
Token ID8046
Feature activation-6.34e+00

Pos logit contributions
istent+0.027
osity+0.023
urance+0.021
istence+0.020
aries+0.019
Neg logit contributions
 water-0.047
 p-0.044
 other-0.042
 cool-0.042
.-0.041
Token,
Token ID11
Feature activation-6.75e-01

Pos logit contributions
istent+0.838
osity+0.795
urance+0.767
istence+0.751
 Majesty+0.740
Neg logit contributions
 water-0.209
 p-0.159
.-0.153
 other-0.139
 cool-0.132
Token you
Token ID345
Feature activation-5.82e-01

Pos logit contributions
istent+0.082
osity+0.075
urance+0.074
istence+0.070
 Majesty+0.069
Neg logit contributions
 water-0.035
 p-0.029
 other-0.027
 cool-0.027
 sw-0.026
Token drove
Token ID10357
Feature activation+1.28e-01

Pos logit contributions
istent+0.063
osity+0.057
urance+0.055
istence+0.053
 Majesty+0.053
Neg logit contributions
 water-0.033
 p-0.028
 cool-0.026
 other-0.026
 sw-0.025
Token too
Token ID1165
Feature activation+5.98e-01

Pos logit contributions
 water+0.004
 p+0.003
 cool+0.002
 other+0.002
 sw+0.002
Neg logit contributions
istent-0.017
osity-0.016
urance-0.015
 Majesty-0.015
istence-0.015
Token fast
Token ID3049
Feature activation-5.60e-01

Pos logit contributions
 water+0.026
 p+0.021
 sw+0.019
 cool+0.018
 other+0.018
Neg logit contributions
istent-0.070
osity-0.064
urance-0.063
 fault-0.061
istence-0.061
Token and
Token ID290
Feature activation+1.42e-01

Pos logit contributions
 water+0.019
 p+0.014
 cool+0.012
 other+0.012
 sw+0.012
Neg logit contributions
istent-0.068
osity-0.063
urance-0.062
 Majesty-0.060
istence-0.060
Token quickly
Token ID2952
Feature activation-4.81e-02

Pos logit contributions
 water+0.006
 other+0.004
 cool+0.004
 p+0.004
P+0.004
Neg logit contributions
istent-0.016
osity-0.015
urance-0.014
 Majesty-0.014
istence-0.014
Token started
Token ID2067
Feature activation+7.09e-01

Pos logit contributions
istent+0.006
osity+0.005
urance+0.005
istence+0.005
 Majesty+0.005
Neg logit contributions
 water-0.002
 other-0.002
 p-0.002
 cool-0.002
P-0.001
Token to
Token ID284
Feature activation+8.66e-02

Pos logit contributions
 water+0.045
 p+0.040
 pe+0.037
 sw+0.036
.+0.036
Neg logit contributions
istent-0.076
osity-0.068
urance-0.066
istence-0.064
 Majesty-0.064
Token m
Token ID285
Feature activation+9.78e-01

Pos logit contributions
 water+0.005
 p+0.004
 cool+0.004
 other+0.004
 sw+0.004
Neg logit contributions
istent-0.009
osity-0.008
urance-0.008
 Majesty-0.008
istence-0.008
Tokenunch
Token ID3316
Feature activation-4.50e+00

Pos logit contributions
 water+0.110
 p+0.100
.+0.097
 was+0.097
 cool+0.097
Neg logit contributions
istent-0.042
osity-0.040
 Majesty-0.035
 fault-0.034
urance-0.033
Token it
Token ID340
Feature activation+9.86e-01

Pos logit contributions
istent+0.506
osity+0.457
urance+0.436
 fault+0.430
arsh+0.428
Neg logit contributions
 water-0.201
 p-0.171
 cool-0.157
 sw-0.147
 other-0.145
Token all
Token ID477
Feature activation+3.24e-01

Pos logit contributions
 water+0.037
 p+0.027
 other+0.026
 sw+0.025
 cool+0.023
Neg logit contributions
istent-0.120
urance-0.109
osity-0.108
istence-0.103
arsh-0.103
Token up
Token ID510
Feature activation-9.50e-01

Pos logit contributions
 water+0.018
P+0.017
 other+0.016
S+0.015
 p+0.015
Neg logit contributions
istent-0.030
osity-0.027
 fault-0.026
urance-0.025
istence-0.025
Token.
Token ID13
Feature activation+1.50e-01

Pos logit contributions
istent+0.112
osity+0.099
urance+0.098
 fault+0.097
istence+0.096
Neg logit contributions
 water-0.034
 other-0.024
 p-0.023
P-0.023
 cool-0.022
Token He
Token ID679
Feature activation+3.31e-02

Pos logit contributions
 water+0.009
 was+0.008
 p+0.007
.+0.007
 cool+0.007
Neg logit contributions
istent-0.016
osity-0.015
 fault-0.014
 Majesty-0.014
aries-0.014
Token it
Token ID340
Feature activation+1.10e+00

Pos logit contributions
 water+0.002
 p+0.002
 other+0.002
 cool+0.002
 was+0.002
Neg logit contributions
istent-0.006
osity-0.005
urance-0.005
 Majesty-0.005
istence-0.005
Token was
Token ID373
Feature activation-3.86e-03

Pos logit contributions
 water+0.023
 p+0.012
 cool+0.009
 other+0.009
 sw+0.008
Neg logit contributions
istent-0.156
osity-0.144
urance-0.143
 fault-0.138
istence-0.137
Token Tim
Token ID5045
Feature activation+8.16e-01

Pos logit contributions
istent+0.000
osity+0.000
urance+0.000
 fault+0.000
istence+0.000
Neg logit contributions
 water-0.000
 p-0.000
 other-0.000
 cool-0.000
 sw-0.000
Tokenmy
Token ID1820
Feature activation-1.63e+00

Pos logit contributions
 water+0.045
.+0.040
 p+0.039
 was+0.039
 other+0.039
Neg logit contributions
istent-0.089
osity-0.082
urance-0.079
 Majesty-0.079
istence-0.078
Token's
Token ID338
Feature activation-2.33e+00

Pos logit contributions
istent+0.194
osity+0.183
 Majesty+0.176
urance+0.176
istence+0.173
Neg logit contributions
 water-0.075
 was-0.066
.-0.065
 p-0.061
 other-0.061
Token fault
Token ID8046
Feature activation-6.48e+00

Pos logit contributions
istent+0.209
osity+0.186
urance+0.180
istence+0.172
 Majesty+0.170
Neg logit contributions
 water-0.176
 p-0.155
 cool-0.148
 other-0.148
 was-0.144
Token but
Token ID475
Feature activation-2.86e-01

Pos logit contributions
istent+0.886
osity+0.842
 Majesty+0.842
urance+0.829
isdom+0.813
Neg logit contributions
 water-0.179
.-0.161
 p-0.132
 in-0.121
 other-0.120
Token Tim
Token ID5045
Feature activation+8.08e-01

Pos logit contributions
istent+0.034
osity+0.030
urance+0.030
 Majesty+0.029
istence+0.029
Neg logit contributions
 water-0.014
 p-0.012
 other-0.011
 cool-0.011
 was-0.011
Tokenmy
Token ID1820
Feature activation-1.64e+00

Pos logit contributions
 water+0.047
 was+0.042
 p+0.042
.+0.040
 cool+0.039
Neg logit contributions
istent-0.085
osity-0.079
urance-0.076
 Majesty-0.075
istence-0.074
Token felt
Token ID2936
Feature activation+4.90e-02

Pos logit contributions
istent+0.210
osity+0.194
urance+0.191
 Majesty+0.184
istence+0.184
Neg logit contributions
 water-0.058
 p-0.043
 cool-0.039
 other-0.039
 sw-0.037
Token guilty
Token ID6717
Feature activation+1.82e+00

Pos logit contributions
 water+0.003
 p+0.002
 cre+0.002
 sw+0.002
 pe+0.002
Neg logit contributions
istent-0.005
urance-0.004
 fault-0.004
osity-0.004
istence-0.004
Token,
Token ID11
Feature activation-2.56e-01

Pos logit contributions
 water+0.028
 p+0.023
 other+0.021
 cool+0.021
 was+0.020
Neg logit contributions
istent-0.075
osity-0.069
urance-0.067
istence-0.065
 Majesty-0.065
Token Riley
Token ID22637
Feature activation-1.25e+00

Pos logit contributions
istent+0.030
osity+0.027
urance+0.027
istence+0.026
 fault+0.026
Neg logit contributions
 water-0.013
 p-0.011
 other-0.010
 cool-0.010
 was-0.009
Token saw
Token ID2497
Feature activation+3.15e-01

Pos logit contributions
istent+0.166
osity+0.154
urance+0.151
istence+0.146
 Majesty+0.145
Neg logit contributions
 water-0.040
 p-0.029
 cool-0.025
 other-0.025
 sw-0.024
Token a
Token ID257
Feature activation-1.38e-01

Pos logit contributions
 water+0.011
 p+0.008
 other+0.008
 cool+0.007
 was+0.007
Neg logit contributions
istent-0.042
osity-0.039
urance-0.038
istence-0.037
 Majesty-0.036
Token bird
Token ID6512
Feature activation-7.08e-01

Pos logit contributions
istent+0.017
osity+0.015
urance+0.015
istence+0.014
 Majesty+0.014
Neg logit contributions
 water-0.006
 p-0.005
 cool-0.004
 other-0.004
 sw-0.004
Token soaring
Token ID32376
Feature activation-4.60e+00

Pos logit contributions
istent+0.073
osity+0.066
urance+0.064
istence+0.061
 Majesty+0.061
Neg logit contributions
 water-0.042
 p-0.036
 cool-0.034
 other-0.034
 sw-0.033
Token through
Token ID832
Feature activation+3.82e-01

Pos logit contributions
istent+0.494
osity+0.460
istence+0.426
urance+0.421
 fault+0.413
Neg logit contributions
 water-0.228
 p-0.189
 other-0.180
 cream-0.173
 cool-0.169
Token the
Token ID262
Feature activation-2.24e-01

Pos logit contributions
 water+0.013
 p+0.010
 cool+0.009
 sw+0.009
 other+0.009
Neg logit contributions
istent-0.047
osity-0.043
urance-0.043
istence-0.041
 Majesty-0.041
Token sky
Token ID6766
Feature activation-9.71e-01

Pos logit contributions
istent+0.020
osity+0.018
urance+0.017
istence+0.017
 Majesty+0.017
Neg logit contributions
 water-0.014
 p-0.012
 cream-0.012
 sw-0.012
 decided-0.012
Token and
Token ID290
Feature activation+5.15e-02

Pos logit contributions
istent+0.142
osity+0.133
urance+0.131
 Majesty+0.128
istence+0.127
Neg logit contributions
 water-0.018
 p-0.009
 cool-0.006
 other-0.006
.-0.006
Token realised
Token ID19169
Feature activation+1.34e+00

Pos logit contributions
 water+0.002
 p+0.002
 was+0.001
 sw+0.001
 other+0.001
Neg logit contributions
istent-0.007
urance-0.006
osity-0.006
 fault-0.006
istence-0.006