TOP ACTIVATIONS
MAX = 7.754

and white cloth and carefully se wed them together .
own two hands . She se wed it with bright colors
a needle and thread and se wed Teddy 's eye back
began to sew . She se wed the piece of cloth
She cut and se wed the fabric and put
big hill . She would even pretend to fly with the
paint pot . She would even mix hot chocolate when she
a needle and thread and se wed a patch on Patch
a needle and thread and se wed the t eddy bear
to pick up toys and even l icked the dust off
of fun . He would even try to make up silly
needle and thread . She se wed a hole in the
blue berries . She would even eat them for breakfast ,
the t eddy bear and se wed up the hole in
healthy things . He would even share these snacks with his
and some buttons . I se wed them together and stuffed
this show ? You can even perform in front of all
loved taking baths and would even ask her mom my if
needle and thread and carefully se wed Mr . Fl uffy
forg ave Tim my and even gave him a reward for

MIN ACTIVATIONS
MIN = -7.186

around the hallway , the dining room and the bedroom .
loud laugh echoed around the chamber . " Welcome visitors ,"
came from deep inside the chamber . Max jumped with fright
to the edge of the pit and leaned over to examine
strange noise coming from the living room . She got scared
loud noise came from the living room . Billy was scared
's voice from inside the cabinet . He wanted to surprise
loud noise came from the living room . It was Daddy
at the edge of the pit . The lion was angry
balance and fell into the pit . He screamed and cried
They ran out of the chamber and back to their room
loud noise coming from the living room . They went to
could see was the deep pit . Mike
a loud noise from the living room . He ran to
and gro oving around the living room . And they had
a big box in the living room . It has a
ice cream out of the freezer again . They also learned
Tom and came to the living room . She saw Lily
ily ran back to the cabinet and looked again . She
and found them behind the cabinet . She was not happy

INTERVAL 4.019 - 7.754
CONTAINS 0.894%

. She gathered a hammer and her toy tool box ,
Christmas ever . <|endoftext|> Tom and Lily were having lunch with
of all . <|endoftext|> Tom and Lily are young twins who
forg ave him and they all played together with Lily 's
mom sat on a bench and ate the big ice cream

INTERVAL 0.284 - 4.019
CONTAINS 42.992%

seen snow before . They drove for a long
could . They passed many kids . They were almost at
mom about their dream . Mom smiled and hugged
trees . He noticed a rabbit hopping around . He was
scared ! Then the hunter noticed her and smiled . He

INTERVAL -3.451 - 0.284
CONTAINS 54.273%

little girl named Lucy . She was only three years old
woman didn 't know what to do , so they decided
Qu ack was sad because he wanted to swim in the
and Tommy â s hat flew off . His
Lily was sad and cried because all her hard work was

INTERVAL -7.186 - -3.451
CONTAINS 1.841%

hurt them . We have to be careful with it ,"
he just stood in the hallway . The noise was strange
so difficult to make the bed ! â
woods . It was cold outside , but Jimmy still stayed
, they bring their bikes to the park and ride around
Token and
Token ID290
Feature activation+4.23e+00

Pos logit contributions
ercise+0.114
ams+0.103
isdom+0.102
ets+0.101
reci+0.097
Neg logit contributions
 Ana-0.113
 El-0.108
 Pen-0.106
 Mir-0.104
 Fl-0.101
Token white
Token ID2330
Feature activation+3.85e+00

Pos logit contributions
ets+0.124
ercise+0.124
ock+0.123
ams+0.123
isdom+0.114
Neg logit contributions
 Ana-0.099
 Pen-0.092
 Mir-0.091
 El-0.088
 Mil-0.084
Token cloth
Token ID16270
Feature activation+2.26e+00

Pos logit contributions
ercise+0.087
ams+0.084
ets+0.084
ock+0.080
isdom+0.076
Neg logit contributions
 Ana-0.116
 Pen-0.110
 Mir-0.108
 El-0.108
 Megan-0.103
Token and
Token ID290
Feature activation+3.95e+00

Pos logit contributions
ets+0.048
ercise+0.047
ams+0.047
ock+0.044
isdom+0.039
Neg logit contributions
 Ana-0.072
 Pen-0.069
 Mir-0.066
 Megan-0.065
 El-0.064
Token carefully
Token ID7773
Feature activation+1.95e+00

Pos logit contributions
ercise+0.110
ets+0.109
ams+0.108
ock+0.105
isdom+0.097
Neg logit contributions
 Ana-0.099
 Pen-0.094
 Mir-0.090
 El-0.088
 Megan-0.087
Token se
Token ID384
Feature activation+7.75e+00

Pos logit contributions
ercise+0.054
ets+0.054
ams+0.053
ock+0.050
isdom+0.047
Neg logit contributions
 Ana-0.049
 Pen-0.047
 Megan-0.044
 Mir-0.044
 El-0.043
Tokenwed
Token ID19103
Feature activation+2.87e+00

Pos logit contributions
weet+0.137
 jets+0.132
 since+0.128
elling+0.125
icated+0.118
Neg logit contributions
 Ana-0.173
 Megan-0.170
 plun-0.169
 Mir-0.169
 Mil-0.165
Token them
Token ID606
Feature activation+1.01e+00

Pos logit contributions
ercise+0.064
ets+0.063
ams+0.063
ock+0.059
isdom+0.054
Neg logit contributions
 Ana-0.088
 Pen-0.085
 Mir-0.081
 Megan-0.080
 El-0.079
Token together
Token ID1978
Feature activation+2.16e+00

Pos logit contributions
ets+0.023
ercise+0.022
ams+0.022
ock+0.021
isdom+0.019
Neg logit contributions
 Ana-0.031
 Pen-0.030
 Mir-0.028
 Megan-0.028
 El-0.028
Token.
Token ID13
Feature activation+1.00e+00

Pos logit contributions
ets+0.048
ercise+0.048
ams+0.048
ock+0.045
isdom+0.040
Neg logit contributions
 Ana-0.065
 Pen-0.063
 Mir-0.060
 Megan-0.059
 El-0.058
Token
Token ID198
Feature activation+1.14e+00

Pos logit contributions
ercise+0.027
ets+0.027
ams+0.026
ock+0.025
isdom+0.023
Neg logit contributions
 Ana-0.026
 Pen-0.025
 Mir-0.024
 Megan-0.024
 El-0.023
Token own
Token ID898
Feature activation+1.07e+00

Pos logit contributions
ercise+0.014
ets+0.014
ams+0.014
ock+0.013
isdom+0.012
Neg logit contributions
 Ana-0.013
 Pen-0.013
 Mir-0.012
 Megan-0.012
 El-0.012
Token two
Token ID734
Feature activation+2.53e+00

Pos logit contributions
ets+0.029
ercise+0.028
ams+0.028
ock+0.027
isdom+0.025
Neg logit contributions
 Ana-0.027
 Pen-0.026
 plun-0.024
 El-0.024
 Ell-0.024
Token hands
Token ID2832
Feature activation+3.25e+00

Pos logit contributions
ercise+0.067
ets+0.065
ams+0.065
ock+0.062
isdom+0.060
Neg logit contributions
 Ana-0.066
 Pen-0.063
 Megan-0.059
 El-0.059
 Mir-0.059
Token.
Token ID13
Feature activation+1.43e+00

Pos logit contributions
ercise+0.073
ets+0.071
ams+0.070
ock+0.066
isdom+0.062
Neg logit contributions
 Ana-0.098
 Pen-0.095
 Megan-0.090
 Mir-0.090
 El-0.089
Token She
Token ID1375
Feature activation-3.53e-01

Pos logit contributions
ercise+0.034
ams+0.034
ets+0.034
ock+0.032
isdom+0.030
Neg logit contributions
 Ana-0.039
 Pen-0.038
 plun-0.036
 gen-0.036
 Mir-0.035
Token se
Token ID384
Feature activation+7.50e+00

Pos logit contributions
 Ana+0.009
 Pen+0.008
 Mir+0.008
 Megan+0.008
 El+0.008
Neg logit contributions
ercise-0.010
ets-0.010
ams-0.010
ock-0.009
isdom-0.009
Tokenwed
Token ID19103
Feature activation+2.97e+00

Pos logit contributions
ercise+0.122
 jets+0.121
 pads+0.110
weet+0.110
ully+0.105
Neg logit contributions
 Ana-0.206
 Megan-0.201
 gen-0.196
illi-0.191
 Mir-0.190
Token it
Token ID340
Feature activation+3.64e-01

Pos logit contributions
ercise+0.074
ets+0.074
ams+0.072
ock+0.067
isdom+0.066
Neg logit contributions
 Ana-0.084
 Pen-0.080
 Mir-0.077
 El-0.076
 Megan-0.075
Token with
Token ID351
Feature activation+1.01e+00

Pos logit contributions
ercise+0.008
ets+0.008
ams+0.008
ock+0.008
isdom+0.007
Neg logit contributions
 Ana-0.011
 Pen-0.011
 Mir-0.010
 Megan-0.010
 El-0.010
Token bright
Token ID6016
Feature activation+3.81e+00

Pos logit contributions
ets+0.028
ercise+0.028
ams+0.028
ock+0.026
isdom+0.025
Neg logit contributions
 Ana-0.026
 Pen-0.024
 El-0.023
 Mir-0.023
 Ell-0.023
Token colors
Token ID7577
Feature activation+2.94e+00

Pos logit contributions
ercise+0.108
ets+0.100
isdom+0.097
ams+0.094
earned+0.092
Neg logit contributions
 Ana-0.091
 Ell-0.090
 El-0.088
 Mir-0.084
 Pen-0.083
Token a
Token ID257
Feature activation+1.67e+00

Pos logit contributions
ercise+0.069
ams+0.069
ets+0.069
ock+0.064
isdom+0.061
Neg logit contributions
 Ana-0.078
 Pen-0.074
 Mir-0.070
 El-0.069
 Megan-0.069
Token needle
Token ID17598
Feature activation+1.28e+00

Pos logit contributions
ercise+0.044
ets+0.043
ock+0.042
ams+0.041
weet+0.038
Neg logit contributions
 Ana-0.043
 Pen-0.042
 Mir-0.040
 Megan-0.040
 El-0.038
Token and
Token ID290
Feature activation+4.20e+00

Pos logit contributions
ercise+0.029
ams+0.028
ets+0.026
isdom+0.024
ock+0.024
Neg logit contributions
 Ana-0.039
 Pen-0.039
 El-0.036
 Mir-0.036
stack-0.036
Token thread
Token ID4704
Feature activation+2.50e+00

Pos logit contributions
ets+0.122
ams+0.122
ercise+0.120
ock+0.115
isdom+0.108
Neg logit contributions
 Ana-0.100
 Pen-0.096
 Mir-0.090
 El-0.088
 plun-0.087
Token and
Token ID290
Feature activation+3.86e+00

Pos logit contributions
ets+0.048
ercise+0.048
ams+0.047
ock+0.044
isdom+0.039
Neg logit contributions
 Ana-0.084
 Pen-0.081
 Mir-0.077
 Megan-0.077
 El-0.076
Token se
Token ID384
Feature activation+7.47e+00

Pos logit contributions
ets+0.110
ams+0.110
ercise+0.110
ock+0.104
isdom+0.098
Neg logit contributions
 Ana-0.094
 Pen-0.089
 Mir-0.084
 El-0.082
 Megan-0.082
Tokenwed
Token ID19103
Feature activation+2.65e+00

Pos logit contributions
 jets+0.129
weet+0.126
 since+0.118
ercise+0.113
ully+0.112
Neg logit contributions
 Ana-0.174
 Megan-0.173
 plun-0.171
 Mir-0.163
 Pen-0.161
Token Teddy
Token ID29345
Feature activation+1.78e+00

Pos logit contributions
ercise+0.060
ets+0.060
ams+0.059
ock+0.056
isdom+0.050
Neg logit contributions
 Ana-0.080
 Pen-0.077
 Megan-0.073
 Mir-0.072
 El-0.071
Token's
Token ID338
Feature activation+3.50e-01

Pos logit contributions
ets+0.037
ercise+0.036
ams+0.035
ock+0.033
 pads+0.029
Neg logit contributions
 Ana-0.057
 Pen-0.055
 Mir-0.053
 Megan-0.053
 El-0.052
Token eye
Token ID4151
Feature activation+7.54e-01

Pos logit contributions
ercise+0.010
ets+0.010
ams+0.010
ock+0.009
isdom+0.008
Neg logit contributions
 Ana-0.009
 Pen-0.008
 Megan-0.008
 Mir-0.008
 El-0.008
Token back
Token ID736
Feature activation+1.08e+00

Pos logit contributions
ercise+0.020
ams+0.020
ets+0.019
ock+0.019
isdom+0.018
Neg logit contributions
 Ana-0.019
 Pen-0.019
 Mir-0.018
 El-0.017
 Megan-0.017
Token began
Token ID2540
Feature activation+7.80e-01

Pos logit contributions
ets+0.019
ams+0.019
ercise+0.019
ock+0.017
ear+0.016
Neg logit contributions
 Ana-0.020
 Pen-0.019
stack-0.018
 Jenkins-0.018
 Megan-0.018
Token to
Token ID284
Feature activation-2.53e+00

Pos logit contributions
ercise+0.012
ets+0.012
ams+0.012
ock+0.010
isdom+0.009
Neg logit contributions
 Ana-0.029
 Pen-0.028
 Megan-0.027
 Mir-0.026
 gen-0.026
Token sew
Token ID34249
Feature activation+1.90e+00

Pos logit contributions
 Ana+0.062
 Pen+0.060
 Mir+0.056
 Megan+0.055
 El+0.055
Neg logit contributions
ercise-0.072
ets-0.072
ams-0.071
ock-0.068
isdom-0.063
Token.
Token ID13
Feature activation+1.44e+00

Pos logit contributions
ets+0.038
ams+0.036
ercise+0.036
ock+0.035
les+0.031
Neg logit contributions
 Ana-0.060
 Pen-0.060
stack-0.056
 Megan-0.056
 gen-0.056
Token She
Token ID1375
Feature activation-5.08e-01

Pos logit contributions
ercise+0.035
ets+0.035
ams+0.034
ock+0.032
ear+0.030
Neg logit contributions
 Ana-0.039
 Pen-0.037
 gen-0.036
 plun-0.036
 Mir-0.035
Token se
Token ID384
Feature activation+7.43e+00

Pos logit contributions
 Ana+0.013
 Pen+0.012
 Megan+0.011
 Mir+0.011
 plun+0.011
Neg logit contributions
ets-0.014
ercise-0.014
ams-0.014
ock-0.013
vious-0.012
Tokenwed
Token ID19103
Feature activation+2.86e+00

Pos logit contributions
 jets+0.130
ercise+0.123
 pads+0.119
weet+0.116
 motorcycles+0.113
Neg logit contributions
 Megan-0.190
 Ana-0.188
illi-0.178
 Pen-0.171
 Ell-0.169
Token the
Token ID262
Feature activation+8.67e-01

Pos logit contributions
ercise+0.066
ets+0.064
ams+0.064
ock+0.059
isdom+0.056
Neg logit contributions
 Ana-0.087
 Pen-0.083
 Mir-0.080
 El-0.079
 Megan-0.078
Token piece
Token ID3704
Feature activation+2.89e-01

Pos logit contributions
ercise+0.022
ets+0.022
ams+0.022
ock+0.021
vious+0.019
Neg logit contributions
 Ana-0.023
 Pen-0.022
 Megan-0.021
 Mir-0.021
 El-0.021
Token of
Token ID286
Feature activation-8.41e-01

Pos logit contributions
ercise+0.006
ams+0.006
ets+0.006
ock+0.005
isdom+0.005
Neg logit contributions
 Ana-0.009
 Pen-0.009
 Mir-0.009
 Megan-0.009
 El-0.009
Token cloth
Token ID16270
Feature activation+4.43e-01

Pos logit contributions
 Ana+0.021
 Pen+0.020
 Mir+0.019
 El+0.019
 Megan+0.019
Neg logit contributions
ets-0.023
ercise-0.023
ams-0.023
ock-0.022
vious-0.021
Token
Token ID198
Feature activation+1.31e+00

Pos logit contributions
ercise+0.031
ets+0.030
ams+0.030
ock+0.029
isdom+0.027
Neg logit contributions
 Ana-0.029
 Pen-0.027
 Mir-0.026
 Megan-0.026
 El-0.025
Token
Token ID198
Feature activation+1.12e+00

Pos logit contributions
ercise+0.036
ets+0.036
ams+0.036
ock+0.034
isdom+0.032
Neg logit contributions
 Ana-0.033
 Pen-0.031
 Mir-0.029
 Megan-0.029
 El-0.029
TokenShe
Token ID3347
Feature activation-7.23e-01

Pos logit contributions
ams+0.028
ets+0.028
ercise+0.028
ock+0.026
isdom+0.024
Neg logit contributions
 Ana-0.032
 Pen-0.031
 Megan-0.028
 Mir-0.028
 El-0.028
Token cut
Token ID2005
Feature activation+1.35e+00

Pos logit contributions
 Ana+0.021
 Pen+0.020
 Megan+0.019
 Mir+0.019
 plun+0.019
Neg logit contributions
ercise-0.017
ets-0.017
ams-0.017
ock-0.015
isdom-0.015
Token and
Token ID290
Feature activation+3.78e+00

Pos logit contributions
ets+0.030
ams+0.030
ercise+0.030
ock+0.028
vious+0.025
Neg logit contributions
 Ana-0.040
 Pen-0.039
 Megan-0.037
 gen-0.036
 Mir-0.036
Token se
Token ID384
Feature activation+7.43e+00

Pos logit contributions
ercise+0.103
ets+0.102
ams+0.102
ock+0.096
isdom+0.089
Neg logit contributions
 Ana-0.097
 Pen-0.093
 Megan-0.087
 Mir-0.086
 El-0.085
Tokenwed
Token ID19103
Feature activation+2.45e+00

Pos logit contributions
 jets+0.138
weet+0.128
 since+0.121
 pads+0.120
 sunset+0.116
Neg logit contributions
 Megan-0.172
 Ana-0.169
illi-0.161
 plun-0.159
 Ann-0.155
Token the
Token ID262
Feature activation+4.66e-01

Pos logit contributions
ets+0.049
ams+0.048
ercise+0.047
ock+0.045
ear+0.039
Neg logit contributions
 Ana-0.080
 Pen-0.078
 Megan-0.074
 Mir-0.073
 gen-0.072
Token fabric
Token ID9664
Feature activation-1.52e-01

Pos logit contributions
ets+0.012
ercise+0.012
ams+0.011
ock+0.011
isdom+0.010
Neg logit contributions
 Ana-0.013
 Pen-0.013
 Mir-0.012
 Megan-0.012
 El-0.012
Token and
Token ID290
Feature activation+3.57e+00

Pos logit contributions
 Ana+0.005
 Pen+0.005
 Mir+0.004
 Megan+0.004
 El+0.004
Neg logit contributions
ets-0.003
ercise-0.003
ams-0.003
ock-0.003
isdom-0.003
Token put
Token ID1234
Feature activation+1.94e+00

Pos logit contributions
ets+0.087
ams+0.087
ercise+0.086
ock+0.079
isdom+0.072
Neg logit contributions
 Ana-0.101
 Pen-0.099
 Megan-0.093
 plun-0.090
 Mir-0.090
Token big
Token ID1263
Feature activation+1.14e+00

Pos logit contributions
ercise+0.009
ets+0.009
ams+0.009
ock+0.009
weet+0.008
Neg logit contributions
 Ana-0.012
 Pen-0.011
 Mir-0.011
 Megan-0.011
 El-0.011
Token hill
Token ID12788
Feature activation-1.65e+00

Pos logit contributions
ercise+0.032
ets+0.031
ams+0.031
ock+0.030
isdom+0.028
Neg logit contributions
 Ana-0.029
 Pen-0.027
 Mir-0.026
 Megan-0.025
 El-0.025
Token.
Token ID13
Feature activation+8.29e-01

Pos logit contributions
 Ana+0.048
 Pen+0.046
 Mir+0.044
 Megan+0.044
 El+0.043
Neg logit contributions
ercise-0.039
ets-0.038
ams-0.038
ock-0.036
isdom-0.033
Token She
Token ID1375
Feature activation-4.50e-01

Pos logit contributions
ercise+0.020
ams+0.020
ets+0.020
ock+0.019
isdom+0.017
Neg logit contributions
 Ana-0.023
 Pen-0.022
 Mir-0.021
 plun-0.021
 Megan-0.021
Token would
Token ID561
Feature activation-2.76e-01

Pos logit contributions
 Ana+0.011
 Pen+0.011
 Mir+0.010
 Megan+0.010
 plun+0.010
Neg logit contributions
ercise-0.012
ets-0.012
ams-0.012
ock-0.011
vious-0.011
Token even
Token ID772
Feature activation+7.41e+00

Pos logit contributions
 Ana+0.007
 Pen+0.006
 Mir+0.006
 Megan+0.006
 El+0.006
Neg logit contributions
ercise-0.008
ets-0.008
ams-0.008
ock-0.007
isdom-0.007
Token pretend
Token ID16614
Feature activation+2.28e+00

Pos logit contributions
ams+0.228
ets+0.224
ercise+0.223
ock+0.210
isdom+0.208
Neg logit contributions
 Ana-0.163
 Pen-0.155
 Mir-0.145
 Megan-0.141
 El-0.141
Token to
Token ID284
Feature activation-2.23e+00

Pos logit contributions
ercise+0.049
ets+0.049
ams+0.048
ock+0.045
isdom+0.041
Neg logit contributions
 Ana-0.071
 Pen-0.068
 Mir-0.065
 Megan-0.065
 El-0.064
Token fly
Token ID6129
Feature activation+3.63e+00

Pos logit contributions
 Ana+0.056
 Pen+0.053
 Jenkins+0.050
 plun+0.049
 Megan+0.049
Neg logit contributions
ercise-0.062
ets-0.061
ock-0.059
ams-0.059
isdom-0.054
Token with
Token ID351
Feature activation+1.26e+00

Pos logit contributions
ets+0.079
ercise+0.079
ams+0.077
ock+0.073
isdom+0.065
Neg logit contributions
 Ana-0.112
 Pen-0.108
 Mir-0.103
 Megan-0.102
 El-0.101
Token the
Token ID262
Feature activation+6.72e-01

Pos logit contributions
ercise+0.029
ets+0.029
ams+0.028
ock+0.027
isdom+0.024
Neg logit contributions
 Ana-0.037
 Pen-0.036
 Mir-0.034
 Megan-0.034
 El-0.033
Token paint
Token ID7521
Feature activation+5.02e-01

Pos logit contributions
ets+0.010
ercise+0.010
ams+0.010
ock+0.009
vious+0.008
Neg logit contributions
 Ana-0.010
 Pen-0.009
 Mir-0.009
 Megan-0.009
 El-0.009
Token pot
Token ID1787
Feature activation-9.81e-01

Pos logit contributions
ercise+0.012
ams+0.011
ets+0.011
ock+0.010
isdom+0.010
Neg logit contributions
 Ana-0.015
 Pen-0.014
 Mir-0.014
 Megan-0.013
 El-0.013
Token.
Token ID13
Feature activation+1.46e+00

Pos logit contributions
 Ana+0.029
 Pen+0.028
 Mir+0.027
 El+0.027
 Megan+0.026
Neg logit contributions
ercise-0.023
ams-0.021
ets-0.021
ock-0.020
isdom-0.020
Token She
Token ID1375
Feature activation-6.91e-01

Pos logit contributions
ercise+0.039
ets+0.038
ams+0.038
ock+0.036
isdom+0.034
Neg logit contributions
 Ana-0.038
 Pen-0.037
 Mir-0.034
 Megan-0.034
 El-0.034
Token would
Token ID561
Feature activation-6.79e-01

Pos logit contributions
 Ana+0.019
 Pen+0.018
 Mir+0.017
 Megan+0.017
 El+0.017
Neg logit contributions
ercise-0.017
ets-0.017
ams-0.017
ock-0.016
isdom-0.015
Token even
Token ID772
Feature activation+7.32e+00

Pos logit contributions
 Ana+0.015
 Pen+0.014
 Mir+0.013
 El+0.013
 Megan+0.013
Neg logit contributions
ercise-0.021
ams-0.021
ets-0.021
ock-0.020
isdom-0.018
Token mix
Token ID5022
Feature activation+3.28e+00

Pos logit contributions
ercise+0.233
ams+0.230
ets+0.230
ock+0.220
isdom+0.211
Neg logit contributions
 Ana-0.155
 Pen-0.144
 Mir-0.137
 Megan-0.132
 El-0.131
Token hot
Token ID3024
Feature activation+5.49e-01

Pos logit contributions
ercise+0.081
ets+0.079
ams+0.078
ock+0.074
isdom+0.071
Neg logit contributions
 Ana-0.094
 Pen-0.089
 Mir-0.086
 Megan-0.085
 El-0.084
Token chocolate
Token ID11311
Feature activation+8.23e-01

Pos logit contributions
ercise+0.014
ets+0.013
ams+0.013
ock+0.013
isdom+0.013
Neg logit contributions
 Ana-0.015
 Pen-0.014
 Mir-0.014
 El-0.014
 Megan-0.013
Token when
Token ID618
Feature activation-1.01e+00

Pos logit contributions
ets+0.017
ams+0.017
ercise+0.017
ock+0.016
ear+0.014
Neg logit contributions
 Ana-0.026
 Pen-0.025
 Megan-0.024
 plun-0.024
 Mir-0.024
Token she
Token ID673
Feature activation+4.71e-01

Pos logit contributions
 Ana+0.030
 plun+0.029
 Pen+0.028
 gen+0.028
 Mir+0.027
Neg logit contributions
ercise-0.020
ams-0.020
ock-0.019
ets-0.019
weet-0.017
Token a
Token ID257
Feature activation-2.93e-01

Pos logit contributions
 Ana+0.022
 Pen+0.021
 Megan+0.020
 Mir+0.020
 El+0.020
Neg logit contributions
ercise-0.018
ams-0.018
ets-0.018
ock-0.017
vious-0.016
Token needle
Token ID17598
Feature activation+2.14e-02

Pos logit contributions
 Ana+0.009
 Pen+0.008
 Megan+0.008
 El+0.008
 Mir+0.008
Neg logit contributions
ercise-0.007
ets-0.007
ock-0.006
ams-0.006
isdom-0.006
Token and
Token ID290
Feature activation+3.42e+00

Pos logit contributions
ercise+0.000
ets+0.000
ams+0.000
ock+0.000
isdom+0.000
Neg logit contributions
 Ana-0.001
 Pen-0.001
 Mir-0.001
 Megan-0.001
 El-0.001
Token thread
Token ID4704
Feature activation+2.03e+00

Pos logit contributions
ams+0.100
ets+0.100
ercise+0.098
ock+0.094
isdom+0.087
Neg logit contributions
 Ana-0.080
 Pen-0.076
 Mir-0.074
 plun-0.071
 gen-0.071
Token and
Token ID290
Feature activation+3.19e+00

Pos logit contributions
ets+0.035
ercise+0.034
ams+0.034
ock+0.032
vious+0.028
Neg logit contributions
 Ana-0.074
 Pen-0.071
 Megan-0.068
 Mir-0.067
 El-0.066
Token se
Token ID384
Feature activation+7.31e+00

Pos logit contributions
ets+0.089
ams+0.088
ercise+0.088
ock+0.084
isdom+0.078
Neg logit contributions
 Ana-0.079
 Pen-0.076
 Mir-0.072
 Megan-0.070
 El-0.070
Tokenwed
Token ID19103
Feature activation+2.35e+00

Pos logit contributions
weet+0.127
 jets+0.124
 since+0.116
 sunset+0.112
ock+0.112
Neg logit contributions
 plun-0.168
 Ana-0.160
 Megan-0.160
 Ann-0.157
ocated-0.156
Token a
Token ID257
Feature activation+7.98e-02

Pos logit contributions
ets+0.051
ercise+0.050
ams+0.050
ock+0.048
ear+0.042
Neg logit contributions
 Ana-0.073
 Pen-0.071
 Megan-0.067
 Mir-0.066
 gen-0.066
Token patch
Token ID8529
Feature activation-3.51e-01

Pos logit contributions
ets+0.002
ercise+0.002
ock+0.002
ams+0.002
ear+0.002
Neg logit contributions
 Ana-0.002
 Pen-0.002
 Megan-0.002
 El-0.002
 Mir-0.002
Token on
Token ID319
Feature activation-1.70e+00

Pos logit contributions
 Ana+0.012
 Pen+0.012
 Mir+0.011
 Megan+0.011
 El+0.011
Neg logit contributions
ercise-0.006
ams-0.006
ets-0.006
ock-0.005
isdom-0.005
Token Patch
Token ID17106
Feature activation+8.84e-01

Pos logit contributions
 Ana+0.050
 Pen+0.048
 Megan+0.046
 gen+0.045
 Mir+0.045
Neg logit contributions
ets-0.038
ercise-0.038
ams-0.036
ock-0.036
isdom-0.032
Token a
Token ID257
Feature activation+8.09e-01

Pos logit contributions
 Ana+0.062
 Pen+0.058
 Mir+0.055
 El+0.054
 Megan+0.054
Neg logit contributions
ercise-0.071
ets-0.070
ams-0.069
ock-0.064
isdom-0.061
Token needle
Token ID17598
Feature activation+3.86e-01

Pos logit contributions
ercise+0.020
ets+0.019
ock+0.018
ams+0.017
isdom+0.016
Neg logit contributions
 Ana-0.023
 Pen-0.022
 Megan-0.021
 Mir-0.021
 Mil-0.021
Token and
Token ID290
Feature activation+4.12e+00

Pos logit contributions
ercise+0.007
ams+0.007
ets+0.007
ock+0.006
isdom+0.006
Neg logit contributions
 Ana-0.013
 Pen-0.013
 Mir-0.012
 El-0.012
 Megan-0.012
Token thread
Token ID4704
Feature activation+2.04e+00

Pos logit contributions
ercise+0.107
ets+0.104
ams+0.103
ock+0.098
isdom+0.091
Neg logit contributions
 Ana-0.111
 Pen-0.107
 Megan-0.101
 Mir-0.099
 El-0.098
Token and
Token ID290
Feature activation+3.71e+00

Pos logit contributions
ets+0.039
ams+0.038
ercise+0.037
ock+0.036
vious+0.031
Neg logit contributions
 Ana-0.070
 Pen-0.067
 Megan-0.064
 Mir-0.064
 El-0.062
Token se
Token ID384
Feature activation+7.31e+00

Pos logit contributions
ercise+0.090
ets+0.087
ams+0.087
ock+0.083
isdom+0.075
Neg logit contributions
 Ana-0.105
 Pen-0.102
 Megan-0.097
 Jenkins-0.094
 Mir-0.094
Tokenwed
Token ID19103
Feature activation+2.28e+00

Pos logit contributions
weet+0.127
 jets+0.127
 since+0.112
ock+0.112
ully+0.112
Neg logit contributions
 plun-0.173
 Ana-0.172
 Megan-0.172
 Mir-0.166
 Ann-0.165
Token the
Token ID262
Feature activation+6.52e-02

Pos logit contributions
ets+0.050
ercise+0.049
ams+0.049
ock+0.047
ear+0.041
Neg logit contributions
 Ana-0.070
 Pen-0.068
 Megan-0.064
 Mir-0.063
 gen-0.063
Token t
Token ID256
Feature activation+6.34e-01

Pos logit contributions
ercise+0.002
ets+0.002
ock+0.002
ams+0.002
les+0.002
Neg logit contributions
 Ana-0.002
 Megan-0.001
 Pen-0.001
 Mil-0.001
 Mir-0.001
Tokeneddy
Token ID21874
Feature activation-1.39e-01

Pos logit contributions
ercise+0.014
ets+0.014
ams+0.013
ock+0.012
isdom+0.011
Neg logit contributions
 Ana-0.020
 Pen-0.019
 Mir-0.018
 Megan-0.018
 El-0.018
Token bear
Token ID6842
Feature activation+7.47e-02

Pos logit contributions
 Ana+0.003
 Pen+0.003
 Megan+0.003
 Mir+0.003
 Mil+0.002
Neg logit contributions
ercise-0.004
ets-0.004
ams-0.004
ock-0.004
les-0.004
Token to
Token ID284
Feature activation-2.23e+00

Pos logit contributions
ercise+0.058
ams+0.055
ets+0.055
ock+0.051
isdom+0.051
Neg logit contributions
 Ana-0.077
 Pen-0.074
 El-0.071
 Mir-0.070
 Megan-0.070
Token pick
Token ID2298
Feature activation+1.87e+00

Pos logit contributions
 Ana+0.061
 Pen+0.058
 Megan+0.055
 Mir+0.054
 Jenkins+0.054
Neg logit contributions
ercise-0.057
ets-0.057
ock-0.054
ams-0.054
isdom-0.049
Token up
Token ID510
Feature activation-1.60e-01

Pos logit contributions
ercise+0.045
ets+0.044
ams+0.044
ock+0.041
isdom+0.038
Neg logit contributions
 Ana-0.054
 Pen-0.052
 Mir-0.049
 Megan-0.049
 El-0.049
Token toys
Token ID14958
Feature activation+2.00e+00

Pos logit contributions
 Ana+0.005
 Pen+0.004
 Mir+0.004
 Megan+0.004
 El+0.004
Neg logit contributions
ercise-0.004
ets-0.004
ams-0.004
ock-0.004
isdom-0.003
Token and
Token ID290
Feature activation+4.58e+00

Pos logit contributions
ets+0.037
ercise+0.037
ams+0.036
ock+0.034
isdom+0.029
Neg logit contributions
 Ana-0.069
 Pen-0.067
 Mir-0.064
 Megan-0.063
 El-0.063
Token even
Token ID772
Feature activation+7.27e+00

Pos logit contributions
ercise+0.123
ets+0.122
ams+0.120
ock+0.113
isdom+0.106
Neg logit contributions
 Ana-0.119
 Pen-0.114
 Mir-0.107
 Megan-0.107
 El-0.105
Token l
Token ID300
Feature activation+9.28e-01

Pos logit contributions
ams+0.202
ercise+0.202
ets+0.201
ock+0.191
isdom+0.182
Neg logit contributions
 Ana-0.181
 Pen-0.171
 Mir-0.162
 Megan-0.158
 El-0.158
Tokenicked
Token ID9484
Feature activation+1.76e+00

Pos logit contributions
ets+0.023
ercise+0.022
ams+0.022
ock+0.021
vious+0.019
Neg logit contributions
 Ana-0.027
 Pen-0.026
 Mir-0.025
 Megan-0.024
 El-0.024
Token the
Token ID262
Feature activation-2.27e-01

Pos logit contributions
ercise+0.043
ets+0.043
ams+0.043
ock+0.040
isdom+0.037
Neg logit contributions
 Ana-0.050
 Pen-0.048
 Mir-0.045
 Megan-0.045
 El-0.045
Token dust
Token ID8977
Feature activation-3.06e+00

Pos logit contributions
 Ana+0.006
 Pen+0.006
 Mir+0.006
 Megan+0.006
 Mil+0.005
Neg logit contributions
ets-0.006
ercise-0.006
ock-0.006
ams-0.006
elling-0.005
Token off
Token ID572
Feature activation-2.49e+00

Pos logit contributions
 Ana+0.095
 Pen+0.092
 Mir+0.087
 Megan+0.087
 El+0.086
Neg logit contributions
ets-0.067
ams-0.064
ercise-0.064
ock-0.062
vious-0.054
Token of
Token ID286
Feature activation-3.93e-01

Pos logit contributions
ercise+0.135
isdom+0.119
ully+0.112
ams+0.103
iper+0.099
Neg logit contributions
 Ana-0.102
 Megan-0.098
 El-0.096
 Ell-0.095
 Pen-0.094
Token fun
Token ID1257
Feature activation+1.94e+00

Pos logit contributions
 Ana+0.011
 Pen+0.011
 Mir+0.010
 El+0.010
 Megan+0.010
Neg logit contributions
ercise-0.009
ets-0.009
ams-0.009
ock-0.009
isdom-0.009
Token.
Token ID13
Feature activation+2.03e+00

Pos logit contributions
ercise+0.058
ets+0.055
ams+0.054
ock+0.053
isdom+0.053
Neg logit contributions
 Ana-0.045
 Pen-0.042
 El-0.041
 Mir-0.040
 Megan-0.040
Token He
Token ID679
Feature activation-5.39e-01

Pos logit contributions
ercise+0.056
ets+0.056
ams+0.056
ock+0.053
isdom+0.049
Neg logit contributions
 Ana-0.052
 Pen-0.050
 Mir-0.047
 Megan-0.047
 El-0.046
Token would
Token ID561
Feature activation-3.10e-01

Pos logit contributions
 Ana+0.013
 Pen+0.013
 Mir+0.012
 Megan+0.012
 El+0.012
Neg logit contributions
ercise-0.015
ets-0.015
ams-0.015
ock-0.014
isdom-0.013
Token even
Token ID772
Feature activation+7.27e+00

Pos logit contributions
 Ana+0.007
 Pen+0.007
 Mir+0.006
 Megan+0.006
 El+0.006
Neg logit contributions
ercise-0.009
ets-0.009
ams-0.009
ock-0.009
isdom-0.008
Token try
Token ID1949
Feature activation+3.28e+00

Pos logit contributions
ams+0.224
ercise+0.222
ets+0.218
isdom+0.214
elling+0.213
Neg logit contributions
 Ana-0.155
 Pen-0.143
 Mir-0.138
 El-0.133
 Megan-0.132
Token to
Token ID284
Feature activation-2.35e+00

Pos logit contributions
ams+0.081
ercise+0.081
ets+0.080
vious+0.073
ock+0.073
Neg logit contributions
 Ana-0.093
 Pen-0.089
 Mir-0.087
 El-0.086
 Mil-0.082
Token make
Token ID787
Feature activation+2.85e+00

Pos logit contributions
 Ana+0.058
 Pen+0.055
 Mir+0.052
 Megan+0.052
 gen+0.050
Neg logit contributions
ercise-0.066
ets-0.066
ams-0.065
ock-0.064
vious-0.057
Token up
Token ID510
Feature activation+9.41e-02

Pos logit contributions
ercise+0.068
ets+0.067
ams+0.067
ock+0.063
isdom+0.058
Neg logit contributions
 Ana-0.083
 Pen-0.080
 Mir-0.076
 Megan-0.075
 El-0.074
Token silly
Token ID14397
Feature activation+1.79e+00

Pos logit contributions
ercise+0.002
ets+0.002
ams+0.002
ock+0.002
isdom+0.002
Neg logit contributions
 Ana-0.003
 Pen-0.003
 Mir-0.003
 Megan-0.003
 El-0.003
Token needle
Token ID17598
Feature activation+1.39e+00

Pos logit contributions
ercise+0.010
ets+0.009
ams+0.009
ock+0.008
isdom+0.008
Neg logit contributions
 Ana-0.013
 Pen-0.012
 Megan-0.012
 Mir-0.011
 El-0.011
Token and
Token ID290
Feature activation+3.28e+00

Pos logit contributions
ercise+0.031
ams+0.030
ets+0.030
ock+0.028
isdom+0.026
Neg logit contributions
 Ana-0.042
 Pen-0.041
 Mir-0.039
 El-0.038
 Megan-0.038
Token thread
Token ID4704
Feature activation+2.61e+00

Pos logit contributions
ercise+0.087
ets+0.086
ams+0.086
ock+0.081
isdom+0.075
Neg logit contributions
 Ana-0.087
 Pen-0.083
 Mir-0.079
 Megan-0.078
 El-0.077
Token.
Token ID13
Feature activation+2.37e-01

Pos logit contributions
ercise+0.061
ets+0.060
ams+0.060
ock+0.057
isdom+0.052
Neg logit contributions
 Ana-0.076
 Pen-0.073
 Mir-0.069
 Megan-0.069
 El-0.069
Token She
Token ID1375
Feature activation-1.01e+00

Pos logit contributions
ercise+0.005
ets+0.005
ams+0.005
ock+0.004
vious+0.004
Neg logit contributions
 Ana-0.007
 Pen-0.007
 gen-0.007
 plun-0.007
 Megan-0.007
Token se
Token ID384
Feature activation+7.25e+00

Pos logit contributions
 Ana+0.028
 Pen+0.027
 Megan+0.025
 Mir+0.025
 El+0.025
Neg logit contributions
ercise-0.025
ets-0.025
ams-0.025
ock-0.023
isdom-0.022
Tokenwed
Token ID19103
Feature activation+2.52e+00

Pos logit contributions
ercise+0.117
 since+0.115
weet+0.111
 pads+0.110
 jets+0.108
Neg logit contributions
 Megan-0.172
 Ana-0.166
illi-0.160
 Ann-0.157
 Mir-0.155
Token a
Token ID257
Feature activation+3.43e-01

Pos logit contributions
ercise+0.064
ets+0.063
ams+0.061
ock+0.057
isdom+0.056
Neg logit contributions
 Ana-0.070
 Pen-0.067
 Mir-0.065
 El-0.064
 Ell-0.063
Token hole
Token ID7604
Feature activation-2.67e+00

Pos logit contributions
ercise+0.009
ets+0.009
ams+0.009
ock+0.009
isdom+0.008
Neg logit contributions
 Ana-0.009
 Pen-0.008
 Mir-0.008
 Megan-0.008
 El-0.008
Token in
Token ID287
Feature activation-2.47e+00

Pos logit contributions
 Ana+0.068
 Pen+0.064
 Megan+0.061
 Mir+0.061
 El+0.061
Neg logit contributions
ercise-0.074
ams-0.070
ets-0.069
ock-0.067
isdom-0.064
Token the
Token ID262
Feature activation-2.14e-02

Pos logit contributions
 Ana+0.079
 Pen+0.075
 Megan+0.071
 Mir+0.070
 gen+0.070
Neg logit contributions
ams-0.048
ock-0.047
ets-0.046
ercise-0.046
ear-0.040
Token blue
Token ID4171
Feature activation+3.29e+00

Pos logit contributions
ercise+0.006
ets+0.006
isdom+0.006
ams+0.005
ear+0.005
Neg logit contributions
 Ana-0.005
 Ell-0.005
 Pen-0.004
 El-0.004
 Megan-0.004
Tokenberries
Token ID20853
Feature activation+3.11e+00

Pos logit contributions
ercise+0.112
ets+0.108
isdom+0.105
ear+0.101
aling+0.100
Neg logit contributions
 Ana-0.061
 Ell-0.059
 El-0.056
 Fl-0.056
 Pen-0.055
Token.
Token ID13
Feature activation+1.96e+00

Pos logit contributions
ercise+0.085
ets+0.081
ams+0.080
ock+0.076
isdom+0.076
Neg logit contributions
 Ana-0.081
 Pen-0.078
 El-0.074
 Megan-0.073
 Mir-0.073
Token She
Token ID1375
Feature activation-4.24e-01

Pos logit contributions
ercise+0.046
ets+0.045
ams+0.044
ock+0.043
isdom+0.039
Neg logit contributions
 Ana-0.056
 Pen-0.053
 plun-0.051
 gen-0.051
 Mir-0.051
Token would
Token ID561
Feature activation-3.80e-01

Pos logit contributions
 Ana+0.013
 Pen+0.012
 plun+0.012
 Mir+0.012
 Megan+0.012
Neg logit contributions
ercise-0.009
ets-0.009
ams-0.009
ock-0.008
isdom-0.008
Token even
Token ID772
Feature activation+7.24e+00

Pos logit contributions
 Ana+0.009
 Pen+0.009
 El+0.008
 Mir+0.008
 Megan+0.008
Neg logit contributions
ams-0.011
ercise-0.011
ets-0.011
ock-0.011
vious-0.010
Token eat
Token ID4483
Feature activation+1.12e+00

Pos logit contributions
ercise+0.217
ets+0.215
ams+0.214
ock+0.210
isdom+0.203
Neg logit contributions
 Ana-0.162
 Pen-0.151
 Mir-0.146
 Megan-0.141
 El-0.136
Token them
Token ID606
Feature activation+1.56e+00

Pos logit contributions
ercise+0.027
ets+0.027
ams+0.026
ock+0.024
isdom+0.023
Neg logit contributions
 Ana-0.033
 Pen-0.032
 Mir-0.030
 Megan-0.030
 El-0.030
Token for
Token ID329
Feature activation-7.32e-01

Pos logit contributions
ercise+0.030
ets+0.029
ams+0.028
ock+0.027
isdom+0.025
Neg logit contributions
 Ana-0.054
 Pen-0.052
 El-0.050
 Megan-0.050
 Mir-0.049
Token breakfast
Token ID12607
Feature activation+4.44e-01

Pos logit contributions
 Ana+0.021
 Pen+0.020
 Mir+0.019
 Megan+0.019
 El+0.018
Neg logit contributions
ercise-0.018
ets-0.018
ams-0.018
ock-0.017
vious-0.016
Token,
Token ID11
Feature activation+1.02e-01

Pos logit contributions
ets+0.008
ams+0.008
ercise+0.008
ock+0.008
isdom+0.007
Neg logit contributions
 Ana-0.015
 Pen-0.014
 Mir-0.014
 Megan-0.014
 El-0.014
Token the
Token ID262
Feature activation+2.84e-01

Pos logit contributions
ercise+0.063
ams+0.063
ets+0.062
ock+0.059
isdom+0.057
Neg logit contributions
 Ana-0.039
 Pen-0.037
 Mir-0.034
 Megan-0.034
 El-0.033
Token t
Token ID256
Feature activation+2.09e-01

Pos logit contributions
ercise+0.009
ock+0.009
ets+0.009
ams+0.009
vious+0.008
Neg logit contributions
 Ana-0.005
 Pen-0.005
 Megan-0.005
 Mir-0.005
 Mil-0.005
Tokeneddy
Token ID21874
Feature activation-2.75e-01

Pos logit contributions
ercise+0.005
ets+0.005
ams+0.005
isdom+0.004
vious+0.004
Neg logit contributions
 Ana-0.006
 Pen-0.006
 gen-0.005
 Mir-0.005
 Sn-0.005
Token bear
Token ID6842
Feature activation-1.22e-01

Pos logit contributions
 Ana+0.004
 Pen+0.004
 Mir+0.004
 El+0.004
 Megan+0.004
Neg logit contributions
ets-0.010
ercise-0.010
ams-0.010
ock-0.010
isdom-0.009
Token and
Token ID290
Feature activation+3.82e+00

Pos logit contributions
 Ana+0.004
 Pen+0.004
 Mir+0.003
 El+0.003
 plun+0.003
Neg logit contributions
ercise-0.003
ams-0.003
ets-0.003
ock-0.003
isdom-0.002
Token se
Token ID384
Feature activation+7.23e+00

Pos logit contributions
ercise+0.094
ams+0.089
ets+0.089
ock+0.085
isdom+0.078
Neg logit contributions
 Ana-0.105
 Pen-0.102
 Megan-0.097
 Mir-0.094
 Jenkins-0.094
Tokenwed
Token ID19103
Feature activation+2.16e+00

Pos logit contributions
 jets+0.127
weet+0.126
ets+0.112
ully+0.112
ercise+0.112
Neg logit contributions
 Megan-0.182
 Ana-0.180
 plun-0.172
 Ann-0.171
 Fl-0.167
Token up
Token ID510
Feature activation+3.90e-01

Pos logit contributions
ercise+0.049
ets+0.049
ams+0.048
ock+0.046
ear+0.041
Neg logit contributions
 Ana-0.064
 Pen-0.062
 Mir-0.059
 Megan-0.058
 El-0.057
Token the
Token ID262
Feature activation+8.29e-01

Pos logit contributions
ercise+0.009
ets+0.009
ams+0.009
ock+0.009
isdom+0.008
Neg logit contributions
 Ana-0.011
 Pen-0.011
 Mir-0.010
 Megan-0.010
 El-0.010
Token hole
Token ID7604
Feature activation-3.96e+00

Pos logit contributions
ercise+0.026
ets+0.026
ams+0.025
ock+0.025
vious+0.023
Neg logit contributions
 Ana-0.018
 Pen-0.017
 Megan-0.016
 Mir-0.016
 El-0.015
Token in
Token ID287
Feature activation-2.50e+00

Pos logit contributions
 Ana+0.121
 Pen+0.117
 Mir+0.111
 Megan+0.110
 El+0.109
Neg logit contributions
ets-0.088
ams-0.086
ercise-0.086
ock-0.081
vious-0.073
Token healthy
Token ID5448
Feature activation+5.55e-01

Pos logit contributions
 Ana+0.044
 Pen+0.043
 Megan+0.040
 Mir+0.040
 El+0.040
Neg logit contributions
ercise-0.035
ets-0.035
ams-0.034
ock-0.032
isdom-0.030
Token things
Token ID1243
Feature activation-3.38e-02

Pos logit contributions
ercise+0.013
ets+0.013
ams+0.013
ock+0.012
isdom+0.011
Neg logit contributions
 Ana-0.016
 Pen-0.016
 Megan-0.015
 Mir-0.015
 El-0.014
Token.
Token ID13
Feature activation+1.43e+00

Pos logit contributions
 Ana+0.001
 Pen+0.001
 El+0.001
 Megan+0.001
 Ell+0.001
Neg logit contributions
ercise-0.001
ams-0.001
ets-0.001
ock-0.001
isdom-0.001
Token He
Token ID679
Feature activation-9.92e-01

Pos logit contributions
ercise+0.046
ets+0.046
ock+0.045
ams+0.045
elling+0.041
Neg logit contributions
 Ana-0.029
 Pen-0.028
 Megan-0.028
 Mir-0.027
 El-0.025
Token would
Token ID561
Feature activation-4.67e-01

Pos logit contributions
 Ana+0.029
 Pen+0.028
 Mir+0.027
 Megan+0.027
 plun+0.026
Neg logit contributions
ets-0.023
ercise-0.023
ams-0.023
ock-0.021
isdom-0.019
Token even
Token ID772
Feature activation+7.21e+00

Pos logit contributions
 Ana+0.013
 Pen+0.012
 Mir+0.011
 Megan+0.011
 El+0.011
Neg logit contributions
ercise-0.012
ets-0.012
ams-0.012
ock-0.011
isdom-0.010
Token share
Token ID2648
Feature activation+2.61e+00

Pos logit contributions
ercise+0.211
ams+0.209
ets+0.209
ock+0.203
isdom+0.191
Neg logit contributions
 Ana-0.167
 Pen-0.157
 Mir-0.150
 Megan-0.146
 El-0.143
Token these
Token ID777
Feature activation+1.35e+00

Pos logit contributions
ercise+0.069
ets+0.068
ams+0.064
ock+0.063
vious+0.063
Neg logit contributions
 Ana-0.071
 Pen-0.066
 Megan-0.064
 Mir-0.063
 Ell-0.063
Token snacks
Token ID28487
Feature activation+2.96e-01

Pos logit contributions
ercise+0.033
ets+0.032
ams+0.032
ock+0.031
isdom+0.029
Neg logit contributions
 Ana-0.038
 Pen-0.036
 Megan-0.035
 El-0.034
 Mir-0.034
Token with
Token ID351
Feature activation+1.03e+00

Pos logit contributions
ercise+0.008
ets+0.008
ams+0.008
ock+0.008
isdom+0.007
Neg logit contributions
 Ana-0.007
 Pen-0.007
 Megan-0.007
 Mir-0.007
 El-0.007
Token his
Token ID465
Feature activation-5.93e-01

Pos logit contributions
ets+0.025
ercise+0.025
ams+0.023
ock+0.023
vious+0.022
Neg logit contributions
 Ana-0.030
 Pen-0.028
 Megan-0.028
 Mir-0.027
 El-0.027
Token and
Token ID290
Feature activation+2.92e+00

Pos logit contributions
ercise+0.012
ets+0.012
ams+0.012
ock+0.011
isdom+0.010
Neg logit contributions
 Ana-0.018
 Pen-0.017
 Mir-0.017
 Megan-0.016
 El-0.016
Token some
Token ID617
Feature activation+8.97e-01

Pos logit contributions
ams+0.077
ercise+0.076
ets+0.076
ock+0.073
isdom+0.068
Neg logit contributions
 Ana-0.078
 Pen-0.074
 Mir-0.071
 El-0.069
 Megan-0.069
Token buttons
Token ID12163
Feature activation+2.40e+00

Pos logit contributions
ercise+0.023
ams+0.023
ets+0.023
ock+0.021
isdom+0.020
Neg logit contributions
 Ana-0.024
 Pen-0.023
 Mir-0.022
 Megan-0.021
 El-0.021
Token.
Token ID13
Feature activation-4.51e-01

Pos logit contributions
ercise+0.059
ams+0.056
ets+0.054
isdom+0.052
ock+0.052
Neg logit contributions
 Ana-0.067
 Pen-0.064
 Mir-0.063
 El-0.062
 Megan-0.061
Token I
Token ID314
Feature activation+2.61e-01

Pos logit contributions
 Ana+0.012
 Pen+0.011
 Mir+0.011
 Megan+0.010
 El+0.010
Neg logit contributions
ercise-0.012
ets-0.012
ams-0.012
ock-0.011
isdom-0.010
Token se
Token ID384
Feature activation+7.18e+00

Pos logit contributions
ets+0.007
ercise+0.007
ams+0.007
ock+0.006
vious+0.006
Neg logit contributions
 Ana-0.007
 Pen-0.007
 Megan-0.006
 Mir-0.006
 Jenkins-0.006
Tokenwed
Token ID19103
Feature activation+2.76e+00

Pos logit contributions
 jets+0.121
ully+0.118
 since+0.111
ercise+0.110
weet+0.109
Neg logit contributions
 Ana-0.190
 Megan-0.184
 Mir-0.180
illi-0.178
 Mil-0.173
Token them
Token ID606
Feature activation+5.02e-01

Pos logit contributions
ercise+0.070
ets+0.069
ams+0.069
ock+0.064
isdom+0.063
Neg logit contributions
 Ana-0.076
 Pen-0.072
 Mir-0.070
 El-0.068
 Megan-0.067
Token together
Token ID1978
Feature activation+1.16e+00

Pos logit contributions
ercise+0.011
ets+0.011
ams+0.011
ock+0.010
isdom+0.009
Neg logit contributions
 Ana-0.015
 Pen-0.015
 Mir-0.014
 Megan-0.014
 El-0.014
Token and
Token ID290
Feature activation+3.21e+00

Pos logit contributions
ercise+0.023
ams+0.023
ets+0.023
ock+0.021
isdom+0.019
Neg logit contributions
 Ana-0.038
 Pen-0.037
 Mir-0.035
 Megan-0.035
 El-0.035
Token stuffed
Token ID22259
Feature activation+1.87e+00

Pos logit contributions
ercise+0.078
ets+0.078
ams+0.077
ock+0.072
isdom+0.067
Neg logit contributions
 Ana-0.090
 Pen-0.088
 Mir-0.082
 Megan-0.082
 plun-0.081
Token this
Token ID428
Feature activation+5.01e-01

Pos logit contributions
ercise+0.036
ets+0.036
ams+0.036
ock+0.034
isdom+0.031
Neg logit contributions
 Ana-0.045
 Pen-0.043
 Mir-0.040
 Megan-0.040
 El-0.040
Token show
Token ID905
Feature activation+3.53e+00

Pos logit contributions
ets+0.012
ercise+0.012
ams+0.012
ock+0.012
isdom+0.011
Neg logit contributions
 Ana-0.014
 Pen-0.013
 Mir-0.013
 Megan-0.013
 El-0.012
Token?
Token ID30
Feature activation+5.69e-01

Pos logit contributions
ercise+0.080
ets+0.079
ams+0.079
ock+0.074
isdom+0.068
Neg logit contributions
 Ana-0.106
 Pen-0.102
 Mir-0.096
 Megan-0.096
 El-0.095
Token You
Token ID921
Feature activation+2.37e+00

Pos logit contributions
ercise+0.014
ams+0.013
ets+0.013
ock+0.012
ear+0.012
Neg logit contributions
 Ana-0.015
 Pen-0.015
 plun-0.014
 gen-0.014
 Mir-0.014
Token can
Token ID460
Feature activation-5.85e-01

Pos logit contributions
ets+0.063
ercise+0.062
ams+0.060
ock+0.058
vious+0.054
Neg logit contributions
 Ana-0.063
 Pen-0.060
 Mir-0.057
 Megan-0.057
 plun-0.055
Token even
Token ID772
Feature activation+7.17e+00

Pos logit contributions
 Ana+0.014
 Pen+0.013
 Mir+0.013
 Megan+0.012
 El+0.012
Neg logit contributions
ercise-0.017
ets-0.017
ams-0.017
ock-0.016
isdom-0.015
Token perform
Token ID1620
Feature activation+2.33e+00

Pos logit contributions
ercise+0.204
ams+0.203
ets+0.203
ock+0.192
isdom+0.179
Neg logit contributions
 Ana-0.174
 Pen-0.166
 Mir-0.155
 Megan-0.153
 El-0.152
Token in
Token ID287
Feature activation-1.56e+00

Pos logit contributions
ercise+0.055
ams+0.054
ets+0.054
ock+0.051
isdom+0.047
Neg logit contributions
 Ana-0.069
 Pen-0.066
 Mir-0.062
 Megan-0.062
 El-0.062
Token front
Token ID2166
Feature activation+1.44e+00

Pos logit contributions
 Ana+0.049
 Pen+0.048
 Mir+0.045
 Megan+0.045
 El+0.044
Neg logit contributions
ercise-0.033
ets-0.033
ams-0.033
ock-0.031
isdom-0.028
Token of
Token ID286
Feature activation-8.11e-01

Pos logit contributions
ercise+0.029
ams+0.026
ets+0.024
ully+0.024
isdom+0.023
Neg logit contributions
 Ana-0.048
 Pen-0.046
 Megan-0.045
 El-0.045
 Mir-0.044
Token all
Token ID477
Feature activation+3.72e+00

Pos logit contributions
 Ana+0.025
 Pen+0.025
 Mir+0.023
 Megan+0.023
 El+0.023
Neg logit contributions
ercise-0.017
ets-0.017
ams-0.017
ock-0.016
isdom-0.014
Token loved
Token ID6151
Feature activation+2.16e+00

Pos logit contributions
 Ana+0.008
 Pen+0.008
 Mir+0.007
 El+0.007
 Megan+0.007
Neg logit contributions
ercise-0.008
ets-0.008
ams-0.008
ock-0.007
isdom-0.007
Token taking
Token ID2263
Feature activation+2.72e+00

Pos logit contributions
ercise+0.053
ets+0.053
ams+0.053
ock+0.050
isdom+0.046
Neg logit contributions
 Ana-0.061
 Pen-0.058
 Mir-0.055
 Megan-0.055
 El-0.054
Token baths
Token ID49076
Feature activation+6.92e-01

Pos logit contributions
ercise+0.059
ams+0.059
ets+0.058
ock+0.054
isdom+0.051
Neg logit contributions
 Ana-0.085
 Pen-0.082
 Mir-0.077
 Megan-0.077
 El-0.077
Token and
Token ID290
Feature activation+3.46e+00

Pos logit contributions
ets+0.014
ercise+0.014
ams+0.014
ock+0.013
vious+0.012
Neg logit contributions
 Ana-0.022
 Pen-0.022
 Mir-0.021
 Megan-0.021
 gen-0.020
Token would
Token ID561
Feature activation-6.69e-01

Pos logit contributions
ercise+0.094
ets+0.093
ams+0.093
ock+0.088
isdom+0.081
Neg logit contributions
 Ana-0.089
 Pen-0.086
 Mir-0.080
 Megan-0.080
 El-0.079
Token even
Token ID772
Feature activation+7.14e+00

Pos logit contributions
 Ana+0.020
 Pen+0.020
 Mir+0.019
 Megan+0.018
 El+0.018
Neg logit contributions
ercise-0.015
ets-0.015
ams-0.015
ock-0.014
isdom-0.013
Token ask
Token ID1265
Feature activation-2.96e-01

Pos logit contributions
ams+0.211
ercise+0.208
ets+0.206
isdom+0.194
ock+0.193
Neg logit contributions
 Ana-0.165
 Pen-0.155
 Mir-0.146
 El-0.144
 Megan-0.143
Token her
Token ID607
Feature activation-7.85e-01

Pos logit contributions
 Ana+0.010
 Pen+0.010
 Megan+0.009
 Mir+0.009
 gen+0.009
Neg logit contributions
ets-0.006
ercise-0.006
ams-0.006
ock-0.005
isdom-0.005
Token mom
Token ID1995
Feature activation+2.12e+00

Pos logit contributions
 Ana+0.020
 Pen+0.019
 Megan+0.018
 Mir+0.018
 El+0.017
Neg logit contributions
ercise-0.021
ets-0.021
ams-0.021
ock-0.020
isdom-0.019
Tokenmy
Token ID1820
Feature activation+2.85e+00

Pos logit contributions
ercise+0.044
ets+0.043
ams+0.042
ock+0.039
vious+0.037
Neg logit contributions
 Ana-0.068
 Pen-0.066
 Mir-0.062
 El-0.062
 Megan-0.062
Token if
Token ID611
Feature activation+3.27e-01

Pos logit contributions
ercise+0.055
ets+0.054
ams+0.054
ock+0.050
isdom+0.045
Neg logit contributions
 Ana-0.095
 Pen-0.092
 Mir-0.088
 Megan-0.087
 El-0.087
Token needle
Token ID17598
Feature activation+4.64e-01

Pos logit contributions
ercise+0.022
ets+0.022
ock+0.021
ams+0.020
ag+0.019
Neg logit contributions
 Ana-0.025
 Pen-0.024
 Megan-0.023
 Mir-0.023
 Mil-0.022
Token and
Token ID290
Feature activation+3.80e+00

Pos logit contributions
ercise+0.008
ets+0.008
ams+0.008
ock+0.007
isdom+0.007
Neg logit contributions
 Ana-0.016
 Pen-0.016
 Mir-0.015
 Megan-0.015
 El-0.015
Token thread
Token ID4704
Feature activation+1.94e+00

Pos logit contributions
ercise+0.104
ets+0.103
ams+0.102
ock+0.097
isdom+0.090
Neg logit contributions
 Ana-0.097
 Pen-0.093
 Mir-0.087
 Megan-0.086
 El-0.085
Token and
Token ID290
Feature activation+3.46e+00

Pos logit contributions
ets+0.036
ercise+0.035
ams+0.035
ock+0.033
vious+0.029
Neg logit contributions
 Ana-0.067
 Pen-0.064
 Megan-0.061
 Mir-0.061
 El-0.060
Token carefully
Token ID7773
Feature activation+1.73e+00

Pos logit contributions
ercise+0.093
ets+0.093
ams+0.092
ock+0.087
isdom+0.081
Neg logit contributions
 Ana-0.090
 Pen-0.086
 Megan-0.080
 Mir-0.080
 El-0.079
Token se
Token ID384
Feature activation+7.12e+00

Pos logit contributions
ets+0.045
ercise+0.045
ams+0.044
ock+0.041
isdom+0.039
Neg logit contributions
 Ana-0.048
 Pen-0.045
 Megan-0.043
 Mir-0.041
 Jenkins-0.041
Tokenwed
Token ID19103
Feature activation+2.44e+00

Pos logit contributions
 jets+0.120
weet+0.118
 since+0.108
ully+0.106
 sunset+0.104
Neg logit contributions
 Ana-0.170
 Mir-0.170
 plun-0.169
 Megan-0.169
 Ann-0.160
Token Mr
Token ID1770
Feature activation-2.65e+00

Pos logit contributions
ets+0.052
ams+0.052
ercise+0.051
ock+0.049
ear+0.043
Neg logit contributions
 Ana-0.076
 Pen-0.073
 Megan-0.069
 gen-0.068
 Mir-0.068
Token.
Token ID13
Feature activation-2.55e+00

Pos logit contributions
 Ana+0.094
 Pen+0.088
 Megan+0.087
 El+0.086
 plun+0.086
Neg logit contributions
ets-0.046
ams-0.044
ock-0.042
ercise-0.042
isdom-0.039
Token Fl
Token ID1610
Feature activation-1.88e+00

Pos logit contributions
 Ana+0.051
 Megan+0.048
 Pen+0.044
 Mil+0.044
 El+0.043
Neg logit contributions
ercise-0.065
isdom-0.064
ams-0.061
weet-0.061
 pads-0.061
Tokenuffy
Token ID15352
Feature activation-2.48e-01

Pos logit contributions
 Ana+0.041
 Pen+0.038
stack+0.037
 Megan+0.037
 Mir+0.037
Neg logit contributions
ams-0.056
ets-0.055
ercise-0.055
isdom-0.054
ock-0.051
Token forg
Token ID5784
Feature activation+5.40e+00

Pos logit contributions
 Ana+0.020
 Pen+0.019
 Mir+0.018
 Megan+0.018
 El+0.018
Neg logit contributions
ercise-0.021
ets-0.021
ams-0.020
ock-0.019
isdom-0.018
Tokenave
Token ID1015
Feature activation+1.30e+00

Pos logit contributions
ercise+0.110
ams+0.102
isdom+0.089
opl+0.089
ock+0.088
Neg logit contributions
 Ana-0.144
 plun-0.135
 Ell-0.133
 El-0.133
 Pen-0.130
Token Tim
Token ID5045
Feature activation+1.42e+00

Pos logit contributions
ercise+0.033
ets+0.033
ams+0.033
ock+0.030
vious+0.028
Neg logit contributions
 Ana-0.036
 Pen-0.035
 Mir-0.033
 Megan-0.033
 El-0.032
Tokenmy
Token ID1820
Feature activation+1.78e+00

Pos logit contributions
ercise+0.033
ets+0.030
ams+0.028
isdom+0.025
ear+0.025
Neg logit contributions
 Ana-0.042
 Pen-0.040
 Mir-0.039
 Fl-0.039
 Jenkins-0.039
Token and
Token ID290
Feature activation+3.94e+00

Pos logit contributions
ercise+0.042
ets+0.039
ams+0.039
ock+0.038
vious+0.035
Neg logit contributions
 Ana-0.052
 Pen-0.049
 Mir-0.047
 El-0.047
 Ell-0.045
Token even
Token ID772
Feature activation+7.10e+00

Pos logit contributions
ercise+0.091
ams+0.090
ets+0.088
ock+0.083
isdom+0.078
Neg logit contributions
 Ana-0.115
 Pen-0.111
 Megan-0.105
 plun-0.104
 Mir-0.103
Token gave
Token ID2921
Feature activation+2.67e+00

Pos logit contributions
ercise+0.190
ets+0.189
ams+0.188
ock+0.180
elling+0.166
Neg logit contributions
 Ana-0.183
 Pen-0.171
 Mir-0.165
 El-0.160
 gen-0.160
Token him
Token ID683
Feature activation-2.84e-01

Pos logit contributions
ets+0.059
ercise+0.058
ams+0.057
ock+0.052
vious+0.049
Neg logit contributions
 Ana-0.084
 Pen-0.080
 Mir-0.077
 Megan-0.077
 El-0.077
Token a
Token ID257
Feature activation-3.93e-02

Pos logit contributions
 Ana+0.006
 Pen+0.006
 El+0.005
 Fl+0.005
 Megan+0.005
Neg logit contributions
ets-0.009
ams-0.009
ercise-0.008
ock-0.008
elling-0.008
Token reward
Token ID6721
Feature activation-4.08e-02

Pos logit contributions
 Ana+0.001
 Pen+0.001
 plun+0.001
 Mir+0.001
 gen+0.001
Neg logit contributions
ams-0.001
ets-0.001
ercise-0.001
ock-0.001
isdom-0.001
Token for
Token ID329
Feature activation-1.23e+00

Pos logit contributions
 Ana+0.001
 Pen+0.001
 Mir+0.001
 Megan+0.001
 El+0.001
Neg logit contributions
ercise-0.001
ets-0.001
ams-0.001
ock-0.001
vious-0.001
Token around
Token ID1088
Feature activation-1.04e+00

Pos logit contributions
ets+0.013
ercise+0.013
ams+0.013
ock+0.012
vious+0.011
Neg logit contributions
 Ana-0.020
 Pen-0.019
 Mir-0.018
 Megan-0.018
 El-0.018
Token the
Token ID262
Feature activation-1.29e+00

Pos logit contributions
 Ana+0.038
 Pen+0.037
 Megan+0.036
 Mei+0.036
illi+0.035
Neg logit contributions
ets-0.014
ock-0.013
ams-0.012
ear-0.011
ercise-0.011
Token hallway
Token ID23959
Feature activation-5.07e+00

Pos logit contributions
 Ana+0.031
 Pen+0.029
 El+0.029
 Megan+0.028
 Mir+0.028
Neg logit contributions
ets-0.036
ams-0.034
ercise-0.033
ock-0.032
off-0.030
Token,
Token ID11
Feature activation-1.36e+00

Pos logit contributions
 Ana+0.170
 Pen+0.166
 Mir+0.155
 plun+0.154
 Megan+0.154
Neg logit contributions
ets-0.102
ams-0.097
ercise-0.089
ock-0.088
ear-0.079
Token the
Token ID262
Feature activation-1.87e+00

Pos logit contributions
 Ana+0.035
 Pen+0.034
 Megan+0.032
 Mir+0.030
 Jenkins+0.030
Neg logit contributions
ets-0.036
ercise-0.035
ams-0.034
ock-0.032
ear-0.030
Token dining
Token ID17423
Feature activation-7.19e+00

Pos logit contributions
 Ana+0.044
 Pen+0.042
 El+0.040
 Megan+0.040
 Mir+0.040
Neg logit contributions
ets-0.052
ercise-0.051
ams-0.049
ock-0.048
vious-0.045
Token room
Token ID2119
Feature activation-4.14e+00

Pos logit contributions
 Ana+0.166
 Pen+0.165
 El+0.159
 Sn+0.156
 plun+0.156
Neg logit contributions
ets-0.211
ams-0.205
ock-0.175
ercise-0.175
les-0.174
Token and
Token ID290
Feature activation+2.61e+00

Pos logit contributions
 Ana+0.123
 Pen+0.120
 Mir+0.111
 Mei+0.109
 Megan+0.108
Neg logit contributions
ets-0.104
ams-0.096
ock-0.089
ercise-0.088
vious-0.080
Token the
Token ID262
Feature activation-1.46e+00

Pos logit contributions
ams+0.053
ercise+0.052
ets+0.050
ock+0.049
 pads+0.041
Neg logit contributions
 Ana-0.083
 Pen-0.081
 Mir-0.075
 plun-0.074
 Mei-0.074
Token bedroom
Token ID14043
Feature activation-4.46e+00

Pos logit contributions
 Ana+0.035
 Pen+0.033
 Mir+0.032
 El+0.032
 Mil+0.031
Neg logit contributions
ercise-0.039
ets-0.038
ams-0.037
ock-0.036
vious-0.033
Token.
Token ID13
Feature activation+8.38e-01

Pos logit contributions
 Ana+0.131
 Pen+0.131
 Mei+0.120
 Mir+0.119
 Flor+0.117
Neg logit contributions
ets-0.113
ams-0.099
ock-0.087
ly-0.086
les-0.084
Token loud
Token ID7812
Feature activation-1.01e+00

Pos logit contributions
 Pen+0.053
 Megan+0.052
 Ana+0.051
 Mir+0.050
 Mil+0.049
Neg logit contributions
ock-0.025
ercise-0.025
ay-0.023
 arrow-0.022
weet-0.022
Token laugh
Token ID6487
Feature activation+3.81e-01

Pos logit contributions
 Ana+0.026
 Pen+0.025
 Megan+0.024
illi+0.024
 Mil+0.023
Neg logit contributions
ock-0.026
ets-0.024
ercise-0.024
weet-0.023
ag-0.022
Token echoed
Token ID22211
Feature activation-1.70e+00

Pos logit contributions
ets+0.010
ercise+0.010
ams+0.010
ock+0.010
vious+0.009
Neg logit contributions
 Ana-0.010
 Pen-0.010
 Mir-0.009
 Megan-0.009
 El-0.009
Token around
Token ID1088
Feature activation-2.53e+00

Pos logit contributions
 Ana+0.054
 Pen+0.053
 Mir+0.051
 Megan+0.050
 plun+0.049
Neg logit contributions
ets-0.035
ams-0.033
ock-0.033
ercise-0.032
ear-0.028
Token the
Token ID262
Feature activation-1.27e+00

Pos logit contributions
 Ana+0.086
 Pen+0.085
 gen+0.085
 Mir+0.084
 Megan+0.082
Neg logit contributions
ets-0.045
ock-0.039
ercise-0.038
ams-0.037
les-0.034
Token chamber
Token ID11847
Feature activation-7.15e+00

Pos logit contributions
 Ana+0.025
 Pen+0.025
 Mir+0.024
 plun+0.022
 Megan+0.022
Neg logit contributions
ets-0.042
ercise-0.040
ams-0.039
ock-0.038
ear-0.036
Token.
Token ID13
Feature activation-2.17e-01

Pos logit contributions
 Pen+0.258
 Ana+0.257
 Mir+0.245
 Megan+0.242
 plun+0.241
Neg logit contributions
ets-0.122
ams-0.094
ock-0.092
ear-0.083
vious-0.082
Token "
Token ID366
Feature activation-1.69e+00

Pos logit contributions
 Ana+0.006
 Pen+0.006
 gen+0.006
 Mir+0.006
 Megan+0.006
Neg logit contributions
ets-0.005
ercise-0.005
ams-0.005
ock-0.005
isdom-0.004
TokenWelcome
Token ID14618
Feature activation+4.63e-01

Pos logit contributions
 Ana+0.040
 Pen+0.038
 Mir+0.036
 Megan+0.035
 El+0.035
Neg logit contributions
ercise-0.050
ets-0.049
ams-0.049
ock-0.047
vious-0.044
Token visitors
Token ID9692
Feature activation+9.21e-01

Pos logit contributions
ercise+0.009
ets+0.008
ams+0.008
ock+0.008
ear+0.007
Neg logit contributions
 Ana-0.016
 Pen-0.015
 Mir-0.015
 plun-0.014
 Megan-0.014
Token,"
Token ID553
Feature activation-1.29e+00

Pos logit contributions
ets+0.019
ercise+0.018
ams+0.018
ock+0.017
vious+0.015
Neg logit contributions
 Ana-0.030
 Pen-0.029
 Mir-0.028
 plun-0.028
 Megan-0.027
Token came
Token ID1625
Feature activation-3.09e+00

Pos logit contributions
 Ana+0.002
 Pen+0.002
 plun+0.002
 Megan+0.002
 Mir+0.002
Neg logit contributions
ets-0.002
ercise-0.002
ock-0.002
ams-0.002
vious-0.001
Token from
Token ID422
Feature activation-4.64e+00

Pos logit contributions
 Ana+0.092
 Pen+0.088
 Megan+0.085
 plun+0.083
 Mir+0.083
Neg logit contributions
ets-0.067
ock-0.066
ams-0.065
ercise-0.065
ear-0.059
Token deep
Token ID2769
Feature activation-1.29e+00

Pos logit contributions
 Ana+0.128
 Pen+0.122
 Mir+0.115
 Megan+0.115
 plun+0.112
Neg logit contributions
ercise-0.116
ets-0.115
ams-0.111
ock-0.109
isdom-0.100
Token inside
Token ID2641
Feature activation-5.06e+00

Pos logit contributions
 Ana+0.038
 Pen+0.037
 Mir+0.035
 El+0.034
 Megan+0.034
Neg logit contributions
ercise-0.031
ets-0.030
ams-0.030
ock-0.028
isdom-0.027
Token the
Token ID262
Feature activation-1.53e+00

Pos logit contributions
 Ana+0.177
 Pen+0.171
 plun+0.168
 Mir+0.165
 Lopez+0.163
Neg logit contributions
ock-0.072
ets-0.071
ams-0.065
ear-0.060
weet-0.059
Token chamber
Token ID11847
Feature activation-6.91e+00

Pos logit contributions
 Ana+0.028
 Pen+0.028
 Mir+0.027
 Mil+0.027
 Megan+0.026
Neg logit contributions
ets-0.050
ercise-0.049
ock-0.046
ams-0.045
elling-0.044
Token.
Token ID13
Feature activation-6.58e-01

Pos logit contributions
 Ana+0.243
 Pen+0.241
 plun+0.236
 Mir+0.229
 Sn+0.228
Neg logit contributions
ets-0.104
ams-0.089
ock-0.085
ercise-0.078
ear-0.078
Token Max
Token ID5436
Feature activation-6.88e-01

Pos logit contributions
 Ana+0.019
 Megan+0.019
 Pen+0.019
 Mil+0.018
 Mir+0.018
Neg logit contributions
ercise-0.014
ets-0.013
isdom-0.012
ock-0.011
ear-0.011
Token jumped
Token ID11687
Feature activation+1.20e-01

Pos logit contributions
 Ana+0.018
 plun+0.018
stack+0.018
 Megan+0.018
 Pen+0.018
Neg logit contributions
ets-0.014
ercise-0.014
ly-0.013
les-0.013
 pads-0.013
Token with
Token ID351
Feature activation-2.14e-01

Pos logit contributions
ets+0.002
ercise+0.002
ams+0.002
ock+0.002
ear+0.002
Neg logit contributions
 Ana-0.004
 Pen-0.004
 Mir-0.004
 Megan-0.003
 gen-0.003
Token fright
Token ID12773
Feature activation+1.33e+00

Pos logit contributions
 Ana+0.006
 Pen+0.006
 Mir+0.006
 Megan+0.006
 El+0.006
Neg logit contributions
ercise-0.005
ets-0.005
ams-0.005
ock-0.005
isdom-0.004
Token to
Token ID284
Feature activation-3.77e+00

Pos logit contributions
 Ana+0.003
 Pen+0.003
 Mir+0.003
 Megan+0.003
 El+0.002
Neg logit contributions
ercise-0.002
ets-0.002
ams-0.002
ock-0.002
vious-0.002
Token the
Token ID262
Feature activation-5.59e-01

Pos logit contributions
 Ana+0.134
ider+0.131
 Pen+0.128
comb+0.127
 gen+0.127
Neg logit contributions
ock-0.046
ercise-0.041
ams-0.036
ag-0.035
ear-0.034
Token edge
Token ID5743
Feature activation-2.83e+00

Pos logit contributions
 Ana+0.015
 Pen+0.014
 Mir+0.013
illi+0.013
 Megan+0.012
Neg logit contributions
ercise-0.013
ets-0.013
ams-0.012
vious-0.012
ock-0.012
Token of
Token ID286
Feature activation-2.58e+00

Pos logit contributions
 Ana+0.101
 Pen+0.098
 Mir+0.096
 Megan+0.096
 Mil+0.092
Neg logit contributions
ercise-0.053
ets-0.046
ams-0.044
isdom-0.041
ock-0.040
Token the
Token ID262
Feature activation-1.11e+00

Pos logit contributions
 Ana+0.089
 Pen+0.086
igor+0.084
 Jenkins+0.083
 gen+0.081
Neg logit contributions
ock-0.037
ams-0.035
ercise-0.032
ets-0.031
weet-0.029
Token pit
Token ID6028
Feature activation-6.90e+00

Pos logit contributions
 Ana+0.024
 Pen+0.023
 Mir+0.020
 Megan+0.020
 El+0.019
Neg logit contributions
ets-0.035
ercise-0.034
ams-0.033
ock-0.033
vious-0.032
Token and
Token ID290
Feature activation+2.94e+00

Pos logit contributions
 Ana+0.251
 Pen+0.244
 Mir+0.229
 Megan+0.229
 El+0.228
Neg logit contributions
ets-0.116
ams-0.114
ercise-0.108
ock-0.103
vious-0.089
Token leaned
Token ID23831
Feature activation-1.19e-01

Pos logit contributions
ercise+0.072
ets+0.071
ams+0.069
vious+0.063
ock+0.059
Neg logit contributions
 Ana-0.078
 Pen-0.075
 Jenkins-0.074
 plun-0.072
 Lopez-0.072
Token over
Token ID625
Feature activation-3.02e+00

Pos logit contributions
 Ana+0.004
 Pen+0.004
 Mir+0.003
 Megan+0.003
 El+0.003
Neg logit contributions
ercise-0.003
ams-0.003
ets-0.002
ock-0.002
vious-0.002
Token to
Token ID284
Feature activation-3.80e+00

Pos logit contributions
 Ana+0.100
 Pen+0.097
 gen+0.093
 plun+0.091
 Mir+0.091
Neg logit contributions
ercise-0.052
ams-0.051
ets-0.051
ock-0.049
ear-0.044
Token examine
Token ID10716
Feature activation+3.58e-01

Pos logit contributions
 Ana+0.110
 Pen+0.106
 Jenkins+0.105
 Lopez+0.102
 gen+0.101
Neg logit contributions
ercise-0.079
ock-0.077
ets-0.073
ams-0.068
ear-0.067
Token strange
Token ID6283
Feature activation+5.87e-01

Pos logit contributions
 Pen+0.002
 Megan+0.002
 Ana+0.002
stack+0.002
 Mir+0.002
Neg logit contributions
ock-0.002
ercise-0.001
ets-0.001
weet-0.001
ag-0.001
Token noise
Token ID7838
Feature activation-2.48e+00

Pos logit contributions
ets+0.015
ock+0.015
ercise+0.015
ams+0.014
isdom+0.013
Neg logit contributions
 Ana-0.015
 Pen-0.015
 Megan-0.014
 Mir-0.014
 Mil-0.013
Token coming
Token ID2406
Feature activation-4.44e+00

Pos logit contributions
 Ana+0.075
 Pen+0.072
 Mir+0.069
 Megan+0.068
 El+0.067
Neg logit contributions
ets-0.056
ercise-0.054
ams-0.054
ock-0.053
vious-0.047
Token from
Token ID422
Feature activation-4.54e+00

Pos logit contributions
 Ana+0.139
 Pen+0.133
 Megan+0.128
 gen+0.126
 plun+0.125
Neg logit contributions
ock-0.092
ets-0.089
ams-0.084
ercise-0.082
ear-0.079
Token the
Token ID262
Feature activation-1.54e+00

Pos logit contributions
 Ana+0.138
 Pen+0.132
 Mir+0.126
 Megan+0.125
 plun+0.123
Neg logit contributions
ets-0.098
ercise-0.098
ams-0.094
ock-0.093
ear-0.083
Token living
Token ID2877
Feature activation-6.84e+00

Pos logit contributions
 Ana+0.036
 Pen+0.034
 Mir+0.033
 Megan+0.033
 Mil+0.032
Neg logit contributions
ock-0.043
ets-0.043
ercise-0.041
vious-0.038
ams-0.037
Token room
Token ID2119
Feature activation-4.92e+00

Pos logit contributions
 Ana+0.168
 Pen+0.167
 Stev+0.155
 El+0.154
 Megan+0.153
Neg logit contributions
ams-0.176
ets-0.175
ock-0.160
les-0.156
off-0.154
Token.
Token ID13
Feature activation+9.88e-02

Pos logit contributions
 Ana+0.163
 Pen+0.158
 Mir+0.152
 El+0.148
 Megan+0.148
Neg logit contributions
ets-0.100
ams-0.095
ock-0.090
ercise-0.089
vious-0.080
Token She
Token ID1375
Feature activation-1.30e+00

Pos logit contributions
ets+0.002
ercise+0.002
ams+0.002
ear+0.002
isdom+0.002
Neg logit contributions
 Ana-0.003
 Pen-0.003
 gen-0.003
 Mir-0.003
 plun-0.003
Token got
Token ID1392
Feature activation-9.40e-01

Pos logit contributions
 Ana+0.032
 Pen+0.032
stack+0.031
 plun+0.030
 Megan+0.030
Neg logit contributions
ets-0.033
ercise-0.033
ams-0.032
ock-0.031
ear-0.029
Token scared
Token ID12008
Feature activation+7.71e-01

Pos logit contributions
 Ana+0.027
 Pen+0.027
stack+0.026
 Megan+0.026
 Mir+0.025
Neg logit contributions
ercise-0.019
ams-0.019
ets-0.018
vious-0.018
ock-0.017
Token loud
Token ID7812
Feature activation-8.01e-01

Pos logit contributions
 Pen+0.049
 Ana+0.049
 Megan+0.048
 Mir+0.048
stack+0.047
Neg logit contributions
ercise-0.032
ock-0.030
ams-0.030
ets-0.028
weet-0.027
Token noise
Token ID7838
Feature activation-2.35e+00

Pos logit contributions
 Ana+0.020
 Pen+0.019
 Megan+0.018
illi+0.018
 plun+0.017
Neg logit contributions
ock-0.021
ercise-0.020
ets-0.020
ams-0.019
weet-0.019
Token came
Token ID1625
Feature activation-3.25e+00

Pos logit contributions
 Ana+0.065
 Pen+0.062
 Mir+0.059
 Megan+0.058
 Mil+0.056
Neg logit contributions
ets-0.060
ock-0.059
ercise-0.058
ams-0.057
les-0.052
Token from
Token ID422
Feature activation-4.63e+00

Pos logit contributions
 Ana+0.103
 Pen+0.097
 Megan+0.094
 Mir+0.092
 gen+0.092
Neg logit contributions
ets-0.068
ock-0.068
ams-0.066
ercise-0.066
ear-0.058
Token the
Token ID262
Feature activation-1.46e+00

Pos logit contributions
 Ana+0.139
 Pen+0.132
 Mir+0.126
 Megan+0.125
 Mil+0.122
Neg logit contributions
ercise-0.104
ets-0.102
ams-0.100
ock-0.098
isdom-0.087
Token living
Token ID2877
Feature activation-6.79e+00

Pos logit contributions
 Ana+0.034
 Pen+0.032
 Mir+0.031
 El+0.030
 Megan+0.030
Neg logit contributions
ets-0.040
ercise-0.040
ams-0.039
ock-0.039
vious-0.037
Token room
Token ID2119
Feature activation-4.64e+00

Pos logit contributions
 Ana+0.157
 Pen+0.154
 Mir+0.142
 Megan+0.141
 Stev+0.140
Neg logit contributions
ams-0.194
ets-0.187
les-0.170
ock-0.170
ercise-0.168
Token.
Token ID13
Feature activation-4.61e-01

Pos logit contributions
 Ana+0.165
 Pen+0.159
 Mir+0.153
 Megan+0.148
 El+0.148
Neg logit contributions
ets-0.085
ams-0.079
ock-0.072
ercise-0.070
vious-0.063
Token Billy
Token ID15890
Feature activation+8.91e-01

Pos logit contributions
 Ana+0.015
 gen+0.015
 Pen+0.014
 plun+0.014
 teaspoon+0.014
Neg logit contributions
ercise-0.007
ets-0.007
ams-0.007
isdom-0.006
ock-0.006
Token was
Token ID373
Feature activation-2.04e+00

Pos logit contributions
ets+0.021
ercise+0.020
ams+0.020
ock+0.019
les+0.019
Neg logit contributions
 Ana-0.025
 Mir-0.023
 gen-0.023
 Pen-0.023
 Megan-0.023
Token scared
Token ID12008
Feature activation+6.11e-01

Pos logit contributions
 Ana+0.058
stack+0.056
 gen+0.055
 Mir+0.055
 Pen+0.054
Neg logit contributions
 about-0.040
vious-0.037
ets-0.036
ams-0.035
ag-0.035
Token's
Token ID338
Feature activation-3.86e-01

Pos logit contributions
 Ana+0.021
 Pen+0.021
 Megan+0.020
 gen+0.020
 Mir+0.020
Neg logit contributions
ets-0.011
ams-0.010
ock-0.010
ercise-0.010
ear-0.009
Token voice
Token ID3809
Feature activation-3.55e-01

Pos logit contributions
 Pen+0.008
 Ana+0.008
stack+0.007
 plun+0.007
 Megan+0.007
Neg logit contributions
ets-0.011
ams-0.011
ock-0.011
ercise-0.010
ag-0.010
Token from
Token ID422
Feature activation-4.53e+00

Pos logit contributions
 Ana+0.012
 Pen+0.012
 Mir+0.011
 Megan+0.011
 El+0.011
Neg logit contributions
ets-0.007
ams-0.007
ercise-0.007
ock-0.006
vious-0.006
Token inside
Token ID2641
Feature activation-4.32e+00

Pos logit contributions
 Ana+0.118
 Pen+0.113
 Mir+0.105
 gen+0.104
 plun+0.104
Neg logit contributions
ets-0.114
ercise-0.112
ock-0.108
ams-0.106
ear-0.099
Token the
Token ID262
Feature activation-1.02e+00

Pos logit contributions
 Ana+0.142
 gen+0.137
 Pen+0.137
 plun+0.132
 Mir+0.131
Neg logit contributions
ets-0.073
ock-0.070
ams-0.068
ercise-0.061
ear-0.057
Token cabinet
Token ID13447
Feature activation-6.73e+00

Pos logit contributions
 Ana+0.021
 Pen+0.021
 El+0.019
 Mir+0.019
 Megan+0.019
Neg logit contributions
ets-0.032
ercise-0.031
ock-0.029
ams-0.029
vious-0.028
Token.
Token ID13
Feature activation-2.06e+00

Pos logit contributions
 Ana+0.228
 Pen+0.221
 Mir+0.208
 Megan+0.208
 El+0.208
Neg logit contributions
ets-0.129
ams-0.122
ercise-0.112
ock-0.112
vious-0.102
Token He
Token ID679
Feature activation-2.19e+00

Pos logit contributions
illi+0.078
 gen+0.077
 plun+0.076
 teaspoon+0.075
ocated+0.075
Neg logit contributions
ercise-0.017
ets-0.015
vious-0.014
ear-0.014
aw-0.012
Token wanted
Token ID2227
Feature activation+1.64e+00

Pos logit contributions
stack+0.061
 Ana+0.060
 Pen+0.059
 Lopez+0.058
 Jenkins+0.057
Neg logit contributions
ercise-0.047
ets-0.046
ams-0.044
aw-0.042
les-0.041
Token to
Token ID284
Feature activation-3.46e+00

Pos logit contributions
ercise+0.019
ets+0.019
ock+0.017
ams+0.017
ear+0.013
Neg logit contributions
 Ana-0.062
 Pen-0.061
 plun-0.061
stack-0.060
 gen-0.059
Token surprise
Token ID5975
Feature activation+3.31e-01

Pos logit contributions
 Ana+0.099
 Pen+0.097
 Mir+0.092
 plun+0.091
 Jenkins+0.090
Neg logit contributions
ercise-0.073
ets-0.072
ock-0.071
ear-0.066
ams-0.065
Token loud
Token ID7812
Feature activation-7.39e-01

Pos logit contributions
 Pen+0.034
 Ana+0.033
 Megan+0.033
stack+0.033
 Mir+0.033
Neg logit contributions
ercise-0.020
ock-0.019
ay-0.018
ams-0.017
ets-0.017
Token noise
Token ID7838
Feature activation-1.97e+00

Pos logit contributions
 Ana+0.018
 Pen+0.017
 Megan+0.017
illi+0.016
 El+0.016
Neg logit contributions
ock-0.020
ercise-0.019
ets-0.019
ams-0.018
weet-0.018
Token came
Token ID1625
Feature activation-2.79e+00

Pos logit contributions
 Ana+0.052
 Pen+0.050
 Mir+0.047
 Megan+0.047
 Mil+0.045
Neg logit contributions
ets-0.052
ercise-0.051
ock-0.051
ams-0.050
vious-0.046
Token from
Token ID422
Feature activation-4.58e+00

Pos logit contributions
 Ana+0.091
 Pen+0.087
 Megan+0.084
 gen+0.083
 Mir+0.082
Neg logit contributions
ock-0.054
ets-0.054
ams-0.053
ercise-0.051
ear-0.046
Token the
Token ID262
Feature activation-1.24e+00

Pos logit contributions
 Ana+0.142
 Pen+0.135
 Mir+0.129
 gen+0.128
 Megan+0.128
Neg logit contributions
ercise-0.095
ets-0.092
ams-0.088
ock-0.088
isdom-0.078
Token living
Token ID2877
Feature activation-6.73e+00

Pos logit contributions
 Ana+0.027
 Pen+0.025
 Megan+0.025
 Mir+0.024
 El+0.024
Neg logit contributions
ercise-0.035
ets-0.035
ock-0.034
ams-0.033
vious-0.033
Token room
Token ID2119
Feature activation-4.59e+00

Pos logit contributions
 Ana+0.164
 Pen+0.161
comb+0.154
stack+0.154
 Stev+0.154
Neg logit contributions
ams-0.182
ets-0.175
les-0.159
off-0.152
vious-0.151
Token.
Token ID13
Feature activation-3.90e-01

Pos logit contributions
 Ana+0.166
 Pen+0.162
 Mir+0.154
 Flor+0.152
 El+0.151
Neg logit contributions
ets-0.082
ams-0.073
ock-0.066
ercise-0.062
vious-0.061
Token It
Token ID632
Feature activation-1.34e-01

Pos logit contributions
 Ana+0.012
stack+0.012
 Pen+0.011
 plun+0.011
 gen+0.011
Neg logit contributions
ercise-0.007
ams-0.006
ets-0.006
elling-0.006
isdom-0.006
Token was
Token ID373
Feature activation-2.57e+00

Pos logit contributions
 Ana+0.003
 Pen+0.003
 Flor+0.003
 Mir+0.003
stack+0.003
Neg logit contributions
ercise-0.003
ets-0.003
ock-0.003
les-0.003
vious-0.003
Token Daddy
Token ID26926
Feature activation+1.53e+00

Pos logit contributions
 Ana+0.082
 Pen+0.077
stack+0.074
 Megan+0.073
 El+0.073
Neg logit contributions
ock-0.044
ercise-0.044
ams-0.043
ets-0.042
weet-0.040
Token at
Token ID379
Feature activation-2.92e+00

Pos logit contributions
 Ana+0.094
 Pen+0.090
 Mir+0.085
 Megan+0.084
 El+0.083
Neg logit contributions
ercise-0.091
ams-0.090
ets-0.090
ock-0.085
vious-0.078
Token the
Token ID262
Feature activation-1.36e-01

Pos logit contributions
 Ana+0.096
 Pen+0.090
 Megan+0.086
 gen+0.085
 plun+0.085
Neg logit contributions
ercise-0.056
ock-0.055
ets-0.054
ams-0.054
weet-0.046
Token edge
Token ID5743
Feature activation-3.42e+00

Pos logit contributions
 Ana+0.003
 Pen+0.003
 Megan+0.003
 El+0.003
 Mir+0.003
Neg logit contributions
ets-0.004
ercise-0.004
ock-0.004
ams-0.004
vious-0.004
Token of
Token ID286
Feature activation-2.77e+00

Pos logit contributions
 Ana+0.112
 Pen+0.108
 Megan+0.106
 Mir+0.105
 El+0.102
Neg logit contributions
ercise-0.073
ets-0.064
ams-0.062
isdom-0.060
ock-0.057
Token the
Token ID262
Feature activation-9.54e-01

Pos logit contributions
 Ana+0.089
 Pen+0.084
 Megan+0.080
 El+0.079
 Jenkins+0.079
Neg logit contributions
ock-0.053
ercise-0.052
ams-0.052
ets-0.050
weet-0.046
Token pit
Token ID6028
Feature activation-6.71e+00

Pos logit contributions
 Ana+0.016
 Pen+0.015
 Mir+0.013
 Megan+0.013
 El+0.013
Neg logit contributions
ets-0.035
ercise-0.034
ams-0.034
ock-0.033
vious-0.032
Token.
Token ID13
Feature activation+1.51e-01

Pos logit contributions
 Ana+0.210
 Pen+0.204
 Mir+0.191
 Megan+0.190
 El+0.188
Neg logit contributions
ets-0.147
ams-0.145
ercise-0.141
ock-0.134
vious-0.122
Token The
Token ID383
Feature activation-5.92e-01

Pos logit contributions
ercise+0.003
ets+0.003
ams+0.003
isdom+0.002
ock+0.002
Neg logit contributions
 Ana-0.005
 Pen-0.005
 Mir-0.004
 El-0.004
 Megan-0.004
Token lion
Token ID18744
Feature activation-1.33e+00

Pos logit contributions
 Ana+0.016
 Pen+0.016
 Mir+0.015
 Megan+0.015
 El+0.015
Neg logit contributions
ercise-0.015
ets-0.015
ams-0.015
ock-0.014
isdom-0.013
Token was
Token ID373
Feature activation-2.67e+00

Pos logit contributions
 Ana+0.033
 Pen+0.032
 plun+0.030
 Megan+0.030
 Mir+0.030
Neg logit contributions
ams-0.035
ercise-0.035
ets-0.035
ock-0.032
isdom-0.031
Token angry
Token ID7954
Feature activation+2.27e-01

Pos logit contributions
 Ana+0.068
 Pen+0.064
 Megan+0.060
 plun+0.059
 El+0.059
Neg logit contributions
ams-0.069
ercise-0.067
ets-0.066
ock-0.064
weet-0.062
Token balance
Token ID5236
Feature activation+1.55e-01

Pos logit contributions
 Ana+0.031
 Pen+0.030
 Mir+0.028
 Megan+0.028
 El+0.027
Neg logit contributions
ercise-0.034
ets-0.033
ams-0.033
ock-0.031
isdom-0.029
Token and
Token ID290
Feature activation+2.60e+00

Pos logit contributions
ercise+0.004
ams+0.003
ets+0.003
isdom+0.003
elling+0.003
Neg logit contributions
 Ana-0.004
 Pen-0.004
 plun-0.004
 Mir-0.004
 Megan-0.004
Token fell
Token ID3214
Feature activation+6.91e-01

Pos logit contributions
ercise+0.067
ets+0.067
ams+0.064
ock+0.061
 pads+0.058
Neg logit contributions
 Ana-0.070
 Pen-0.065
 Lopez-0.061
 Jenkins-0.061
 Megan-0.061
Token into
Token ID656
Feature activation-4.70e+00

Pos logit contributions
ets+0.014
ams+0.013
ercise+0.013
ock+0.013
vious+0.011
Neg logit contributions
 Ana-0.023
 Pen-0.022
 Megan-0.021
 Mir-0.021
 gen-0.020
Token the
Token ID262
Feature activation-1.36e+00

Pos logit contributions
stack+0.174
ider+0.173
igor+0.172
 Ana+0.171
 Pen+0.167
Neg logit contributions
ock-0.043
ams-0.036
weet-0.032
ear-0.028
vious-0.027
Token pit
Token ID6028
Feature activation-6.67e+00

Pos logit contributions
 Ana+0.026
 Pen+0.025
 Mir+0.022
 El+0.021
 Megan+0.021
Neg logit contributions
ets-0.047
ercise-0.046
ams-0.046
ock-0.044
vious-0.043
Token.
Token ID13
Feature activation-1.17e+00

Pos logit contributions
 Ana+0.225
 Pen+0.218
 Mir+0.205
 El+0.204
 Megan+0.203
Neg logit contributions
ets-0.133
ams-0.125
ock-0.120
ercise-0.115
vious-0.107
Token He
Token ID679
Feature activation-2.11e+00

Pos logit contributions
 Ana+0.039
 Pen+0.037
 gen+0.036
 El+0.036
 plun+0.035
Neg logit contributions
ams-0.019
ets-0.019
ercise-0.019
ock-0.018
ear-0.017
Token screamed
Token ID25421
Feature activation-1.29e+00

Pos logit contributions
 Ana+0.051
 Pen+0.048
 Megan+0.045
 Mir+0.045
 El+0.045
Neg logit contributions
ets-0.061
ercise-0.059
ams-0.059
ock-0.056
vious-0.054
Token and
Token ID290
Feature activation+1.80e+00

Pos logit contributions
 Ana+0.050
 Pen+0.049
 Megan+0.047
 Mir+0.046
 El+0.046
Neg logit contributions
ets-0.019
ercise-0.018
ams-0.017
ock-0.016
ear-0.014
Token cried
Token ID16896
Feature activation-5.80e-01

Pos logit contributions
ets+0.049
ercise+0.047
ams+0.046
ock+0.043
vious+0.042
Neg logit contributions
 Ana-0.045
 Pen-0.042
 Jenkins-0.041
 Lopez-0.041
 Megan-0.040
Token They
Token ID1119
Feature activation-1.12e+00

Pos logit contributions
 Ana+0.092
 Pen+0.088
 Megan+0.086
 gen+0.085
 El+0.083
Neg logit contributions
ercise-0.066
ets-0.066
ams-0.064
ock-0.056
isdom-0.055
Token ran
Token ID4966
Feature activation+5.48e-02

Pos logit contributions
 Ana+0.034
 Pen+0.034
 Mir+0.032
 Megan+0.031
 El+0.031
Neg logit contributions
ets-0.025
ercise-0.024
ams-0.024
ock-0.022
vious-0.022
Token out
Token ID503
Feature activation-3.67e+00

Pos logit contributions
ercise+0.001
ets+0.001
ams+0.001
ock+0.001
isdom+0.001
Neg logit contributions
 Ana-0.002
 Pen-0.002
 Mir-0.002
 Megan-0.002
 El-0.002
Token of
Token ID286
Feature activation-1.21e+00

Pos logit contributions
 Ana+0.152
 Pen+0.149
 Megan+0.142
 Mir+0.142
 El+0.141
Neg logit contributions
ets-0.039
ams-0.038
ercise-0.036
ock-0.035
vious-0.026
Token the
Token ID262
Feature activation-1.16e+00

Pos logit contributions
 Ana+0.038
 Pen+0.037
 Megan+0.035
 Mir+0.035
 El+0.035
Neg logit contributions
ams-0.023
ercise-0.023
ock-0.023
ets-0.023
weet-0.020
Token chamber
Token ID11847
Feature activation-6.67e+00

Pos logit contributions
 Ana+0.019
 Pen+0.018
 Mir+0.017
 plun+0.016
 gen+0.016
Neg logit contributions
ercise-0.042
ets-0.042
ams-0.042
ock-0.040
isdom-0.038
Token and
Token ID290
Feature activation+2.94e+00

Pos logit contributions
 Ana+0.251
 Pen+0.249
 Mir+0.236
 El+0.236
 Megan+0.235
Neg logit contributions
ets-0.102
ams-0.086
ock-0.076
ercise-0.074
ear-0.068
Token back
Token ID736
Feature activation-4.96e-01

Pos logit contributions
ets+0.069
ercise+0.068
ams+0.067
 pads+0.057
ock+0.055
Neg logit contributions
 Ana-0.082
 Pen-0.080
 gen-0.075
 El-0.074
 Mir-0.074
Token to
Token ID284
Feature activation-3.36e+00

Pos logit contributions
 gen+0.020
 Ana+0.020
 Pen+0.019
 plun+0.019
 Maur+0.018
Neg logit contributions
ets-0.005
ams-0.004
ercise-0.004
ear-0.003
off-0.003
Token their
Token ID511
Feature activation-1.35e+00

Pos logit contributions
 Ana+0.116
 Pen+0.114
 gen+0.112
 plun+0.110
comb+0.107
Neg logit contributions
ercise-0.051
ets-0.047
ams-0.046
isdom-0.043
ock-0.042
Token room
Token ID2119
Feature activation-2.83e+00

Pos logit contributions
 Ana+0.034
 Pen+0.034
 Mir+0.032
 El+0.031
 Megan+0.031
Neg logit contributions
ets-0.034
ercise-0.033
ams-0.033
ock-0.029
off-0.029
Token loud
Token ID7812
Feature activation-3.68e-01

Pos logit contributions
 Megan+0.006
 Pen+0.006
stack+0.006
 Ana+0.006
 Mil+0.006
Neg logit contributions
ock-0.003
ercise-0.003
ets-0.003
weet-0.003
ly-0.003
Token noise
Token ID7838
Feature activation-2.56e+00

Pos logit contributions
 Ana+0.009
 Pen+0.009
 Megan+0.009
 Lopez+0.008
 Jenkins+0.008
Neg logit contributions
ock-0.010
ets-0.009
ercise-0.009
weet-0.009
ag-0.008
Token coming
Token ID2406
Feature activation-4.73e+00

Pos logit contributions
 Ana+0.077
 Pen+0.074
 Mir+0.071
 Megan+0.070
 El+0.069
Neg logit contributions
ercise-0.058
ets-0.058
ams-0.057
ock-0.054
isdom-0.049
Token from
Token ID422
Feature activation-4.53e+00

Pos logit contributions
 Ana+0.145
 Pen+0.138
 Megan+0.133
 gen+0.130
 Mir+0.129
Neg logit contributions
ets-0.101
ock-0.100
ams-0.095
ercise-0.095
ear-0.088
Token the
Token ID262
Feature activation-1.38e+00

Pos logit contributions
 Ana+0.136
 Pen+0.130
 Megan+0.124
 Mir+0.123
 gen+0.121
Neg logit contributions
ercise-0.098
ets-0.098
ock-0.093
ams-0.093
ear-0.081
Token living
Token ID2877
Feature activation-6.66e+00

Pos logit contributions
 Ana+0.030
 Megan+0.028
 Pen+0.028
 Mir+0.028
 El+0.028
Neg logit contributions
ock-0.038
ets-0.037
ercise-0.036
vious-0.033
off-0.033
Token room
Token ID2119
Feature activation-4.68e+00

Pos logit contributions
 Ana+0.162
 Pen+0.160
stack+0.154
comb+0.153
 El+0.152
Neg logit contributions
ams-0.169
ets-0.167
ock-0.152
les-0.150
off-0.148
Token.
Token ID13
Feature activation-3.67e-01

Pos logit contributions
 Ana+0.166
 Pen+0.162
 Mir+0.154
 El+0.151
 Megan+0.150
Neg logit contributions
ets-0.088
ams-0.079
ock-0.074
ercise-0.068
vious-0.065
Token They
Token ID1119
Feature activation+2.19e-01

Pos logit contributions
 gen+0.011
 Pen+0.011
 Ana+0.010
stack+0.010
 Mir+0.010
Neg logit contributions
ets-0.008
ercise-0.007
ams-0.007
ly-0.006
ear-0.006
Token went
Token ID1816
Feature activation-6.70e-01

Pos logit contributions
ets+0.005
ercise+0.005
ock+0.005
ams+0.005
ully+0.005
Neg logit contributions
 Ana-0.006
 Pen-0.006
 Megan-0.005
 plun-0.005
 Mir-0.005
Token to
Token ID284
Feature activation-3.41e+00

Pos logit contributions
 Ana+0.026
 Pen+0.025
 gen+0.024
 Mir+0.024
 Megan+0.024
Neg logit contributions
ets-0.009
ercise-0.008
ock-0.007
ams-0.007
ag-0.006
Token could
Token ID714
Feature activation-7.59e-01

Pos logit contributions
 Ana+0.017
 Pen+0.016
 Mir+0.016
 plun+0.015
 Megan+0.015
Neg logit contributions
ets-0.016
ercise-0.016
ams-0.016
ock-0.015
vious-0.014
Token see
Token ID766
Feature activation+8.04e-01

Pos logit contributions
 Ana+0.020
 Pen+0.019
 Jenkins+0.018
 Mir+0.018
 plun+0.018
Neg logit contributions
ets-0.018
ercise-0.018
ock-0.018
ams-0.017
vious-0.016
Token was
Token ID373
Feature activation-1.82e+00

Pos logit contributions
ets+0.021
ams+0.021
ercise+0.020
ock+0.020
les+0.018
Neg logit contributions
 Ana-0.020
 Pen-0.020
 Mir-0.018
 plun-0.018
 Megan-0.018
Token the
Token ID262
Feature activation-1.65e+00

Pos logit contributions
 Ana+0.054
 Pen+0.051
 Mir+0.048
 Megan+0.047
 Jenkins+0.047
Neg logit contributions
ets-0.039
ercise-0.038
ams-0.038
ock-0.036
vious-0.034
Token deep
Token ID2769
Feature activation-3.65e+00

Pos logit contributions
 Ana+0.046
 Pen+0.044
 Mir+0.042
 Megan+0.042
 El+0.040
Neg logit contributions
ets-0.039
ercise-0.039
ock-0.039
ams-0.038
vious-0.035
Token pit
Token ID6028
Feature activation-6.64e+00

Pos logit contributions
 Ana+0.091
 Pen+0.087
 Mir+0.081
 Megan+0.080
 El+0.078
Neg logit contributions
ets-0.102
ercise-0.101
ams-0.101
ock-0.096
vious-0.089
Token.
Token ID13
Feature activation+8.94e-01

Pos logit contributions
 Ana+0.213
 Pen+0.206
 Mir+0.195
 Megan+0.192
 El+0.189
Neg logit contributions
ets-0.140
ams-0.137
ercise-0.134
ock-0.129
vious-0.115
Token
Token ID220
Feature activation+8.51e-01

Pos logit contributions
ams+0.018
ercise+0.017
ets+0.017
ear+0.015
ock+0.015
Neg logit contributions
 Ana-0.027
 gen-0.026
 Pen-0.025
 plun-0.025
 teaspoon-0.024
Token
Token ID198
Feature activation+1.15e+00

Pos logit contributions
ams+0.018
ets+0.018
ercise+0.018
ock+0.017
ear+0.016
Neg logit contributions
 Ana-0.025
 Pen-0.024
 gen-0.024
 plun-0.022
 Megan-0.022
Token
Token ID198
Feature activation+9.74e-01

Pos logit contributions
ams+0.023
ock+0.022
ercise+0.022
ets+0.021
ear+0.021
Neg logit contributions
 Ana-0.035
 Pen-0.033
 gen-0.033
stack-0.032
 plun-0.032
TokenMike
Token ID16073
Feature activation+3.08e-01

Pos logit contributions
ams+0.026
ercise+0.025
ets+0.024
ock+0.024
ear+0.022
Neg logit contributions
 Ana-0.026
 Pen-0.024
 gen-0.023
 Mir-0.023
 plun-0.022
Token a
Token ID257
Feature activation-7.90e-01

Pos logit contributions
ams+0.001
ercise+0.001
ets+0.001
ock+0.001
vious+0.001
Neg logit contributions
 Ana-0.001
 Pen-0.001
 El-0.001
 plun-0.001
stack-0.001
Token loud
Token ID7812
Feature activation-4.07e-01

Pos logit contributions
stack+0.023
 Megan+0.022
 Pen+0.022
 Jenkins+0.022
 Ana+0.022
Neg logit contributions
ock-0.016
ets-0.014
ercise-0.014
ag-0.013
ly-0.013
Token noise
Token ID7838
Feature activation-2.81e+00

Pos logit contributions
 Ana+0.010
 Pen+0.009
 Megan+0.009
 Jenkins+0.009
 Lopez+0.009
Neg logit contributions
ock-0.011
ets-0.011
ercise-0.011
ams-0.010
ag-0.010
Token from
Token ID422
Feature activation-4.89e+00

Pos logit contributions
 Ana+0.093
 Pen+0.090
 Mir+0.085
 Megan+0.085
 El+0.084
Neg logit contributions
ercise-0.056
ets-0.055
ams-0.055
ock-0.051
isdom-0.046
Token the
Token ID262
Feature activation-1.61e+00

Pos logit contributions
 Ana+0.146
 Pen+0.139
 Megan+0.131
 Mir+0.130
 gen+0.130
Neg logit contributions
ercise-0.106
ets-0.106
ock-0.103
ams-0.102
vious-0.089
Token living
Token ID2877
Feature activation-6.63e+00

Pos logit contributions
 Ana+0.042
 Pen+0.039
 Megan+0.038
 Mil+0.038
 El+0.038
Neg logit contributions
ets-0.039
ercise-0.039
ock-0.038
ams-0.035
weet-0.035
Token room
Token ID2119
Feature activation-4.77e+00

Pos logit contributions
 Ana+0.171
 Pen+0.168
comb+0.167
 Stev+0.162
 El+0.160
Neg logit contributions
ams-0.159
ets-0.154
les-0.135
ock-0.133
off-0.133
Token.
Token ID13
Feature activation-1.91e+00

Pos logit contributions
 Ana+0.174
 Pen+0.167
 El+0.158
 Mir+0.157
 Megan+0.156
Neg logit contributions
ets-0.085
ams-0.078
ock-0.073
ercise-0.065
vious-0.061
Token He
Token ID679
Feature activation-2.25e+00

Pos logit contributions
 Ana+0.073
 Pen+0.071
 El+0.069
 gen+0.067
 teaspoon+0.067
Neg logit contributions
ets-0.020
ams-0.020
ercise-0.019
ear-0.018
isdom-0.016
Token ran
Token ID4966
Feature activation+3.15e-01

Pos logit contributions
 Ana+0.061
stack+0.060
 Pen+0.060
 Lopez+0.057
 Jenkins+0.057
Neg logit contributions
ets-0.052
ams-0.051
ercise-0.051
ock-0.047
aw-0.046
Token to
Token ID284
Feature activation-3.99e+00

Pos logit contributions
ets+0.005
ercise+0.005
ams+0.005
ock+0.004
ear+0.004
Neg logit contributions
 Ana-0.012
 Pen-0.011
 Mir-0.011
 gen-0.011
 Megan-0.011
Token and
Token ID290
Feature activation+2.55e+00

Pos logit contributions
ets+0.033
ercise+0.033
ams+0.032
ock+0.030
vious+0.027
Neg logit contributions
 Ana-0.054
 Pen-0.052
 Mir-0.050
 Megan-0.049
 gen-0.049
Token gro
Token ID7128
Feature activation-1.42e-01

Pos logit contributions
ercise+0.060
ets+0.057
ams+0.056
ock+0.053
 pads+0.051
Neg logit contributions
 Ana-0.068
 gen-0.068
 Pen-0.067
 plun-0.066
 Mir-0.064
Tokenoving
Token ID5165
Feature activation+7.23e-01

Pos logit contributions
 Ana+0.004
 Pen+0.004
 Mir+0.004
 Megan+0.004
 El+0.004
Neg logit contributions
ercise-0.003
ets-0.003
ams-0.003
ock-0.003
isdom-0.003
Token around
Token ID1088
Feature activation-2.24e+00

Pos logit contributions
ets+0.014
ercise+0.014
ams+0.014
ock+0.013
ear+0.011
Neg logit contributions
 Ana-0.024
 Pen-0.023
 gen-0.022
 Mir-0.022
 plun-0.022
Token the
Token ID262
Feature activation-1.96e+00

Pos logit contributions
 Ana+0.076
 gen+0.076
 Pen+0.074
 Mir+0.073
 plun+0.072
Neg logit contributions
ets-0.037
ock-0.032
ams-0.032
ercise-0.031
ear-0.028
Token living
Token ID2877
Feature activation-6.62e+00

Pos logit contributions
 Ana+0.048
 Pen+0.045
 Mir+0.045
 Megan+0.044
 El+0.043
Neg logit contributions
ets-0.056
ercise-0.055
ams-0.054
ock-0.053
vious-0.049
Token room
Token ID2119
Feature activation-4.87e+00

Pos logit contributions
 Ana+0.160
 Pen+0.159
 Mir+0.152
 Stev+0.147
 gen+0.146
Neg logit contributions
ams-0.186
ets-0.185
les-0.162
ercise-0.158
ock-0.158
Token.
Token ID13
Feature activation+3.00e-01

Pos logit contributions
 Ana+0.167
 Pen+0.164
 Mir+0.158
 gen+0.154
 plun+0.152
Neg logit contributions
ets-0.095
ams-0.083
ock-0.076
ercise-0.074
vious-0.068
Token And
Token ID843
Feature activation+1.39e+00

Pos logit contributions
ets+0.006
ercise+0.006
ams+0.006
ock+0.006
isdom+0.006
Neg logit contributions
 Ana-0.009
 gen-0.009
 Pen-0.008
 plun-0.008
 Mir-0.008
Token they
Token ID484
Feature activation+9.44e-01

Pos logit contributions
ets+0.031
ams+0.030
ercise+0.030
ock+0.028
ear+0.025
Neg logit contributions
 Ana-0.041
 Pen-0.040
 plun-0.038
 Mir-0.038
 gen-0.038
Token had
Token ID550
Feature activation+2.25e+00

Pos logit contributions
ets+0.023
ercise+0.022
ams+0.022
ock+0.021
vious+0.019
Neg logit contributions
 Ana-0.027
 Pen-0.026
 Mir-0.025
 plun-0.025
 gen-0.025
Token a
Token ID257
Feature activation-2.90e+00

Pos logit contributions
 Ana+0.054
 Pen+0.051
 Megan+0.048
 Jenkins+0.048
 El+0.048
Neg logit contributions
ets-0.034
ercise-0.034
ams-0.032
ock-0.030
ear-0.027
Token big
Token ID1263
Feature activation-1.86e+00

Pos logit contributions
 Ana+0.087
 Pen+0.086
 El+0.084
 Megan+0.083
 Mir+0.079
Neg logit contributions
ercise-0.059
ets-0.056
ock-0.052
 poems-0.050
ams-0.050
Token box
Token ID3091
Feature activation-3.01e+00

Pos logit contributions
 Ana+0.046
 Pen+0.044
 Megan+0.042
 El+0.041
 Mir+0.040
Neg logit contributions
ets-0.051
ercise-0.051
ams-0.049
ock-0.048
isdom-0.046
Token in
Token ID287
Feature activation-4.20e+00

Pos logit contributions
 Ana+0.094
 Pen+0.090
 Mir+0.086
 Megan+0.085
 El+0.085
Neg logit contributions
ets-0.066
ams-0.064
ercise-0.064
ock-0.061
vious-0.054
Token the
Token ID262
Feature activation-1.20e+00

Pos logit contributions
 Ana+0.130
 Pen+0.125
 plun+0.118
 Megan+0.117
 El+0.117
Neg logit contributions
ams-0.086
ercise-0.083
ets-0.083
ock-0.082
ear-0.072
Token living
Token ID2877
Feature activation-6.61e+00

Pos logit contributions
 Ana+0.027
 Pen+0.026
 El+0.024
 Megan+0.024
 Mir+0.023
Neg logit contributions
ets-0.036
ercise-0.036
ams-0.035
ock-0.033
off-0.031
Token room
Token ID2119
Feature activation-4.44e+00

Pos logit contributions
 Ana+0.150
 Pen+0.147
 Megan+0.136
 El+0.135
stack+0.129
Neg logit contributions
ams-0.200
ets-0.196
ercise-0.181
ock-0.176
off-0.171
Token.
Token ID13
Feature activation-1.64e+00

Pos logit contributions
 Ana+0.147
 Pen+0.141
 plun+0.134
 Mir+0.134
 El+0.134
Neg logit contributions
ets-0.091
ams-0.088
ercise-0.080
ock-0.078
ear-0.072
Token It
Token ID632
Feature activation-9.24e-01

Pos logit contributions
 Ana+0.044
 Pen+0.042
 Megan+0.040
 plun+0.040
 gen+0.039
Neg logit contributions
ercise-0.041
ets-0.040
ams-0.040
ock-0.037
ear-0.036
Token has
Token ID468
Feature activation+5.25e-01

Pos logit contributions
 Ana+0.027
 Jenkins+0.026
 Pen+0.026
 Megan+0.026
 Lopez+0.025
Neg logit contributions
ets-0.021
ercise-0.019
ams-0.018
elling-0.017
ock-0.017
Token a
Token ID257
Feature activation-2.08e+00

Pos logit contributions
ets+0.013
ercise+0.013
ams+0.013
ock+0.012
isdom+0.011
Neg logit contributions
 Ana-0.015
 Pen-0.014
 Megan-0.013
 Mir-0.013
 El-0.013
Token ice
Token ID4771
Feature activation-2.23e+00

Pos logit contributions
 Ana+0.032
 Pen+0.029
 Mir+0.028
 Megan+0.028
 El+0.028
Neg logit contributions
ercise-0.037
ets-0.036
ams-0.036
ock-0.035
vious-0.032
Token cream
Token ID8566
Feature activation-3.73e+00

Pos logit contributions
 Ana+0.065
 Pen+0.062
 Mir+0.059
 El+0.058
 Megan+0.058
Neg logit contributions
ams-0.054
ets-0.053
ercise-0.053
ock-0.050
vious-0.045
Token out
Token ID503
Feature activation-5.35e+00

Pos logit contributions
 Ana+0.113
 Pen+0.107
 Mir+0.102
 El+0.102
 Megan+0.100
Neg logit contributions
ets-0.086
ams-0.086
ercise-0.084
ock-0.081
vious-0.073
Token of
Token ID286
Feature activation-2.54e+00

Pos logit contributions
 Ana+0.172
 Pen+0.165
 Mir+0.157
 Megan+0.157
 El+0.155
Neg logit contributions
ercise-0.113
ets-0.108
ams-0.108
ock-0.101
isdom-0.094
Token the
Token ID262
Feature activation-1.49e+00

Pos logit contributions
 Ana+0.081
 Pen+0.077
 El+0.072
 Mir+0.071
 plun+0.071
Neg logit contributions
ams-0.052
ercise-0.049
ets-0.048
ock-0.047
isdom-0.041
Token freezer
Token ID30967
Feature activation-6.57e+00

Pos logit contributions
 Ana+0.033
 Pen+0.030
 Mir+0.028
 El+0.028
 Megan+0.028
Neg logit contributions
ams-0.046
ets-0.046
ercise-0.045
ock-0.043
vious-0.040
Token again
Token ID757
Feature activation-9.32e-01

Pos logit contributions
 Ana+0.225
 Pen+0.217
 El+0.206
 Mir+0.204
 Megan+0.199
Neg logit contributions
ets-0.128
ams-0.126
ock-0.110
ercise-0.109
vious-0.099
Token.
Token ID13
Feature activation-8.86e-01

Pos logit contributions
 Ana+0.027
 Pen+0.026
 Mir+0.025
 Megan+0.024
 El+0.024
Neg logit contributions
ercise-0.022
ets-0.022
ams-0.022
ock-0.021
isdom-0.019
Token They
Token ID1119
Feature activation-4.05e-01

Pos logit contributions
 Ana+0.025
 Pen+0.024
 plun+0.024
 gen+0.023
 Megan+0.023
Neg logit contributions
ets-0.020
ams-0.020
ercise-0.019
ock-0.018
ear-0.017
Token also
Token ID635
Feature activation+2.97e+00

Pos logit contributions
 Ana+0.012
 Pen+0.012
 Mir+0.011
 plun+0.011
 Megan+0.011
Neg logit contributions
ets-0.009
ercise-0.009
ams-0.009
ock-0.008
vious-0.008
Token learned
Token ID4499
Feature activation+2.77e+00

Pos logit contributions
ets+0.062
ercise+0.062
ams+0.060
ock+0.055
vious+0.052
Neg logit contributions
 Ana-0.097
 Pen-0.093
 Megan-0.088
 Mir-0.088
 El-0.087
Token Tom
Token ID4186
Feature activation-2.81e-01

Pos logit contributions
 Ana+0.022
 Pen+0.021
 Mir+0.019
 Megan+0.019
 El+0.019
Neg logit contributions
ercise-0.021
ets-0.021
ams-0.021
ock-0.020
isdom-0.018
Token and
Token ID290
Feature activation+1.89e+00

Pos logit contributions
 Ana+0.008
 Pen+0.008
 Mir+0.007
 Megan+0.007
 El+0.007
Neg logit contributions
ets-0.007
ercise-0.007
ams-0.007
ock-0.006
vious-0.006
Token came
Token ID1625
Feature activation-2.85e+00

Pos logit contributions
ock+0.036
ets+0.034
ams+0.032
ly+0.031
ercise+0.031
Neg logit contributions
stack-0.058
comb-0.055
fire-0.053
 Lopez-0.052
 Jenkins-0.052
Token to
Token ID284
Feature activation-4.77e+00

Pos logit contributions
 Ana+0.103
 gen+0.103
 Pen+0.100
stack+0.099
 Megan+0.096
Neg logit contributions
ets-0.040
ock-0.039
ams-0.039
ercise-0.036
ear-0.033
Token the
Token ID262
Feature activation-2.09e+00

Pos logit contributions
stack+0.160
 Ana+0.157
comb+0.152
ider+0.150
 Pen+0.149
Neg logit contributions
ock-0.068
ercise-0.068
ear-0.063
ets-0.061
off-0.060
Token living
Token ID2877
Feature activation-6.56e+00

Pos logit contributions
 Ana+0.052
 Pen+0.048
 El+0.048
 Megan+0.048
 Mil+0.047
Neg logit contributions
ercise-0.052
ets-0.051
ock-0.050
off-0.048
vious-0.046
Token room
Token ID2119
Feature activation-4.75e+00

Pos logit contributions
comb+0.170
 Pen+0.167
stack+0.167
 Ana+0.166
 El+0.161
Neg logit contributions
ams-0.156
ets-0.148
off-0.137
les-0.136
ock-0.134
Token.
Token ID13
Feature activation-2.07e+00

Pos logit contributions
 Ana+0.174
 Pen+0.170
 El+0.162
 Mir+0.162
 gen+0.158
Neg logit contributions
ets-0.079
ams-0.071
ock-0.065
ercise-0.058
vious-0.057
Token She
Token ID1375
Feature activation-2.16e+00

Pos logit contributions
 Ana+0.067
 gen+0.065
 Pen+0.065
 El+0.062
 plun+0.060
Neg logit contributions
ercise-0.035
ets-0.035
ams-0.031
vious-0.031
elling-0.031
Token saw
Token ID2497
Feature activation-1.04e+00

Pos logit contributions
 Ana+0.065
 Pen+0.064
stack+0.064
comb+0.063
 Lopez+0.062
Neg logit contributions
ams-0.039
ercise-0.039
ets-0.038
ock-0.036
les-0.033
Token Lily
Token ID20037
Feature activation-4.97e-01

Pos logit contributions
 Ana+0.030
 Pen+0.030
 El+0.027
 Megan+0.027
 Mir+0.027
Neg logit contributions
ets-0.023
ams-0.023
ercise-0.023
ock-0.023
vious-0.021
Tokenily
Token ID813
Feature activation-1.25e+00

Pos logit contributions
 Ana+0.033
 Pen+0.032
 Mir+0.029
 El+0.029
 Megan+0.029
Neg logit contributions
ets-0.036
ercise-0.035
ams-0.035
ock-0.034
vious-0.031
Token ran
Token ID4966
Feature activation+6.70e-02

Pos logit contributions
 Ana+0.036
 Pen+0.035
stack+0.034
 plun+0.034
 Mir+0.034
Neg logit contributions
ercise-0.027
ets-0.027
ams-0.026
vious-0.024
ock-0.024
Token back
Token ID736
Feature activation-1.17e+00

Pos logit contributions
ets+0.001
ercise+0.001
ams+0.001
ock+0.001
ear+0.001
Neg logit contributions
 Ana-0.002
 Pen-0.002
 Mir-0.002
 gen-0.002
 El-0.002
Token to
Token ID284
Feature activation-4.01e+00

Pos logit contributions
 Ana+0.045
 gen+0.045
 Pen+0.044
 plun+0.043
stack+0.043
Neg logit contributions
ets-0.012
ams-0.012
ercise-0.011
ock-0.010
ear-0.010
Token the
Token ID262
Feature activation-1.25e+00

Pos logit contributions
 gen+0.147
fire+0.146
igor+0.142
ider+0.139
comb+0.138
Neg logit contributions
ock-0.039
ercise-0.035
 yours-0.035
isdom-0.034
ossible-0.034
Token cabinet
Token ID13447
Feature activation-6.54e+00

Pos logit contributions
 Ana+0.030
 Pen+0.029
 El+0.029
 Mir+0.028
 Mil+0.028
Neg logit contributions
ercise-0.031
ets-0.030
off-0.027
ock-0.027
vious-0.027
Token and
Token ID290
Feature activation+3.05e+00

Pos logit contributions
 Ana+0.256
 Pen+0.249
 El+0.238
 Mir+0.238
 Megan+0.238
Neg logit contributions
ets-0.090
ams-0.084
ercise-0.078
ock-0.075
vious-0.067
Token looked
Token ID3114
Feature activation-8.77e-02

Pos logit contributions
ets+0.065
ercise+0.064
ams+0.060
 pads+0.053
vious+0.052
Neg logit contributions
 Pen-0.083
 Ana-0.083
 Jenkins-0.082
 Lopez-0.080
 plun-0.080
Token again
Token ID757
Feature activation+1.44e-01

Pos logit contributions
 Ana+0.003
 Pen+0.003
 Megan+0.003
 Mir+0.003
 El+0.003
Neg logit contributions
ercise-0.002
ams-0.002
ets-0.001
ock-0.001
isdom-0.001
Token.
Token ID13
Feature activation-1.51e+00

Pos logit contributions
ercise+0.004
ets+0.004
ams+0.004
ock+0.003
vious+0.003
Neg logit contributions
 Ana-0.004
 Pen-0.004
 Mir-0.004
 Megan-0.004
 El-0.004
Token She
Token ID1375
Feature activation-1.93e+00

Pos logit contributions
 gen+0.046
 Pen+0.045
 Ana+0.045
stack+0.043
 plun+0.042
Neg logit contributions
ets-0.030
ercise-0.029
ear-0.027
isdom-0.026
ams-0.025
Token and
Token ID290
Feature activation+3.09e+00

Pos logit contributions
 Ana+0.017
 Pen+0.017
 gen+0.016
 Megan+0.016
 Mir+0.016
Neg logit contributions
ets-0.007
ams-0.006
ock-0.006
ercise-0.006
ear-0.005
Token found
Token ID1043
Feature activation+1.17e-01

Pos logit contributions
ets+0.060
ams+0.056
ercise+0.055
ock+0.049
vious+0.045
Neg logit contributions
stack-0.092
 Pen-0.092
 Jenkins-0.090
 Ana-0.089
 Lopez-0.088
Token them
Token ID606
Feature activation-4.05e-01

Pos logit contributions
ets+0.002
ercise+0.002
ock+0.002
ams+0.002
elling+0.002
Neg logit contributions
 Ana-0.004
 Pen-0.004
 Jenkins-0.004
 Megan-0.004
stack-0.004
Token behind
Token ID2157
Feature activation-1.57e+00

Pos logit contributions
 Ana+0.013
 Pen+0.013
 Mir+0.013
 Mil+0.012
 gen+0.012
Neg logit contributions
ets-0.008
ams-0.007
ercise-0.007
ock-0.007
ag-0.006
Token the
Token ID262
Feature activation-1.58e+00

Pos logit contributions
 Ana+0.055
 Pen+0.052
 Mir+0.051
 gen+0.051
 Mil+0.049
Neg logit contributions
ets-0.026
ock-0.024
ams-0.024
ercise-0.023
les-0.020
Token cabinet
Token ID13447
Feature activation-6.53e+00

Pos logit contributions
 Pen+0.032
 Ana+0.032
 Megan+0.030
 Mir+0.030
 El+0.029
Neg logit contributions
ets-0.044
ock-0.043
les-0.038
ercise-0.038
ams-0.038
Token.
Token ID13
Feature activation-1.87e+00

Pos logit contributions
 Ana+0.255
 Pen+0.253
 Mei+0.239
 El+0.239
 Stev+0.238
Neg logit contributions
ets-0.089
ams-0.070
ock-0.055
vious-0.054
aw-0.054
Token She
Token ID1375
Feature activation-2.23e+00

Pos logit contributions
 Ana+0.052
 Pen+0.051
 gen+0.050
 Megan+0.048
 El+0.047
Neg logit contributions
ets-0.044
ercise-0.043
ams-0.041
ock-0.038
vious-0.038
Token was
Token ID373
Feature activation-1.91e+00

Pos logit contributions
 Pen+0.063
stack+0.063
 Ana+0.062
 Lopez+0.061
 drown+0.060
Neg logit contributions
ams-0.044
ets-0.042
ercise-0.042
ock-0.039
les-0.037
Token not
Token ID407
Feature activation+1.81e-01

Pos logit contributions
 Ana+0.055
stack+0.052
 El+0.052
 Pen+0.051
 plun+0.050
Neg logit contributions
ams-0.039
ag-0.037
 about-0.037
ets-0.036
ercise-0.036
Token happy
Token ID3772
Feature activation+2.26e+00

Pos logit contributions
ams+0.004
ets+0.003
ock+0.003
ag+0.003
weet+0.003
Neg logit contributions
stack-0.006
 Ana-0.006
 Pen-0.006
 El-0.006
 Me-0.006
Token.
Token ID13
Feature activation+6.84e-01

Pos logit contributions
ercise+0.077
ams+0.075
ets+0.074
ock+0.072
isdom+0.067
Neg logit contributions
 Ana-0.093
 Pen-0.090
 Mir-0.085
 El-0.083
 Megan-0.083
Token She
Token ID1375
Feature activation-4.41e-01

Pos logit contributions
ercise+0.017
ets+0.017
ams+0.016
ock+0.015
isdom+0.015
Neg logit contributions
 Ana-0.018
 Pen-0.018
 gen-0.017
 Mir-0.017
 plun-0.017
Token gathered
Token ID9272
Feature activation+2.24e+00

Pos logit contributions
 Ana+0.012
 Pen+0.012
 Megan+0.011
 Mir+0.011
 plun+0.011
Neg logit contributions
ercise-0.011
ets-0.011
ams-0.011
ock-0.010
isdom-0.009
Token a
Token ID257
Feature activation+5.42e-01

Pos logit contributions
ercise+0.051
ets+0.051
ams+0.051
ock+0.048
isdom+0.044
Neg logit contributions
 Ana-0.068
 Pen-0.065
 Mir-0.062
 Megan-0.062
 El-0.061
Token hammer
Token ID15554
Feature activation+1.24e+00

Pos logit contributions
ercise+0.014
ets+0.014
ams+0.013
ock+0.013
isdom+0.012
Neg logit contributions
 Ana-0.014
 Pen-0.014
 Megan-0.013
 Mir-0.013
 El-0.013
Token and
Token ID290
Feature activation+4.48e+00

Pos logit contributions
ercise+0.026
ams+0.025
ets+0.024
ock+0.022
isdom+0.022
Neg logit contributions
 Ana-0.039
 Pen-0.038
 Mir-0.037
 El-0.037
 Megan-0.036
Token her
Token ID607
Feature activation-1.51e-01

Pos logit contributions
ets+0.122
ercise+0.122
ams+0.121
ock+0.116
isdom+0.107
Neg logit contributions
 Ana-0.115
 Pen-0.110
 Mir-0.104
 El-0.101
 Megan-0.101
Token toy
Token ID13373
Feature activation+4.42e-01

Pos logit contributions
 Ana+0.004
 Pen+0.004
 Megan+0.003
 Mir+0.003
 gen+0.003
Neg logit contributions
ercise-0.004
ams-0.004
ets-0.004
isdom-0.004
ock-0.004
Token tool
Token ID2891
Feature activation-4.08e-01

Pos logit contributions
ercise+0.012
ets+0.012
ams+0.011
ock+0.011
ully+0.010
Neg logit contributions
 Ana-0.012
 Pen-0.011
 Megan-0.011
 Mir-0.010
 Mei-0.010
Tokenbox
Token ID3524
Feature activation-6.67e-01

Pos logit contributions
 Ana+0.012
 Pen+0.012
 Megan+0.011
 Mir+0.011
 Mei+0.011
Neg logit contributions
ets-0.009
ercise-0.009
ams-0.009
ock-0.008
 pads-0.008
Token,
Token ID11
Feature activation-2.23e-01

Pos logit contributions
 Ana+0.022
 Pen+0.022
 Mir+0.021
 Megan+0.020
 Mei+0.020
Neg logit contributions
ets-0.013
ams-0.013
ercise-0.012
ock-0.011
isdom-0.010
Token Christmas
Token ID6786
Feature activation-3.69e-01

Pos logit contributions
ercise+0.035
ets+0.033
ams+0.033
ock+0.029
isdom+0.029
Neg logit contributions
 Ana-0.054
 Pen-0.053
 Megan-0.050
 Mir-0.050
 gen-0.050
Token ever
Token ID1683
Feature activation+2.93e+00

Pos logit contributions
 Ana+0.011
 Pen+0.011
 Mir+0.010
 Megan+0.010
 El+0.010
Neg logit contributions
ets-0.008
ercise-0.008
ams-0.008
ock-0.008
isdom-0.007
Token.
Token ID13
Feature activation-7.99e-01

Pos logit contributions
ercise+0.097
ams+0.084
isdom+0.084
ock+0.081
ully+0.081
Neg logit contributions
 Ana-0.057
 Pen-0.056
 Megan-0.053
 Ell-0.052
 Mir-0.051
Token<|endoftext|>
Token ID50256
Feature activation-1.87e+00

Pos logit contributions
 Ana+0.021
 Pen+0.020
 plun+0.020
 Megan+0.019
 gen+0.019
Neg logit contributions
ets-0.020
ercise-0.020
ams-0.020
ock-0.018
isdom-0.017
TokenTom
Token ID13787
Feature activation+1.27e+00

Pos logit contributions
 Ana+0.048
 Pen+0.044
 Mir+0.044
stack+0.044
 gen+0.044
Neg logit contributions
ock-0.045
ets-0.045
ams-0.045
ercise-0.044
les-0.041
Token and
Token ID290
Feature activation+4.69e+00

Pos logit contributions
ercise+0.026
ets+0.026
ams+0.025
ock+0.024
isdom+0.022
Neg logit contributions
 Ana-0.041
 Pen-0.040
 Mir-0.038
 Megan-0.038
 El-0.037
Token Lily
Token ID20037
Feature activation+1.98e+00

Pos logit contributions
ets+0.135
ercise+0.129
ams+0.125
ock+0.125
elling+0.115
Neg logit contributions
 Ana-0.121
 Pen-0.119
 Mir-0.113
 Megan-0.111
 El-0.109
Token were
Token ID547
Feature activation+3.72e-01

Pos logit contributions
ets+0.049
ercise+0.049
ams+0.049
ock+0.046
vious+0.042
Neg logit contributions
 Ana-0.055
 Pen-0.052
 Mir-0.050
 Megan-0.049
 plun-0.049
Token having
Token ID1719
Feature activation+2.09e+00

Pos logit contributions
ercise+0.011
ets+0.010
ams+0.010
ock+0.010
isdom+0.009
Neg logit contributions
 Ana-0.009
 Pen-0.009
 Mir-0.008
 Megan-0.008
 El-0.008
Token lunch
Token ID9965
Feature activation-7.61e-01

Pos logit contributions
ercise+0.059
ets+0.058
ams+0.057
ock+0.055
isdom+0.052
Neg logit contributions
 Ana-0.052
 Pen-0.050
 Mir-0.047
 Megan-0.047
 El-0.046
Token with
Token ID351
Feature activation+1.56e+00

Pos logit contributions
 Ana+0.023
 Pen+0.022
 Mir+0.021
 Megan+0.020
 El+0.020
Neg logit contributions
ets-0.017
ercise-0.017
ams-0.017
ock-0.016
isdom-0.015
Token of
Token ID286
Feature activation-1.94e+00

Pos logit contributions
 Ana+0.049
 Pen+0.047
 plun+0.045
 Mir+0.044
 El+0.044
Neg logit contributions
ets-0.037
ams-0.036
ercise-0.036
ock-0.034
ear-0.031
Token all
Token ID477
Feature activation+3.22e+00

Pos logit contributions
 Ana+0.062
 Pen+0.059
 Mir+0.057
 Megan+0.056
 El+0.056
Neg logit contributions
ercise-0.041
ets-0.041
ams-0.040
ock-0.038
isdom-0.034
Token.
Token ID13
Feature activation-5.26e-01

Pos logit contributions
ercise+0.090
ams+0.086
ets+0.084
ock+0.081
isdom+0.077
Neg logit contributions
 Ana-0.084
 Pen-0.082
 Megan-0.077
 Mir-0.076
 El-0.074
Token<|endoftext|>
Token ID50256
Feature activation-1.83e+00

Pos logit contributions
 Ana+0.013
 Pen+0.013
 Mir+0.012
 Megan+0.012
 El+0.012
Neg logit contributions
ercise-0.015
ets-0.015
ams-0.015
ock-0.014
isdom-0.013
TokenTom
Token ID13787
Feature activation+1.65e+00

Pos logit contributions
 Ana+0.044
 Pen+0.041
 Mir+0.040
 Megan+0.039
 gen+0.039
Neg logit contributions
ets-0.050
ock-0.049
ercise-0.049
ams-0.049
vious-0.045
Token and
Token ID290
Feature activation+5.13e+00

Pos logit contributions
ercise+0.046
ets+0.045
ams+0.045
ock+0.043
isdom+0.040
Neg logit contributions
 Ana-0.040
 Pen-0.039
 Mir-0.037
 Megan-0.036
 El-0.035
Token Lily
Token ID20037
Feature activation+2.37e+00

Pos logit contributions
ets+0.166
ercise+0.156
ams+0.155
ock+0.155
elling+0.144
Neg logit contributions
 Ana-0.111
 Pen-0.110
 Mir-0.103
 Megan-0.103
 Ell-0.103
Token are
Token ID389
Feature activation+2.90e-02

Pos logit contributions
ercise+0.065
ams+0.065
ets+0.064
ock+0.062
isdom+0.059
Neg logit contributions
 Ana-0.057
 Pen-0.055
 El-0.052
 Megan-0.051
 Mir-0.051
Token young
Token ID1862
Feature activation+1.60e-01

Pos logit contributions
ercise+0.001
ets+0.001
ock+0.001
ams+0.001
isdom+0.001
Neg logit contributions
 Ana-0.001
 Pen-0.001
 Mir-0.001
 Megan-0.001
 Ell-0.001
Token twins
Token ID20345
Feature activation+3.32e-01

Pos logit contributions
ams+0.003
ets+0.002
ercise+0.002
ock+0.002
isdom+0.002
Neg logit contributions
 Ana-0.006
 Pen-0.005
 plun-0.005
 Mir-0.005
 Megan-0.005
Token who
Token ID508
Feature activation+2.53e+00

Pos logit contributions
ets+0.007
ams+0.007
ercise+0.007
ock+0.006
isdom+0.006
Neg logit contributions
 Ana-0.011
 Pen-0.010
 Mir-0.010
 plun-0.010
 Megan-0.010
Token forg
Token ID5784
Feature activation+4.58e+00

Pos logit contributions
ercise+0.004
ets+0.004
ams+0.004
ock+0.003
vious+0.003
Neg logit contributions
 Ana-0.005
 Pen-0.005
 Mir-0.005
 Megan-0.004
 El-0.004
Tokenave
Token ID1015
Feature activation+8.69e-01

Pos logit contributions
ercise+0.097
ams+0.093
opl+0.093
 yours+0.086
isdom+0.086
Neg logit contributions
 Ana-0.112
 plun-0.111
 sob-0.106
 slammed-0.105
 Pen-0.102
Token him
Token ID683
Feature activation-9.46e-01

Pos logit contributions
ets+0.019
ercise+0.019
ams+0.018
ock+0.016
vious+0.016
Neg logit contributions
 Ana-0.027
 Pen-0.026
 Mir-0.025
 Megan-0.025
 Ell-0.025
Token and
Token ID290
Feature activation+4.00e+00

Pos logit contributions
 Ana+0.029
 Pen+0.028
 Mir+0.027
 Jenkins+0.026
 Megan+0.026
Neg logit contributions
ercise-0.021
ams-0.020
ets-0.019
ock-0.018
isdom-0.017
Token they
Token ID484
Feature activation+2.21e+00

Pos logit contributions
ercise+0.096
ams+0.094
ets+0.094
ock+0.087
isdom+0.082
Neg logit contributions
 Ana-0.115
 Pen-0.110
 Megan-0.103
 Mir-0.103
 El-0.102
Token all
Token ID477
Feature activation+4.66e+00

Pos logit contributions
ercise+0.048
ets+0.048
ams+0.047
ock+0.045
isdom+0.041
Neg logit contributions
 Ana-0.069
 Pen-0.066
 Mir-0.063
 Megan-0.062
 El-0.062
Token played
Token ID2826
Feature activation+2.36e-01

Pos logit contributions
ercise+0.120
ets+0.118
ams+0.117
ock+0.113
isdom+0.107
Neg logit contributions
 Ana-0.123
 Pen-0.117
 Megan-0.113
 Ell-0.111
 El-0.110
Token together
Token ID1978
Feature activation+1.57e+00

Pos logit contributions
ercise+0.005
ets+0.005
ams+0.005
ock+0.005
isdom+0.004
Neg logit contributions
 Ana-0.007
 Pen-0.007
 Mir-0.007
 Megan-0.007
 El-0.007
Token with
Token ID351
Feature activation+8.24e-01

Pos logit contributions
ercise+0.037
ets+0.037
ams+0.036
ock+0.034
isdom+0.031
Neg logit contributions
 Ana-0.046
 Pen-0.044
 Mir-0.042
 Megan-0.042
 El-0.041
Token Lily
Token ID20037
Feature activation+1.61e+00

Pos logit contributions
ercise+0.019
ams+0.019
ets+0.019
ock+0.018
isdom+0.016
Neg logit contributions
 Ana-0.024
 Pen-0.023
 Mir-0.022
 Megan-0.022
 El-0.022
Token's
Token ID338
Feature activation-4.75e-01

Pos logit contributions
ercise+0.038
ams+0.037
ets+0.036
ock+0.035
isdom+0.032
Neg logit contributions
 Ana-0.047
 Pen-0.046
 Mir-0.043
 Megan-0.042
 El-0.042
Token mom
Token ID1995
Feature activation+2.28e+00

Pos logit contributions
 Ana+0.023
 Pen+0.021
 El+0.020
 Mir+0.020
 Megan+0.020
Neg logit contributions
ams-0.026
ercise-0.026
ets-0.024
ock-0.024
isdom-0.023
Token sat
Token ID3332
Feature activation-1.05e+00

Pos logit contributions
ercise+0.055
ets+0.055
ams+0.055
ock+0.052
vious+0.047
Neg logit contributions
 Ana-0.066
 Pen-0.063
 Mir-0.060
 Megan-0.059
 plun-0.058
Token on
Token ID319
Feature activation-1.86e+00

Pos logit contributions
 Ana+0.032
 Pen+0.031
 Mir+0.030
 Megan+0.029
 El+0.029
Neg logit contributions
ercise-0.024
ams-0.023
ets-0.023
ock-0.022
isdom-0.020
Token a
Token ID257
Feature activation+1.28e+00

Pos logit contributions
 Ana+0.055
 Pen+0.052
 Mir+0.050
 Megan+0.050
 El+0.049
Neg logit contributions
ercise-0.042
ams-0.041
ets-0.041
ock-0.039
isdom-0.036
Token bench
Token ID7624
Feature activation-2.52e+00

Pos logit contributions
ercise+0.048
ets+0.048
ams+0.048
ock+0.046
isdom+0.044
Neg logit contributions
 Ana-0.020
 Pen-0.018
 Mir-0.016
 Megan-0.016
 El-0.016
Token and
Token ID290
Feature activation+4.04e+00

Pos logit contributions
 Ana+0.092
 Pen+0.089
 Mir+0.086
 Megan+0.085
 El+0.084
Neg logit contributions
ets-0.041
ams-0.040
ercise-0.039
ock-0.036
isdom-0.031
Token ate
Token ID15063
Feature activation+1.10e+00

Pos logit contributions
ercise+0.088
ams+0.087
ets+0.085
ock+0.076
 pads+0.071
Neg logit contributions
 Ana-0.119
 plun-0.114
 Pen-0.113
 gen-0.112
 Mir-0.109
Token the
Token ID262
Feature activation+1.52e+00

Pos logit contributions
ercise+0.025
ams+0.025
ets+0.025
ock+0.023
isdom+0.021
Neg logit contributions
 Ana-0.033
 Pen-0.031
 Mir-0.030
 Megan-0.029
 El-0.029
Token big
Token ID1263
Feature activation-6.17e-02

Pos logit contributions
ercise+0.039
ets+0.039
ams+0.039
ock+0.037
isdom+0.034
Neg logit contributions
 Ana-0.041
 Pen-0.039
 Mir-0.037
 Megan-0.037
 El-0.037
Token ice
Token ID4771
Feature activation-3.63e-01

Pos logit contributions
 Ana+0.002
 Pen+0.002
 Megan+0.001
 Mir+0.001
 El+0.001
Neg logit contributions
ets-0.002
ercise-0.002
ams-0.002
ock-0.002
isdom-0.001
Token cream
Token ID8566
Feature activation-1.86e+00

Pos logit contributions
 Ana+0.010
 Pen+0.010
 Mir+0.009
 Megan+0.009
 El+0.009
Neg logit contributions
ercise-0.009
ets-0.009
ams-0.009
ock-0.008
isdom-0.008
Token seen
Token ID1775
Feature activation+2.01e+00

Pos logit contributions
ercise+0.111
ets+0.106
ams+0.105
ock+0.101
isdom+0.098
Neg logit contributions
 Ana-0.103
 Pen-0.098
 Mir-0.094
 Megan-0.093
 Mil-0.090
Token snow
Token ID6729
Feature activation-2.11e+00

Pos logit contributions
ercise+0.055
ets+0.055
ams+0.054
ock+0.049
isdom+0.048
Neg logit contributions
 Ana-0.053
 Pen-0.051
 Mir-0.048
 El-0.047
 Megan-0.047
Token before
Token ID878
Feature activation-2.58e+00

Pos logit contributions
 Ana+0.060
 Pen+0.057
 Megan+0.054
 Mir+0.054
 El+0.053
Neg logit contributions
ock-0.050
ets-0.050
ams-0.049
ercise-0.048
les-0.042
Token.
Token ID13
Feature activation-8.27e-01

Pos logit contributions
 Ana+0.086
 Pen+0.082
 gen+0.079
 Megan+0.079
 Mir+0.078
Neg logit contributions
ets-0.048
ams-0.046
ercise-0.046
ock-0.045
isdom-0.039
Token
Token ID198
Feature activation+8.06e-01

Pos logit contributions
 Ana+0.021
 Pen+0.020
 Mir+0.019
 Megan+0.018
 El+0.018
Neg logit contributions
ercise-0.024
ets-0.023
ams-0.023
ock-0.023
isdom-0.021
Token
Token ID198
Feature activation+5.21e-01

Pos logit contributions
ets+0.022
ercise+0.021
ams+0.021
ock+0.020
vious+0.019
Neg logit contributions
 Ana-0.022
 Pen-0.021
 Mir-0.020
 Megan-0.019
 El-0.019
TokenThey
Token ID2990
Feature activation-7.24e-01

Pos logit contributions
ets+0.015
ercise+0.014
ams+0.014
ock+0.014
vious+0.014
Neg logit contributions
 Ana-0.013
 Pen-0.012
 Mir-0.012
 Megan-0.011
 El-0.011
Token drove
Token ID10357
Feature activation+1.36e+00

Pos logit contributions
 Ana+0.021
 Pen+0.020
 Mir+0.019
 plun+0.019
 Megan+0.019
Neg logit contributions
ets-0.017
ams-0.017
ercise-0.017
ock-0.016
vious-0.015
Token for
Token ID329
Feature activation-1.52e+00

Pos logit contributions
ercise+0.029
ets+0.028
ams+0.028
ock+0.026
isdom+0.024
Neg logit contributions
 Ana-0.044
 Pen-0.042
 Mir-0.040
 Megan-0.040
 El-0.040
Token a
Token ID257
Feature activation+5.11e-02

Pos logit contributions
 Ana+0.044
 Pen+0.043
 Megan+0.040
stack+0.040
 El+0.040
Neg logit contributions
ets-0.035
ercise-0.035
ams-0.033
ock-0.033
ear-0.029
Token long
Token ID890
Feature activation+9.25e-01

Pos logit contributions
ets+0.001
ercise+0.001
ams+0.001
ock+0.001
isdom+0.001
Neg logit contributions
 Ana-0.002
 Pen-0.001
 Megan-0.001
 Mir-0.001
 El-0.001
Token could
Token ID714
Feature activation-1.31e+00

Pos logit contributions
 Ana+0.007
 Pen+0.006
 Megan+0.006
 Mir+0.006
 Jenkins+0.006
Neg logit contributions
ets-0.005
ams-0.005
ercise-0.005
ock-0.005
vious-0.004
Token.
Token ID13
Feature activation+2.34e-03

Pos logit contributions
 Ana+0.041
 Pen+0.039
 Mir+0.037
 Megan+0.037
 El+0.037
Neg logit contributions
ets-0.029
ercise-0.028
ams-0.028
ock-0.027
ear-0.024
Token They
Token ID1119
Feature activation-2.66e-01

Pos logit contributions
ets+0.000
ercise+0.000
ams+0.000
ear+0.000
 pads+0.000
Neg logit contributions
 gen-0.000
 teaspoon-0.000
 Ana-0.000
 Pen-0.000
 plun-0.000
Token passed
Token ID3804
Feature activation+1.56e+00

Pos logit contributions
 Ana+0.007
 Pen+0.007
 gen+0.007
 Jenkins+0.007
 Mir+0.007
Neg logit contributions
ets-0.006
ams-0.006
ercise-0.006
ock-0.005
 pads-0.005
Token many
Token ID867
Feature activation+5.63e-01

Pos logit contributions
ets+0.031
ams+0.030
ercise+0.029
ock+0.028
ear+0.025
Neg logit contributions
 Ana-0.050
 Pen-0.048
 gen-0.048
 plun-0.047
stack-0.047
Token kids
Token ID3988
Feature activation+6.22e-01

Pos logit contributions
ercise+0.011
ams+0.011
ets+0.011
ock+0.010
isdom+0.010
Neg logit contributions
 Ana-0.019
 Pen-0.018
 Mir-0.017
 Megan-0.017
 El-0.017
Token.
Token ID13
Feature activation-8.12e-01

Pos logit contributions
ets+0.013
ams+0.012
ercise+0.012
ock+0.011
ear+0.010
Neg logit contributions
 Ana-0.020
 Pen-0.020
 gen-0.019
 Mir-0.019
 plun-0.019
Token They
Token ID1119
Feature activation-6.27e-01

Pos logit contributions
 gen+0.025
 Pen+0.025
 Ana+0.025
 plun+0.024
 teaspoon+0.023
Neg logit contributions
ets-0.016
ercise-0.015
ams-0.015
ock-0.013
ear-0.013
Token were
Token ID547
Feature activation-1.59e+00

Pos logit contributions
 Ana+0.017
 Pen+0.017
 Mir+0.016
 plun+0.016
 Megan+0.016
Neg logit contributions
ets-0.015
ercise-0.014
ams-0.014
ock-0.014
vious-0.013
Token almost
Token ID2048
Feature activation+1.43e+00

Pos logit contributions
 Ana+0.044
 Pen+0.042
 plun+0.041
 gen+0.040
stack+0.040
Neg logit contributions
ams-0.039
ets-0.038
ercise-0.036
ock-0.034
weet-0.032
Token at
Token ID379
Feature activation-2.38e+00

Pos logit contributions
ercise+0.033
ets+0.033
ams+0.033
ock+0.031
isdom+0.028
Neg logit contributions
 Ana-0.042
 Pen-0.041
 Mir-0.039
 Megan-0.039
 El-0.038
Token mom
Token ID1995
Feature activation+1.71e+00

Pos logit contributions
ercise+0.023
ets+0.023
ams+0.022
ock+0.021
isdom+0.020
Neg logit contributions
 Ana-0.026
 Pen-0.025
 Mir-0.024
 Megan-0.023
 El-0.023
Token about
Token ID546
Feature activation-7.51e-01

Pos logit contributions
ercise+0.041
ets+0.037
ams+0.035
vious+0.034
isdom+0.033
Neg logit contributions
 Ana-0.052
 Pen-0.050
 Megan-0.049
 Mir-0.049
 Ell-0.047
Token their
Token ID511
Feature activation-1.22e+00

Pos logit contributions
 Ana+0.022
 Pen+0.021
 Mir+0.020
 Megan+0.020
 plun+0.019
Neg logit contributions
ercise-0.018
ets-0.017
ams-0.017
ock-0.016
isdom-0.015
Token dream
Token ID4320
Feature activation+1.09e+00

Pos logit contributions
 Ana+0.038
 Pen+0.036
 Mir+0.034
 Megan+0.034
 El+0.034
Neg logit contributions
ercise-0.027
ets-0.027
ams-0.027
ock-0.025
isdom-0.022
Token.
Token ID13
Feature activation-1.06e+00

Pos logit contributions
ercise+0.026
ams+0.026
ets+0.025
ock+0.024
isdom+0.022
Neg logit contributions
 Ana-0.032
 Pen-0.030
 Mir-0.029
 Megan-0.028
 El-0.028
Token
Token ID198
Feature activation+5.05e-01

Pos logit contributions
 Ana+0.030
 Pen+0.029
 plun+0.029
 gen+0.029
 El+0.027
Neg logit contributions
ams-0.022
ercise-0.022
ets-0.022
ear-0.020
isdom-0.020
Token
Token ID198
Feature activation+2.52e-01

Pos logit contributions
ercise+0.013
ams+0.012
ets+0.012
ock+0.012
ear+0.011
Neg logit contributions
 Ana-0.014
 Pen-0.013
 Megan-0.012
 Mir-0.012
 plun-0.012
TokenMom
Token ID29252
Feature activation+1.35e+00

Pos logit contributions
ercise+0.005
ams+0.005
ets+0.005
ock+0.005
ear+0.004
Neg logit contributions
 Ana-0.008
 Pen-0.008
 Mir-0.007
 El-0.007
 Megan-0.007
Token smiled
Token ID13541
Feature activation+1.30e+00

Pos logit contributions
ets+0.030
ams+0.030
ock+0.030
ercise+0.030
les+0.026
Neg logit contributions
 Ana-0.039
 Pen-0.037
 plun-0.037
stack-0.035
 Mir-0.035
Token and
Token ID290
Feature activation+2.45e+00

Pos logit contributions
ercise+0.030
ets+0.028
ams+0.028
ock+0.026
isdom+0.025
Neg logit contributions
 Ana-0.041
 Pen-0.039
 Mir-0.038
 El-0.037
 Megan-0.036
Token hugged
Token ID41130
Feature activation+9.92e-01

Pos logit contributions
ercise+0.050
ams+0.048
ets+0.048
ock+0.045
isdom+0.041
Neg logit contributions
 Ana-0.076
 Pen-0.072
 plun-0.072
 Jenkins-0.071
stack-0.070
Token trees
Token ID7150
Feature activation-5.10e-01

Pos logit contributions
ercise+0.019
ets+0.019
ams+0.019
ock+0.018
vious+0.016
Neg logit contributions
 Ana-0.026
 Pen-0.025
 Mir-0.024
 Megan-0.024
 plun-0.023
Token.
Token ID13
Feature activation+1.85e+00

Pos logit contributions
 Ana+0.014
 Pen+0.014
 Mir+0.013
 El+0.013
 Megan+0.013
Neg logit contributions
ercise-0.013
ets-0.012
ams-0.012
ock-0.012
isdom-0.011
Token He
Token ID679
Feature activation-5.46e-01

Pos logit contributions
ercise+0.044
ets+0.043
ams+0.043
ock+0.040
isdom+0.037
Neg logit contributions
 Ana-0.054
 Pen-0.052
 Mir-0.049
 Megan-0.049
 El-0.049
Token noticed
Token ID6810
Feature activation+2.06e+00

Pos logit contributions
 Ana+0.014
 Pen+0.013
 plun+0.013
 Mir+0.012
 gen+0.012
Neg logit contributions
ercise-0.015
ets-0.014
ams-0.014
ock-0.013
isdom-0.013
Token a
Token ID257
Feature activation-1.05e+00

Pos logit contributions
ets+0.056
ercise+0.055
ams+0.054
ock+0.050
isdom+0.048
Neg logit contributions
 Ana-0.054
 Pen-0.052
 El-0.049
 Mir-0.049
 Megan-0.049
Token rabbit
Token ID22746
Feature activation+3.97e-01

Pos logit contributions
 Ana+0.031
 Pen+0.031
 Mir+0.031
 Megan+0.030
 El+0.029
Neg logit contributions
ercise-0.020
ock-0.020
ams-0.019
ets-0.019
weet-0.018
Token hopping
Token ID47153
Feature activation+1.36e+00

Pos logit contributions
ercise+0.010
ets+0.010
ams+0.009
ock+0.009
isdom+0.008
Neg logit contributions
 Ana-0.011
 Pen-0.011
 Mir-0.010
 Megan-0.010
 El-0.010
Token around
Token ID1088
Feature activation-1.76e+00

Pos logit contributions
ercise+0.030
ams+0.030
ets+0.029
isdom+0.028
ock+0.026
Neg logit contributions
 Ana-0.041
 Pen-0.040
 El-0.039
 plun-0.038
 Megan-0.038
Token.
Token ID13
Feature activation+1.17e+00

Pos logit contributions
 Ana+0.059
 Pen+0.058
 Mir+0.055
 gen+0.054
 Megan+0.054
Neg logit contributions
ercise-0.031
ets-0.031
ams-0.030
ock-0.029
ear-0.025
Token He
Token ID679
Feature activation-1.00e+00

Pos logit contributions
ercise+0.026
ets+0.026
ams+0.025
ock+0.024
vious+0.022
Neg logit contributions
 Ana-0.035
 Pen-0.034
 Mir-0.032
 Megan-0.032
 gen-0.032
Token was
Token ID373
Feature activation-1.36e+00

Pos logit contributions
 Ana+0.025
 Pen+0.024
 Mir+0.023
 plun+0.023
 Megan+0.022
Neg logit contributions
ercise-0.028
ets-0.027
ams-0.027
ock-0.025
isdom-0.024
Token scared
Token ID12008
Feature activation+1.26e+00

Pos logit contributions
 Ana+0.006
 Pen+0.006
stack+0.006
 plun+0.006
 Jenkins+0.006
Neg logit contributions
ams-0.006
ets-0.006
ercise-0.006
vious-0.006
ear-0.006
Token!
Token ID0
Feature activation-1.15e-01

Pos logit contributions
ercise+0.030
ams+0.029
ets+0.028
ock+0.025
isdom+0.025
Neg logit contributions
 Ana-0.039
 Pen-0.037
 El-0.036
 Mir-0.035
 Megan-0.035
Token Then
Token ID3244
Feature activation-1.56e+00

Pos logit contributions
 Ana+0.003
 gen+0.003
 plun+0.003
 Pen+0.003
 Mir+0.003
Neg logit contributions
ets-0.002
ercise-0.002
ams-0.002
vious-0.002
ear-0.002
Token the
Token ID262
Feature activation-1.66e+00

Pos logit contributions
 Ana+0.051
 Pen+0.049
 plun+0.049
 Megan+0.047
 Mir+0.047
Neg logit contributions
ercise-0.030
ams-0.028
ets-0.027
ock-0.024
isdom-0.024
Token hunter
Token ID19177
Feature activation-7.68e-01

Pos logit contributions
 Ana+0.043
 Pen+0.042
 Mir+0.039
 Megan+0.038
 El+0.038
Neg logit contributions
ets-0.045
ercise-0.045
ams-0.045
ock-0.042
isdom-0.039
Token noticed
Token ID6810
Feature activation+7.95e-01

Pos logit contributions
 Ana+0.021
 Pen+0.021
 Megan+0.020
 Mir+0.019
 plun+0.019
Neg logit contributions
ets-0.019
ercise-0.019
ams-0.018
ock-0.017
vious-0.017
Token her
Token ID607
Feature activation-1.75e+00

Pos logit contributions
ercise+0.017
ets+0.016
ams+0.016
ock+0.016
isdom+0.014
Neg logit contributions
 Ana-0.025
 Pen-0.024
 Megan-0.022
 Mir-0.022
 plun-0.022
Token and
Token ID290
Feature activation+3.32e+00

Pos logit contributions
 Ana+0.052
 Pen+0.050
 Mir+0.048
 Megan+0.048
 Mil+0.046
Neg logit contributions
ets-0.039
ercise-0.038
ams-0.038
ock-0.036
ully-0.034
Token smiled
Token ID13541
Feature activation+1.61e+00

Pos logit contributions
ercise+0.072
ams+0.069
ets+0.066
ock+0.063
vious+0.059
Neg logit contributions
 Ana-0.098
 Pen-0.095
 plun-0.092
 Megan-0.091
 Jenkins-0.090
Token.
Token ID13
Feature activation-3.23e-01

Pos logit contributions
ercise+0.041
ets+0.041
ams+0.040
ock+0.038
isdom+0.036
Neg logit contributions
 Ana-0.044
 Pen-0.042
 Mir-0.040
 El-0.040
 Megan-0.040
Token He
Token ID679
Feature activation-1.33e+00

Pos logit contributions
 Ana+0.009
 Pen+0.009
 plun+0.009
 gen+0.009
 Megan+0.009
Neg logit contributions
ercise-0.007
ets-0.007
ams-0.007
ock-0.006
ear-0.006
Token little
Token ID1310
Feature activation+8.59e-01

Pos logit contributions
 Ana+0.020
 Megan+0.020
 Pen+0.019
stack+0.019
 El+0.018
Neg logit contributions
ercise-0.011
ock-0.011
ams-0.011
ets-0.010
weet-0.010
Token girl
Token ID2576
Feature activation-1.01e+00

Pos logit contributions
ercise+0.025
ams+0.024
ock+0.024
ets+0.024
vious+0.022
Neg logit contributions
 Ana-0.019
 Pen-0.019
 Megan-0.018
 Mir-0.017
 El-0.017
Token named
Token ID3706
Feature activation+1.89e+00

Pos logit contributions
 Ana+0.027
 Pen+0.026
 Mir+0.025
 Megan+0.024
 El+0.024
Neg logit contributions
ercise-0.027
ets-0.027
ams-0.026
ock-0.025
vious-0.023
Token Lucy
Token ID22162
Feature activation+9.70e-02

Pos logit contributions
ets+0.045
ercise+0.043
ams+0.042
weet+0.042
ock+0.042
Neg logit contributions
 gen-0.049
 plun-0.047
 Ana-0.047
stack-0.047
 Pen-0.046
Token.
Token ID13
Feature activation+1.36e+00

Pos logit contributions
ercise+0.002
ets+0.002
ams+0.002
ock+0.002
isdom+0.002
Neg logit contributions
 Ana-0.003
 Pen-0.003
 Mir-0.002
 Megan-0.002
 El-0.002
Token She
Token ID1375
Feature activation-8.39e-01

Pos logit contributions
ets+0.033
ercise+0.032
ams+0.031
ock+0.031
vious+0.028
Neg logit contributions
 Ana-0.035
 plun-0.035
 gen-0.035
 Mir-0.034
 Pen-0.033
Token was
Token ID373
Feature activation-1.11e+00

Pos logit contributions
 Ana+0.025
 Pen+0.025
 Mir+0.023
 Megan+0.023
 El+0.023
Neg logit contributions
ercise-0.019
ets-0.019
ams-0.018
ock-0.017
isdom-0.016
Token only
Token ID691
Feature activation+5.41e-01

Pos logit contributions
 Ana+0.031
 Pen+0.030
stack+0.029
 Megan+0.029
 plun+0.029
Neg logit contributions
ams-0.023
ercise-0.023
ets-0.022
vious-0.021
ock-0.021
Token three
Token ID1115
Feature activation-1.35e-02

Pos logit contributions
ets+0.012
ams+0.012
ercise+0.012
ock+0.011
vious+0.011
Neg logit contributions
stack-0.015
 gen-0.014
 Ana-0.014
 Pen-0.013
 plun-0.013
Token years
Token ID812
Feature activation-6.05e-02

Pos logit contributions
 Ana+0.000
 Pen+0.000
 Mir+0.000
 Megan+0.000
 El+0.000
Neg logit contributions
ercise-0.000
ets-0.000
ams-0.000
ock-0.000
isdom-0.000
Token old
Token ID1468
Feature activation+6.42e-01

Pos logit contributions
 Ana+0.002
 Pen+0.002
 Mir+0.002
 Megan+0.002
 El+0.002
Neg logit contributions
ercise-0.002
ets-0.001
ams-0.001
ock-0.001
isdom-0.001
Token woman
Token ID2415
Feature activation+1.30e+00

Pos logit contributions
ams+0.050
ercise+0.048
ock+0.047
isdom+0.044
weet+0.043
Neg logit contributions
 plun-0.072
 Ana-0.072
igor-0.069
 Jenkins-0.068
ocated-0.068
Token didn
Token ID1422
Feature activation+1.09e+00

Pos logit contributions
ets+0.033
ams+0.032
ercise+0.030
ock+0.029
vious+0.028
Neg logit contributions
 Ana-0.035
 Pen-0.034
 plun-0.034
 Mir-0.033
 Jenkins-0.032
Token't
Token ID470
Feature activation+1.91e+00

Pos logit contributions
ercise+0.035
ets+0.035
ock+0.034
ams+0.033
ear+0.032
Neg logit contributions
 Ana-0.022
 Pen-0.020
 Mir-0.019
 Megan-0.018
 El-0.018
Token know
Token ID760
Feature activation+1.23e+00

Pos logit contributions
ets+0.043
ercise+0.043
ams+0.042
ock+0.040
vious+0.036
Neg logit contributions
 Ana-0.058
 Pen-0.056
 Mir-0.053
 Megan-0.053
 El-0.052
Token what
Token ID644
Feature activation-9.19e-01

Pos logit contributions
ets+0.018
ams+0.018
ercise+0.018
ock+0.017
isdom+0.016
Neg logit contributions
 Ana-0.043
 Pen-0.042
 plun-0.042
 Jenkins-0.040
stack-0.040
Token to
Token ID284
Feature activation-3.20e+00

Pos logit contributions
 Ana+0.033
 Pen+0.032
 plun+0.031
 Mir+0.031
stack+0.031
Neg logit contributions
ercise-0.014
ets-0.013
ams-0.012
isdom-0.012
ock-0.011
Token do
Token ID466
Feature activation-1.49e+00

Pos logit contributions
 Ana+0.077
 Pen+0.073
 Mir+0.069
 plun+0.067
 Megan+0.067
Neg logit contributions
ets-0.092
ercise-0.091
ams-0.090
ock-0.087
isdom-0.082
Token,
Token ID11
Feature activation-1.84e+00

Pos logit contributions
 Ana+0.045
 Pen+0.044
 Mir+0.041
 Megan+0.041
 El+0.041
Neg logit contributions
ets-0.034
ercise-0.033
ams-0.033
ock-0.031
isdom-0.028
Token so
Token ID523
Feature activation+1.12e+00

Pos logit contributions
 Ana+0.056
 Pen+0.054
 Mir+0.051
 Megan+0.051
 plun+0.050
Neg logit contributions
ets-0.041
ams-0.040
ercise-0.040
ock-0.038
vious-0.034
Token they
Token ID484
Feature activation+5.80e-01

Pos logit contributions
ams+0.028
ets+0.028
ercise+0.028
ock+0.026
isdom+0.024
Neg logit contributions
 Ana-0.029
 Pen-0.028
 plun-0.028
 gen-0.027
 Mir-0.026
Token decided
Token ID3066
Feature activation+1.39e+00

Pos logit contributions
ets+0.013
ercise+0.012
ams+0.012
ock+0.011
vious+0.010
Neg logit contributions
 Ana-0.018
 Pen-0.018
 Mir-0.017
 Megan-0.017
 plun-0.017
TokenQu
Token ID4507
Feature activation+1.44e+00

Pos logit contributions
ercise+0.021
ets+0.021
ams+0.021
ock+0.020
isdom+0.018
Neg logit contributions
 Ana-0.023
 Pen-0.022
 Mir-0.021
 Megan-0.021
 El-0.021
Tokenack
Token ID441
Feature activation+6.25e-01

Pos logit contributions
ercise+0.034
ams+0.031
ets+0.030
ock+0.029
isdom+0.028
Neg logit contributions
 Ana-0.043
 Pen-0.039
 Megan-0.039
 Mil-0.038
 plun-0.038
Token was
Token ID373
Feature activation-1.83e+00

Pos logit contributions
ets+0.018
ercise+0.017
ams+0.017
ock+0.016
vious+0.015
Neg logit contributions
 Ana-0.015
 Pen-0.015
 Mir-0.014
 Megan-0.014
 El-0.013
Token sad
Token ID6507
Feature activation+1.06e+00

Pos logit contributions
 Ana+0.048
 Pen+0.046
 Mir+0.043
 Megan+0.042
 El+0.042
Neg logit contributions
ams-0.048
ercise-0.048
ets-0.048
ock-0.045
vious-0.043
Token because
Token ID780
Feature activation-1.10e+00

Pos logit contributions
ercise+0.023
ams+0.022
ets+0.021
ock+0.019
isdom+0.018
Neg logit contributions
 Ana-0.035
 Pen-0.033
 Mir-0.032
 El-0.032
 Megan-0.032
Token he
Token ID339
Feature activation-3.21e-01

Pos logit contributions
 Ana+0.036
 Pen+0.035
 plun+0.033
 Mir+0.033
stack+0.032
Neg logit contributions
ams-0.021
ercise-0.019
ets-0.019
ock-0.019
ear-0.017
Token wanted
Token ID2227
Feature activation+2.44e+00

Pos logit contributions
 Ana+0.008
 Pen+0.008
 Mir+0.008
 Megan+0.007
 El+0.007
Neg logit contributions
ercise-0.009
ets-0.009
ams-0.009
ock-0.008
isdom-0.008
Token to
Token ID284
Feature activation-2.84e+00

Pos logit contributions
ercise+0.044
ets+0.044
ams+0.044
ock+0.040
isdom+0.036
Neg logit contributions
 Ana-0.085
 Pen-0.082
 Mir-0.079
 Megan-0.078
 El-0.078
Token swim
Token ID9422
Feature activation+1.72e+00

Pos logit contributions
 Ana+0.078
 Pen+0.074
 Mir+0.070
 Megan+0.070
 El+0.068
Neg logit contributions
ercise-0.072
ets-0.071
ams-0.069
ock-0.068
isdom-0.062
Token in
Token ID287
Feature activation-2.52e+00

Pos logit contributions
ercise+0.041
ets+0.040
ams+0.040
ock+0.038
isdom+0.035
Neg logit contributions
 Ana-0.050
 Pen-0.048
 Megan-0.046
 Mir-0.045
 El-0.045
Token the
Token ID262
Feature activation+8.30e-01

Pos logit contributions
 Ana+0.073
 Pen+0.071
 Mir+0.067
 Megan+0.066
 El+0.065
Neg logit contributions
ets-0.058
ercise-0.058
ams-0.058
ock-0.055
vious-0.050
Token and
Token ID290
Feature activation+2.19e+00

Pos logit contributions
 Ana+0.006
 Pen+0.006
 Mir+0.006
 Megan+0.006
 El+0.006
Neg logit contributions
ercise-0.005
ets-0.005
ams-0.005
ock-0.004
isdom-0.004
Token Tommy
Token ID19919
Feature activation+9.35e-01

Pos logit contributions
ercise+0.057
ams+0.054
ets+0.053
ock+0.052
vious+0.048
Neg logit contributions
 Ana-0.060
 Pen-0.056
 Megan-0.053
 Mir-0.052
 Jenkins-0.051
Tokenâ
Token ID22940
Feature activation+2.80e+00

Pos logit contributions
ets+0.025
ercise+0.023
ams+0.023
ock+0.022
 pads+0.022
Neg logit contributions
 Ana-0.025
 Pen-0.023
 Mir-0.023
 Megan-0.023
 gen-0.023
Token
Token ID26391
Feature activation-7.27e-01

Pos logit contributions
ercise+0.067
ams+0.066
ets+0.066
ock+0.062
isdom+0.057
Neg logit contributions
 Ana-0.080
 Pen-0.078
 Mir-0.073
 Megan-0.073
 El-0.072
Token
Token ID8151
Feature activation+1.90e+00

Pos logit contributions
 Ana+0.019
 Pen+0.018
 Mir+0.017
 Megan+0.017
 El+0.017
Neg logit contributions
ercise-0.019
ams-0.019
ets-0.019
ock-0.018
isdom-0.017
Tokens
Token ID82
Feature activation-9.24e-01

Pos logit contributions
ercise+0.044
ets+0.044
ams+0.044
ock+0.041
isdom+0.037
Neg logit contributions
 Ana-0.056
 Pen-0.054
 Mir-0.051
 Megan-0.051
 El-0.050
Token hat
Token ID6877
Feature activation+1.07e+00

Pos logit contributions
 Ana+0.024
 Pen+0.023
 Mir+0.022
 Megan+0.021
 El+0.021
Neg logit contributions
ets-0.025
ercise-0.025
ams-0.025
ock-0.024
isdom-0.021
Token flew
Token ID13112
Feature activation+1.60e+00

Pos logit contributions
ets+0.031
ercise+0.029
ams+0.029
ock+0.028
vious+0.027
Neg logit contributions
 Ana-0.027
 Pen-0.026
 Mir-0.024
 Megan-0.024
 El-0.023
Token off
Token ID572
Feature activation-3.52e+00

Pos logit contributions
ercise+0.037
ams+0.037
ets+0.036
ock+0.034
isdom+0.033
Neg logit contributions
 Ana-0.047
 Pen-0.046
 El-0.043
 Mir-0.043
 Megan-0.043
Token.
Token ID13
Feature activation+1.76e-01

Pos logit contributions
 Ana+0.117
 Pen+0.112
 Mir+0.107
 Megan+0.106
 gen+0.106
Neg logit contributions
ets-0.065
ams-0.062
ock-0.062
ercise-0.060
ear-0.053
Token His
Token ID2399
Feature activation-8.63e-01

Pos logit contributions
ercise+0.004
ams+0.004
ets+0.004
ock+0.004
isdom+0.003
Neg logit contributions
 Ana-0.005
 Pen-0.005
 Mir-0.005
 Megan-0.005
 El-0.005
Token Lily
Token ID20037
Feature activation-9.46e-02

Pos logit contributions
ets+0.007
ercise+0.007
ams+0.006
ock+0.006
vious+0.006
Neg logit contributions
 Ana-0.010
 Pen-0.010
 gen-0.009
 Mir-0.009
 Megan-0.009
Token was
Token ID373
Feature activation-1.58e+00

Pos logit contributions
 Ana+0.002
 Mir+0.002
 Pen+0.002
 Megan+0.002
 gen+0.002
Neg logit contributions
ets-0.003
ercise-0.002
ams-0.002
ock-0.002
vious-0.002
Token sad
Token ID6507
Feature activation+1.06e+00

Pos logit contributions
 Ana+0.039
 Pen+0.036
 Mir+0.034
 Megan+0.034
 El+0.033
Neg logit contributions
ets-0.044
ams-0.043
ercise-0.043
ock-0.041
vious-0.041
Token and
Token ID290
Feature activation+1.82e+00

Pos logit contributions
ercise+0.024
ams+0.022
ets+0.021
ock+0.019
isdom+0.019
Neg logit contributions
 Ana-0.034
 Pen-0.032
 Mir-0.032
 El-0.031
 Ell-0.031
Token cried
Token ID16896
Feature activation+6.79e-02

Pos logit contributions
ercise+0.052
ets+0.051
ams+0.050
ock+0.048
vious+0.045
Neg logit contributions
 Ana-0.045
 Pen-0.043
 Mir-0.040
 Megan-0.040
 El-0.039
Token because
Token ID780
Feature activation-4.59e-01

Pos logit contributions
ets+0.001
ercise+0.001
ams+0.001
ock+0.001
isdom+0.001
Neg logit contributions
 Ana-0.002
 Pen-0.002
 Mir-0.002
 Megan-0.002
 El-0.002
Token all
Token ID477
Feature activation+2.33e+00

Pos logit contributions
 Ana+0.011
 Pen+0.011
 Mir+0.010
 Megan+0.010
 El+0.010
Neg logit contributions
ercise-0.013
ets-0.013
ams-0.013
ock-0.012
isdom-0.012
Token her
Token ID607
Feature activation-1.21e+00

Pos logit contributions
ercise+0.065
ams+0.062
ets+0.062
isdom+0.056
ear+0.055
Neg logit contributions
 Ana-0.064
 Pen-0.062
 Megan-0.058
 Mir-0.057
 El-0.056
Token hard
Token ID1327
Feature activation+6.76e-01

Pos logit contributions
 Ana+0.035
 Pen+0.034
 Mir+0.032
 Megan+0.032
 El+0.032
Neg logit contributions
ercise-0.029
ets-0.029
ams-0.028
ock-0.027
vious-0.024
Token work
Token ID670
Feature activation-8.65e-01

Pos logit contributions
ercise+0.018
ams+0.017
ock+0.017
ets+0.016
vious+0.015
Neg logit contributions
 Ana-0.018
 Pen-0.017
 Mir-0.016
 El-0.016
 plun-0.016
Token was
Token ID373
Feature activation-2.11e+00

Pos logit contributions
 Ana+0.021
 Pen+0.020
 Mir+0.020
 Megan+0.019
 El+0.019
Neg logit contributions
ets-0.026
ams-0.024
ercise-0.024
ock-0.024
vious-0.022
Token hurt
Token ID5938
Feature activation+4.29e-01

Pos logit contributions
ercise+0.082
ets+0.082
ams+0.082
ock+0.078
isdom+0.072
Neg logit contributions
 Ana-0.078
 Pen-0.074
 Mir-0.070
 Megan-0.069
 El-0.069
Token them
Token ID606
Feature activation-5.11e-01

Pos logit contributions
ercise+0.010
ets+0.009
ams+0.009
ock+0.009
isdom+0.008
Neg logit contributions
 Ana-0.013
 Pen-0.013
 Mir-0.012
 Megan-0.012
 El-0.012
Token.
Token ID13
Feature activation-5.59e-01

Pos logit contributions
 Ana+0.014
 Pen+0.013
 Megan+0.012
 Mir+0.012
 El+0.012
Neg logit contributions
ercise-0.013
ets-0.013
ams-0.013
ock-0.012
isdom-0.011
Token We
Token ID775
Feature activation+1.04e+00

Pos logit contributions
 Ana+0.015
 Pen+0.014
 Mir+0.013
 Megan+0.013
 El+0.013
Neg logit contributions
ercise-0.015
ets-0.015
ams-0.014
ock-0.014
isdom-0.013
Token have
Token ID423
Feature activation+2.44e+00

Pos logit contributions
ercise+0.029
ams+0.029
ets+0.028
ock+0.027
isdom+0.025
Neg logit contributions
 Ana-0.026
 Pen-0.025
 Mir-0.023
 Megan-0.023
 El-0.023
Token to
Token ID284
Feature activation-3.66e+00

Pos logit contributions
ets+0.058
ock+0.058
ams+0.057
ercise+0.057
ully+0.051
Neg logit contributions
 Pen-0.068
 Ana-0.068
 Mir-0.064
 Megan-0.063
 bathroom-0.062
Token be
Token ID307
Feature activation+1.34e+00

Pos logit contributions
 Ana+0.095
 Pen+0.090
 Mir+0.085
 Megan+0.084
 El+0.083
Neg logit contributions
ercise-0.099
ets-0.098
ams-0.097
ock-0.092
isdom-0.086
Token careful
Token ID8161
Feature activation-1.08e-01

Pos logit contributions
ets+0.034
ercise+0.034
ams+0.033
ock+0.032
isdom+0.030
Neg logit contributions
 Ana-0.037
 Pen-0.035
 Mir-0.034
 Megan-0.033
 El-0.032
Token with
Token ID351
Feature activation-4.04e-01

Pos logit contributions
 Ana+0.003
 Pen+0.003
 Megan+0.003
 Mir+0.003
 El+0.003
Neg logit contributions
ercise-0.003
ets-0.003
ams-0.003
ock-0.002
isdom-0.002
Token it
Token ID340
Feature activation-5.78e-01

Pos logit contributions
 Ana+0.012
 Pen+0.011
 Mir+0.011
 Megan+0.010
 El+0.010
Neg logit contributions
ets-0.010
ercise-0.010
ams-0.010
ock-0.009
vious-0.008
Token,"
Token ID553
Feature activation-1.99e+00

Pos logit contributions
 Ana+0.017
 Pen+0.017
 Mir+0.016
 Megan+0.016
 El+0.016
Neg logit contributions
ercise-0.013
ets-0.013
ams-0.013
ock-0.012
isdom-0.011
Token he
Token ID339
Feature activation+1.49e-02

Pos logit contributions
ercise+0.042
ets+0.042
ams+0.040
vious+0.038
ock+0.037
Neg logit contributions
 Ana-0.047
 Pen-0.045
 Mir-0.043
 gen-0.043
 Jenkins-0.042
Token just
Token ID655
Feature activation+2.34e+00

Pos logit contributions
ets+0.000
ercise+0.000
ams+0.000
 pads+0.000
ock+0.000
Neg logit contributions
 Ana-0.000
 Pen-0.000
 Mir-0.000
stack-0.000
 Lopez-0.000
Token stood
Token ID6204
Feature activation-1.51e+00

Pos logit contributions
ets+0.064
ams+0.062
ercise+0.061
ock+0.058
vious+0.055
Neg logit contributions
 Ana-0.060
 Pen-0.057
 plun-0.054
 Mir-0.053
 gen-0.053
Token in
Token ID287
Feature activation-3.00e+00

Pos logit contributions
 Ana+0.044
 Pen+0.043
 Mir+0.040
 Megan+0.040
 plun+0.039
Neg logit contributions
ams-0.035
ercise-0.034
ets-0.033
ock-0.031
ear-0.029
Token the
Token ID262
Feature activation+2.15e-01

Pos logit contributions
 Ana+0.096
 Pen+0.091
 Mir+0.087
stack+0.086
 Mil+0.085
Neg logit contributions
ets-0.056
ock-0.054
ams-0.053
ercise-0.052
ear-0.049
Token hallway
Token ID23959
Feature activation-3.99e+00

Pos logit contributions
ets+0.007
ercise+0.007
ams+0.007
ock+0.007
vious+0.006
Neg logit contributions
 Ana-0.004
 Pen-0.004
 Mir-0.004
 El-0.004
 Megan-0.004
Token.
Token ID13
Feature activation+2.96e-01

Pos logit contributions
 Ana+0.129
 Pen+0.124
 Mir+0.117
 El+0.116
 plun+0.115
Neg logit contributions
ets-0.085
ams-0.081
ercise-0.078
ock-0.076
vious-0.068
Token The
Token ID383
Feature activation-5.06e-01

Pos logit contributions
ercise+0.005
ams+0.004
ets+0.004
ear+0.004
isdom+0.004
Neg logit contributions
 Ana-0.009
 gen-0.009
 plun-0.009
 Pen-0.009
 teaspoon-0.009
Token noise
Token ID7838
Feature activation-2.37e+00

Pos logit contributions
 Pen+0.012
 Ana+0.012
 Mir+0.011
 Megan+0.011
 El+0.011
Neg logit contributions
ets-0.014
ock-0.013
ercise-0.013
ams-0.013
vious-0.012
Token was
Token ID373
Feature activation-3.28e+00

Pos logit contributions
 Ana+0.063
 Pen+0.060
 Mir+0.058
 Megan+0.056
stack+0.056
Neg logit contributions
ets-0.062
ock-0.060
ercise-0.060
ams-0.058
les-0.054
Token strange
Token ID6283
Feature activation+5.42e-02

Pos logit contributions
 Ana+0.095
 Pen+0.089
 Mir+0.085
 Megan+0.083
 Mil+0.083
Neg logit contributions
ercise-0.075
ets-0.074
ock-0.074
ams-0.073
vious-0.065
Token so
Token ID523
Feature activation+7.37e-01

Pos logit contributions
 Ana+0.056
 Pen+0.053
 Mir+0.050
 Megan+0.050
 El+0.049
Neg logit contributions
ercise-0.061
ets-0.061
ams-0.060
ock-0.057
isdom-0.053
Token difficult
Token ID2408
Feature activation+1.61e+00

Pos logit contributions
ets+0.019
ercise+0.019
ams+0.019
ock+0.018
vious+0.016
Neg logit contributions
 Ana-0.020
 Pen-0.019
 Mir-0.018
 Megan-0.018
 El-0.018
Token to
Token ID284
Feature activation-2.93e+00

Pos logit contributions
ercise+0.036
ams+0.036
ets+0.035
ock+0.033
isdom+0.030
Neg logit contributions
 Ana-0.049
 Pen-0.047
 Mir-0.045
 El-0.044
 Megan-0.044
Token make
Token ID787
Feature activation+2.00e+00

Pos logit contributions
 Ana+0.081
 Pen+0.076
 Mir+0.073
 Jenkins+0.073
 Megan+0.073
Neg logit contributions
ock-0.071
ercise-0.070
ets-0.069
ams-0.064
ear-0.062
Token the
Token ID262
Feature activation-1.01e+00

Pos logit contributions
ercise+0.045
ets+0.044
ams+0.044
ock+0.042
ear+0.038
Neg logit contributions
 Ana-0.061
 Pen-0.058
 Megan-0.055
 Mir-0.055
 El-0.054
Token bed
Token ID3996
Feature activation-3.49e+00

Pos logit contributions
 Ana+0.025
 Pen+0.024
 Megan+0.023
 Mir+0.022
 El+0.022
Neg logit contributions
ets-0.028
ercise-0.028
ock-0.027
ams-0.027
vious-0.024
Token!
Token ID0
Feature activation+1.08e+00

Pos logit contributions
 Ana+0.102
 Pen+0.099
 Mir+0.094
 El+0.092
 Megan+0.092
Neg logit contributions
ets-0.085
ams-0.080
ercise-0.080
ock-0.078
vious-0.069
Tokenâ
Token ID22940
Feature activation+3.43e+00

Pos logit contributions
ercise+0.027
ets+0.026
ams+0.026
ock+0.025
isdom+0.023
Neg logit contributions
 Ana-0.030
 Pen-0.029
 Mir-0.027
 Megan-0.027
 El-0.027
Token
Token ID26391
Feature activation-7.42e-02

Pos logit contributions
ams+0.098
ercise+0.096
ets+0.096
ock+0.091
isdom+0.087
Neg logit contributions
 Pen-0.072
 Ana-0.071
 Megan-0.066
 Mir-0.065
 plun-0.063
Token
Token ID198
Feature activation+1.02e+00

Pos logit contributions
 Ana+0.002
 Pen+0.002
 Mir+0.002
 Megan+0.002
 El+0.002
Neg logit contributions
ercise-0.002
ets-0.002
ams-0.002
ock-0.002
isdom-0.002
Token
Token ID198
Feature activation+7.70e-01

Pos logit contributions
ercise+0.024
ets+0.024
ams+0.024
ock+0.024
ear+0.022
Neg logit contributions
 Ana-0.028
 Pen-0.027
 Mir-0.025
 gen-0.025
 Megan-0.025
Token woods
Token ID16479
Feature activation-2.84e+00

Pos logit contributions
ets+0.046
ercise+0.045
ams+0.045
ock+0.042
isdom+0.040
Neg logit contributions
 Ana-0.036
 Pen-0.035
 Mir-0.032
 El-0.032
 Megan-0.032
Token.
Token ID13
Feature activation+1.89e+00

Pos logit contributions
 Ana+0.090
 Pen+0.087
 Megan+0.082
 Mir+0.082
 plun+0.081
Neg logit contributions
ets-0.060
ams-0.059
ercise-0.057
ock-0.054
ear-0.049
Token It
Token ID632
Feature activation+2.25e-01

Pos logit contributions
ets+0.038
ercise+0.037
ams+0.037
ock+0.033
ear+0.032
Neg logit contributions
 Ana-0.058
 gen-0.056
 Pen-0.055
stack-0.053
 plun-0.053
Token was
Token ID373
Feature activation-1.78e+00

Pos logit contributions
ercise+0.005
ets+0.005
ock+0.005
ams+0.005
vious+0.005
Neg logit contributions
 Ana-0.006
 Lee-0.006
 Pen-0.006
 plun-0.005
 Mir-0.005
Token cold
Token ID4692
Feature activation-4.19e-01

Pos logit contributions
 Ana+0.052
 Pen+0.049
 Mir+0.046
 Megan+0.046
 El+0.046
Neg logit contributions
ams-0.042
ercise-0.042
ets-0.042
ock-0.040
vious-0.036
Token outside
Token ID2354
Feature activation-4.27e+00

Pos logit contributions
 Ana+0.011
 Pen+0.011
 El+0.011
 Ell+0.011
 Mir+0.011
Neg logit contributions
ercise-0.011
ams-0.010
isdom-0.010
ets-0.009
earned-0.009
Token,
Token ID11
Feature activation-8.74e-02

Pos logit contributions
 Ana+0.136
 Pen+0.132
 Mir+0.126
 Megan+0.125
 El+0.124
Neg logit contributions
ercise-0.090
ets-0.088
ams-0.087
ock-0.081
isdom-0.075
Token but
Token ID475
Feature activation+1.17e+00

Pos logit contributions
 Ana+0.002
 Pen+0.002
 Mir+0.002
 Megan+0.002
 El+0.002
Neg logit contributions
ercise-0.002
ets-0.002
ams-0.002
ock-0.002
isdom-0.002
Token Jimmy
Token ID12963
Feature activation+8.47e-01

Pos logit contributions
ercise+0.033
ams+0.033
ets+0.032
ock+0.031
isdom+0.028
Neg logit contributions
 Ana-0.028
 Pen-0.026
 Mir-0.025
 plun-0.025
 gen-0.025
Token still
Token ID991
Feature activation+1.72e+00

Pos logit contributions
ercise+0.021
ets+0.020
ams+0.020
 pads+0.018
isdom+0.017
Neg logit contributions
 Ana-0.024
 gen-0.022
 Pen-0.022
 Mir-0.022
 plun-0.022
Token stayed
Token ID9658
Feature activation-1.85e-01

Pos logit contributions
ets+0.042
ams+0.042
ercise+0.041
ock+0.037
isdom+0.036
Neg logit contributions
 Ana-0.049
 Pen-0.046
 Mir-0.044
 gen-0.044
 plun-0.044
Token,
Token ID11
Feature activation-1.16e+00

Pos logit contributions
ams+0.054
ercise+0.052
ets+0.051
ock+0.045
vious+0.043
Neg logit contributions
 Ana-0.123
 Pen-0.121
 Megan-0.115
 Mir-0.114
 El-0.113
Token they
Token ID484
Feature activation+1.61e+00

Pos logit contributions
 Ana+0.031
 Pen+0.029
 plun+0.028
 Megan+0.027
 Mir+0.027
Neg logit contributions
ercise-0.029
ams-0.029
ets-0.029
ock-0.027
weet-0.025
Token bring
Token ID2222
Feature activation+4.21e+00

Pos logit contributions
ets+0.041
ercise+0.040
ams+0.039
ock+0.037
vious+0.035
Neg logit contributions
 Ana-0.044
 Pen-0.043
 Mir-0.041
 plun-0.040
 Megan-0.040
Token their
Token ID511
Feature activation+1.78e-01

Pos logit contributions
ercise+0.103
ets+0.103
ams+0.101
ock+0.096
isdom+0.089
Neg logit contributions
 Ana-0.120
 Pen-0.115
 Mir-0.109
 Megan-0.109
 El-0.108
Token bikes
Token ID16715
Feature activation+3.02e+00

Pos logit contributions
ercise+0.004
ets+0.004
ams+0.004
ock+0.004
isdom+0.004
Neg logit contributions
 Ana-0.005
 Pen-0.005
 Mir-0.004
 Megan-0.004
 El-0.004
Token to
Token ID284
Feature activation-3.50e+00

Pos logit contributions
ercise+0.076
ets+0.072
ams+0.070
isdom+0.069
ock+0.067
Neg logit contributions
 Ana-0.080
 Pen-0.078
 Megan-0.075
 Ell-0.074
 El-0.073
Token the
Token ID262
Feature activation-3.85e-02

Pos logit contributions
 Ana+0.109
 Pen+0.102
 plun+0.099
 gen+0.099
 Jenkins+0.099
Neg logit contributions
ercise-0.073
ets-0.070
ock-0.069
ams-0.068
weet-0.062
Token park
Token ID3952
Feature activation-1.53e+00

Pos logit contributions
 Ana+0.001
 Pen+0.001
 Megan+0.001
 Mir+0.001
 El+0.001
Neg logit contributions
ercise-0.001
ets-0.001
ams-0.001
ock-0.001
vious-0.001
Token and
Token ID290
Feature activation+3.80e+00

Pos logit contributions
 Ana+0.047
 Pen+0.045
 Mir+0.043
 Megan+0.043
 El+0.042
Neg logit contributions
ets-0.033
ercise-0.033
ams-0.033
ock-0.031
isdom-0.028
Token ride
Token ID6594
Feature activation+2.61e+00

Pos logit contributions
ercise+0.094
ets+0.092
ams+0.090
ock+0.083
isdom+0.077
Neg logit contributions
 Ana-0.105
 Pen-0.100
 plun-0.095
 Mir-0.095
 gen-0.094
Token around
Token ID1088
Feature activation-5.19e-01

Pos logit contributions
ercise+0.059
ets+0.059
ams+0.059
ock+0.055
isdom+0.049
Neg logit contributions
 Ana-0.079
 Pen-0.075
 Mir-0.072
 Megan-0.071
 gen-0.071