INDEX
Explanations
mentions of a particular surname "Pher" alongside various words or phrases
references to the pronoun "her."
New Auto-Interp
Negative Logits
ãĥ³ãĤ¸
-0.66
bluff
-0.66
govtrack
-0.65
stret
-0.63
CCC
-0.62
curfew
-0.62
ured
-0.61
prints
-0.59
Krug
-0.57
RAW
-0.56
POSITIVE LOGITS
itage
1.35
tz
1.29
ding
1.11
jee
1.01
itance
0.99
pes
0.99
ald
0.97
der
0.97
rha
0.95
mite
0.93
Activations Density 0.031%