INDEX
Explanations
second-person pronouns and verbs related to combat or adversity
references to the second-person pronoun "you."
New Auto-Interp
Negative Logits
ipal
-0.69
Lago
-0.66
Samoa
-0.65
Canaver
-0.61
ulla
-0.61
ensable
-0.60
Sabha
-0.56
Filip
-0.55
ariat
-0.55
Parameters
-0.54
POSITIVE LOGITS
're
1.15
guys
1.07
've
0.97
'll
0.91
tub
0.89
RS
0.82
wanna
0.81
know
0.80
hei
0.77
'd
0.76
Activations Density 0.169%