INDEX
Explanations
dialogue or conversational elements in the text
New Auto-Interp
Negative Logits
guy
-0.21
dudes
-0.20
dude
-0.19
guys
-0.19
Guys
-0.17
"Yeah
-0.16
hey
-0.15
aget
-0.15
Hey
-0.15
braco
-0.15
POSITIVE LOGITS
sir
0.32
Sir
0.24
Sir
0.22
erm
0.19
åħĪçĶŁ
0.16
er
0.16
um
0.16
uh
0.16
ladies
0.15
æĤ¨çļĦ
0.15
Activations Density 0.384%