INDEX
Explanations
references to team dynamics and interpersonal relationships
New Auto-Interp
Negative Logits
â̦
-0.31
‘
-0.30
...
-0.29
“
-0.28
“â̦
-0.28
(“
-0.27
’
-0.25
"...
-0.25
“[
-0.24
"
-0.24
POSITIVE LOGITS
.
0.25
Um
0.19
Oh
0.19
Yeah
0.19
yeah
0.19
uh
0.18
Uh
0.18
.↵
0.17
Ah
0.17
Okay
0.17
Activations Density 0.135%