INDEX
Explanations
phrases related to challenging or doubting something
instances of the word "questioning."
New Auto-Interp
Negative Logits
HD
-0.69
ids
-0.66
esse
-0.64
1024
-0.64
Distribution
-0.63
ouri
-0.63
Store
-0.62
map
-0.61
contiguous
-0.61
Send
-0.60
POSITIVE LOGITS
questioning
3.86
questioned
1.61
interrog
1.59
interrogation
1.59
question
1.55
interviewing
1.49
probing
1.45
questions
1.43
criticizing
1.37
scrutiny
1.37
Activations Density 0.010%