INDEX
Explanations
time-related phrases and dates
New Auto-Interp
Negative Logits
201
-0.29
recent
-0.24
recently
-0.21
Û²Û°Û±
-0.20
yesterday
-0.19
recent
-0.19
Yesterday
-0.18
Yesterday
-0.17
ufe
-0.17
202
-0.17
POSITIVE LOGITS
191
0.24
192
0.22
189
0.21
188
0.21
185
0.20
194
0.20
187
0.20
193
0.20
190
0.19
184
0.19
Activations Density 0.100%