Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    historical events and notable dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     WWII
    -0.23
    192
    -0.21
    194
    -0.21
    191
    -0.21
    193
    -0.19
     Hitler
    -0.19
     Roosevelt
    -0.19
     WW
    -0.18
    196
    -0.18
    190
    -0.17
    POSITIVE LOGITS
    184
    0.60
    183
    0.59
    185
    0.59
    182
    0.51
    186
    0.47
     Victorian
    0.42
    181
    0.40
    187
    0.35
     nineteenth
    0.28
     Dickens
    0.28
    Act Density 0.375%

    No Known Activations