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

    Neuronpedia

    INDEX
    Explanations

    references to influential literary figures and their works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    194
    -0.20
     Hitler
    -0.19
     Broadcast
    -0.18
     jeep
    -0.17
    atica
    -0.17
     WWII
    -0.17
    ï¼ĪæĺŃåĴĮ
    -0.16
     garage
    -0.16
    eza
    -0.16
    193
    -0.16
    POSITIVE LOGITS
     Victorian
    0.61
    184
    0.56
    185
    0.56
    183
    0.56
    182
    0.53
    186
    0.51
    181
    0.45
    187
    0.43
     nineteenth
    0.43
     Victor
    0.35
    Act Density 0.320%

    No Known Activations