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

    Neuronpedia

    INDEX
    Explanations

    references to high-ranking executives in organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to executives and executive roles within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FUL
    -0.77
    TPS
    -0.72
     Ern
    -0.72
    FACE
    -0.71
    theless
    -0.71
    Ô
    -0.70
     Twain
    -0.68
     Crimean
    -0.67
     Sense
    -0.67
     Mania
    -0.65
    POSITIVE LOGITS
    ution
    1.43
    utive
    1.41
    utions
    1.33
    uting
    1.21
    utable
    1.19
    uted
    1.12
    ination
    1.07
    utor
    1.02
    uments
    1.02
    utes
    1.01
    Act Density 0.009%

    No Known Activations