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

    Neuronpedia

    INDEX
    Explanations

    terms related to philosophical concepts or academic topics

    oai_token-act-pair · gpt-3.5-turbo

    themes related to social and moral issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kosher
    -0.65
    FUL
    -0.64
     Airl
    -0.63
     Famous
    -0.62
     bartender
    -0.60
     Forgotten
    -0.60
     Sapphire
    -0.60
     uphill
    -0.60
    Rated
    -0.59
     unused
    -0.59
    POSITIVE LOGITS
    ism
    1.32
    itism
    1.27
    ivism
    1.25
    rification
    1.23
    icism
    1.16
    utics
    1.14
    ogenesis
    1.13
    osis
    1.13
    atism
    1.12
    ativity
    1.11
    Act Density 0.412%

    No Known Activations