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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating examples or instances of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce examples or instances of various concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antage
    -0.69
    ushima
    -0.69
    orem
    -0.64
    allo
    -0.64
    ribution
    -0.64
    emi
    -0.62
    emale
    -0.61
    ogun
    -0.60
    enger
    -0.60
    ombat
    -0.59
    POSITIVE LOGITS
    ties
    0.86
    cond
    0.72
     embodiments
    0.67
    ities
    0.64
    minded
    0.64
    amount
    0.64
    ones
    0.61
    inyl
    0.61
    things
    0.61
     minded
    0.59
    Act Density 0.033%

    No Known Activations