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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bp
    -0.82
    ãĥĵ
    -0.77
    psc
    -0.77
    urai
    -0.74
    ument
    -0.73
    uked
    -0.73
    ray
    -0.70
     scrap
    -0.69
    McC
    -0.69
    pp
    -0.68
    POSITIVE LOGITS
     El
    2.50
    El
    2.31
     EL
    2.19
    Els
    2.08
     el
    1.99
     Elm
    1.55
     Elk
    1.53
    EL
    1.52
    el
    1.49
     Elven
    1.42
    Act Density 0.187%

    No Known Activations