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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    keyes
    -0.81
    acea
    -0.76
    etheless
    -0.75
    oidal
    -0.74
    aceous
    -0.73
    arser
    -0.72
    angers
    -0.72
    İĭ
    -0.71
    ummer
    -0.70
    aido
    -0.70
    POSITIVE LOGITS
    leon
    1.02
    eh
    0.91
    ña
    0.86
    llan
    0.80
    e
    0.77
    ez
    0.76
    xual
    0.76
    ñ
    0.75
    lled
    0.73
    lla
    0.71
    Act Density 0.024%

    No Known Activations