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

    Neuronpedia

    INDEX
    Explanations

    names, possibly of famous people

    oai_token-act-pair · gpt-3.5-turbo

    single letters or short abbreviations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glers
    -0.94
    LOAD
    -0.67
    ĵĺ
    -0.67
     intersections
    -0.63
     mot
    -0.62
     impunity
    -0.61
    Newsletter
    -0.60
    holding
    -0.59
    ׾
    -0.59
    gerald
    -0.58
    POSITIVE LOGITS
    ciating
    0.98
    hyde
    0.87
    bourg
    0.87
    ovych
    0.83
    afort
    0.80
    isen
    0.80
    umeric
    0.79
    orf
    0.78
    enium
    0.76
    ahime
    0.76
    Act Density 0.252%

    No Known Activations