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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to specific companies or organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ments
    -1.08
    uably
    -0.95
    ously
    -0.94
    istically
    -0.92
    istics
    -0.85
    ania
    -0.82
    ancy
    -0.78
    naire
    -0.77
    chest
    -0.76
    mentation
    -0.75
    POSITIVE LOGITS
    ignt
    0.78
    hao
    0.76
    hops
    0.75
    meier
    0.74
     mathemat
    0.71
    alez
    0.71
    nesday
    0.66
    abee
    0.66
    kj
    0.65
    pher
    0.63
    Act Density 0.062%

    No Known Activations