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

    names of people in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    į
    -0.83
    berra
    -0.70
    mble
    -0.65
    Americ
    -0.64
    ãĥŁ
    -0.61
    è¡
    -0.61
    Ĥ¬
    -0.61
    fecture
    -0.60
    ĭ
    -0.60
    κ
    -0.59
    POSITIVE LOGITS
     himself
    0.88
    's
    0.86
     herself
    0.84
     testified
    0.77
    enegger
    0.76
     wore
    0.70
     underwent
    0.70
     was
    0.70
     began
    0.68
     admitted
    0.67
    Act Density 0.229%

    No Known Activations