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

    Neuronpedia

    INDEX
    Explanations

    words related to a specific name: "Hahime"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mentions of a specific name or reference in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ateur
    -0.77
    displayText
    -0.76
    rations
    -0.72
     outgoing
    -0.71
    lace
    -0.69
    papers
    -0.68
    urated
    -0.68
    atories
    -0.67
    ateurs
    -0.64
    entric
    -0.62
    POSITIVE LOGITS
    wn
    1.01
    ha
    0.99
    jj
    0.88
    pton
    0.87
    pless
    0.87
    azard
    0.87
    iku
    0.86
    verty
    0.84
    qua
    0.83
    ichi
    0.82
    Act Density 0.007%

    No Known Activations