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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of people

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent individuals, particularly in the context of fashion, film, and politics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ORTS
    -0.83
    士
    -0.79
    merce
    -0.72
    ruary
    -0.71
    lished
    -0.70
    âĶĢâĶĢ
    -0.68
    STATE
    -0.68
    essee
    -0.66
    DragonMagazine
    -0.62
    alore
    -0.62
    POSITIVE LOGITS
    kov
    0.74
    uty
    0.72
    zinski
    0.68
    jad
    0.68
    atz
    0.66
    opoulos
    0.66
    bard
    0.65
    ansky
    0.62
    ahl
    0.62
     (@
    0.61
    Act Density 0.207%

    No Known Activations