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

    proper names, particularly of individuals and their associated roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PDATE
    -0.70
    translation
    -0.69
    GoldMagikarp
    -0.68
     hindsight
    -0.67
    incial
    -0.67
    ISION
    -0.67
    ãĤŃ
    -0.65
    perty
    -0.64
    ATIONS
    -0.64
    Excellent
    -0.64
    POSITIVE LOGITS
     herself
    0.93
    deen
    0.80
    bors
    0.78
    ahl
    0.76
    ova
    0.75
    otte
    0.74
    shaw
    0.74
     bikini
    0.73
     miscar
    0.71
    itte
    0.71
    Act Density 0.254%

    No Known Activations