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 nouns, particularly names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATIONS
    -0.67
    ISION
    -0.66
    perty
    -0.63
     Pradesh
    -0.62
    ModLoader
    -0.62
     Dhabi
    -0.61
    WAYS
    -0.61
     Hirosh
    -0.61
    PDATE
    -0.61
     erection
    -0.60
    POSITIVE LOGITS
     herself
    1.05
    otte
    0.83
    thia
    0.81
     miscar
    0.81
    ova
    0.80
    rigan
    0.79
    fet
    0.78
    lette
    0.78
     bikini
    0.77
     breasts
    0.76
    Act Density 0.254%

    No Known Activations