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

    Neuronpedia

    INDEX
    Explanations

    names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual named "Pa."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    schild
    -0.90
    eering
    -0.90
    suit
    -0.90
    scape
    -0.88
    casting
    -0.81
    dress
    -0.80
    geist
    -0.79
    æĺ¯
    -0.76
    binding
    -0.76
    suits
    -0.73
    POSITIVE LOGITS
    aternal
    0.99
    atern
    0.96
    izo
    0.95
    ignt
    0.92
    olo
    0.92
    olini
    0.90
    odcast
    0.87
     Pa
    0.87
    uter
    0.86
    atell
    0.85
    Act Density 0.012%

    No Known Activations