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

    Neuronpedia

    INDEX
    Explanations

    names, particularly those of individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Stef" and "Giov"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stump
    -0.77
     wounding
    -0.73
    vasive
    -0.66
     Terminal
    -0.66
    ciating
    -0.66
    20439
    -0.64
     nursery
    -0.64
    iliary
    -0.64
     negotiator
    -0.63
     Prol
    -0.63
    POSITIVE LOGITS
    ano
    0.96
    ansson
    0.95
    ania
    0.90
     Stef
    0.87
    sburgh
    0.86
    olini
    0.84
    ão
    0.83
    anes
    0.83
     Giov
    0.82
    ani
    0.82
    Act Density 0.019%

    No Known Activations