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

    Neuronpedia

    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ultimate
    -0.88
    words
    -0.79
    dies
    -0.78
    alore
    -0.73
    itars
    -0.73
    romeda
    -0.73
    sci
    -0.72
    teenth
    -0.72
    mates
    -0.71
    istar
    -0.70
    POSITIVE LOGITS
     Baldwin
    0.90
     Reed
    0.88
     Bennett
    0.87
     Gib
    0.85
     Stewart
    0.85
     Gomez
    0.85
     Howard
    0.85
     Kir
    0.84
     Kurt
    0.84
     Lopez
    0.83
    Act Density 0.238%

    No Known Activations