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

    Neuronpedia

    INDEX
    Explanations

    references to individuals' names in text

    oai_token-act-pair · gpt-3.5-turbo

    names or mentions of specific individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liest
    -0.87
    ansas
    -0.76
    drawn
    -0.68
     reluct
    -0.68
    nesota
    -0.67
    ccording
    -0.66
     coroner
    -0.66
    termin
    -0.65
    moving
    -0.64
    itars
    -0.63
    POSITIVE LOGITS
    otti
    1.54
    ota
    1.00
    ucci
    0.99
    ón
    0.93
    olini
    0.90
    etta
    0.85
    ogl
    0.84
    orno
    0.83
    arella
    0.81
    aceae
    0.79
    Act Density 0.004%

    No Known Activations