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

    Neuronpedia

    INDEX
    Explanations

    the name "Elaine" at various activation levels

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Kaine"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NUM
    -0.94
    dimension
    -0.85
    displayText
    -0.76
    ticket
    -0.75
    LOC
    -0.74
    notes
    -0.73
    ologically
    -0.70
    Trend
    -0.70
    ocene
    -0.69
    DOWN
    -0.68
    POSITIVE LOGITS
    aine
    0.98
    llor
    0.95
    cia
    0.93
    issance
    0.87
    isance
    0.78
     Lans
    0.78
    lette
    0.77
     Lamp
    0.75
    jah
    0.74
    ffe
    0.72
    Act Density 0.007%

    No Known Activations