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

    Neuronpedia

    INDEX
    Explanations

    the name "Tony" at various activation levels

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Tony"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INESS
    -0.90
    ãģ¦
    -0.79
    fulness
    -0.76
    words
    -0.75
    rences
    -0.71
    esley
    -0.71
    tm
    -0.69
    ANC
    -0.69
    station
    -0.67
    Roaming
    -0.67
    POSITIVE LOGITS
     Sop
    1.04
     Blair
    1.03
     Abbott
    1.01
     Romo
    0.98
     Stark
    0.92
     Hawk
    0.91
     Fernand
    0.84
     Robbins
    0.83
     Rodham
    0.81
    neau
    0.78
    Act Density 0.025%

    No Known Activations