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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "Av" followed by a single letter."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Av," indicating a focus on a specific individual or character mentioned in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hyde
    -0.79
    utenant
    -0.73
    zsche
    -0.69
    FORMATION
    -0.68
    cipline
    -0.66
    ngth
    -0.64
    hower
    -0.63
     Coke
    -0.63
     unions
    -0.63
    ciplinary
    -0.62
    POSITIVE LOGITS
    atars
    1.15
    ocado
    1.07
    ril
    1.00
    raham
    1.00
    iew
    0.98
    iva
    0.97
    atar
    0.95
    iator
    0.95
    eus
    0.92
    iol
    0.91
    Act Density 0.006%

    No Known Activations