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

    Neuronpedia

    INDEX
    Explanations

    alphanumeric codes or unusual character sequences

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istically
    -0.71
    hedon
    -0.69
     manic
    -0.66
    pop
    -0.66
    icum
    -0.63
    monary
    -0.63
    aneous
    -0.63
    ampires
    -0.62
    capital
    -0.61
    oulos
    -0.60
    POSITIVE LOGITS
    âĸ
    1.26
    âĸł
    1.00
    ¼
    0.92
    ¡
    0.89
    ª
    0.89
    NEY
    0.88
    edin
    0.87
    wcsstore
    0.86
    ï¸
    0.83
     Flavoring
    0.80
    Act Density 0.016%

    No Known Activations