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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emphasis or importance

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating subjective opinions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.88
     ABV
    -0.68
    20439
    -0.67
    ickets
    -0.67
    merce
    -0.67
     Pwr
    -0.66
     Sultan
    -0.63
     Tik
    -0.63
    racuse
    -0.62
     Zup
    -0.61
    POSITIVE LOGITS
    âĶĢâĶĢâĶĢâĶĢ
    0.71
    ????
    0.67
     metaph
    0.66
    ????????
    0.64
    mma
    0.62
    ?!
    0.61
    plet
    0.61
    arre
    0.60
    chron
    0.60
    !?
    0.58
    Act Density 1.011%

    No Known Activations