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

    Neuronpedia

    INDEX
    Explanations

    personal titles like "Pri" with associated numbers, possibly related to ranking or importance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -1.16
    schild
    -0.80
    è¦ļéĨĴ
    -0.71
    stead
    -0.69
    geist
    -0.68
    ded
    -0.68
    ORGE
    -0.66
     HELL
    -0.66
    ding
    -0.66
    INESS
    -0.63
    POSITIVE LOGITS
    etary
    1.22
    ests
    1.16
    eties
    1.12
    zes
    1.06
    ety
    1.04
    Ľ
    0.97
    eur
    0.89
    angular
    0.87
    pper
    0.87
    vy
    0.87
    Act Density 0.012%

    No Known Activations