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

    Neuronpedia

    INDEX
    Explanations

    references to parallel processes or systems

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.68
    Гу
    -0.68
    rungsseite
    -0.64
    受
    -0.64
    cookie
    -0.63
     խ
    -0.59
    අ
    -0.59
    pub
    -0.58
    ઊ
    -0.58
     تع
    -0.58
    POSITIVE LOGITS
     suspic
    1.63
     affor
    1.56
     desir
    1.51
     emphat
    1.50
     madonna
    1.49
     fta
    1.48
     perfet
    1.48
     ftu
    1.47
     foon
    1.46
     Juf
    1.45
    Act Density 0.322%

    No Known Activations