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

    Neuronpedia

    INDEX
    Explanations

    terms related to rewards and their various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SerializedSize
    -0.81
    DoubleQuotes
    -0.80
    XmlAccessType
    -0.73
     trouvez
    -0.70
    rubin
    -0.70
    InitStruct
    -0.68
     ویکی‌پدیای
    -0.67
    setVerticalGroup
    -0.66
     Roskov
    -0.66
     giras
    -0.66
    POSITIVE LOGITS
     delivery
    0.77
     Granville
    0.75
     Delivery
    0.73
     inci
    0.73
    archie
    0.73
     Schuyler
    0.72
     Potts
    0.70
     Bartol
    0.70
    ImageIO
    0.70
     Granger
    0.67
    Act Density 0.034%

    No Known Activations