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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and affirmations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    incy
    -0.16
     Giov
    -0.15
    thon
    -0.14
     Vig
    -0.14
    group
    -0.13
     Friends
    -0.13
    -plugin
    -0.13
     Incredible
    -0.13
    xis
    -0.13
    roids
    -0.13
    POSITIVE LOGITS
    baum
    0.14
    ocard
    0.14
    StartPosition
    0.14
    kip
    0.14
    rer
    0.14
    ights
    0.14
    UES
    0.13
    ä¸Ī
    0.13
     yem
    0.13
    ÙħÙĦ
    0.13
    Act Density 0.079%

    No Known Activations