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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships or connections to specific subjects or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owie
    -0.15
    ipeg
    -0.15
    ảy
    -0.15
     ï¿¥
    -0.15
    ibold
    -0.14
    ENCIL
    -0.14
    vrier
    -0.14
    gli
    -0.14
    wit
    -0.14
    white
    -0.14
    POSITIVE LOGITS
    nal
    0.17
    iness
    0.16
    idot
    0.15
    obot
    0.15
    phrase
    0.15
    weets
    0.15
    dzi
    0.14
     dout
    0.14
    aining
    0.14
    ùy
    0.14
    Act Density 0.006%

    No Known Activations