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

    Neuronpedia

    INDEX
    Explanations

    numerical values and references to specific data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isos
    -0.15
    ières
    -0.14
    nants
    -0.14
    enet
    -0.14
    enant
    -0.14
    uracy
    -0.14
    llib
    -0.13
    abit
    -0.13
    etched
    -0.13
     Christopher
    -0.13
    POSITIVE LOGITS
     Sug
    0.18
    翼
    0.16
    opis
    0.15
    -Col
    0.14
    roke
    0.14
    rame
    0.14
    hta
    0.14
    gal
    0.14
    ime
    0.14
    lum
    0.14
    Act Density 0.017%

    No Known Activations