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

    Neuronpedia

    INDEX
    Explanations

    occurrences of negative values or terms suggesting a decrease

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fur
    -0.17
    .AutoScaleMode
    -0.14
    rud
    -0.14
    ç·ł
    -0.14
    arer
    -0.14
    лим
    -0.14
     Surg
    -0.14
    itness
    -0.14
     Fletcher
    -0.14
     fur
    -0.13
    POSITIVE LOGITS
    zyst
    0.15
    pta
    0.15
    aupt
    0.15
    ieres
    0.14
     Artifact
    0.14
    amber
    0.14
    Downloader
    0.14
    iges
    0.14
     Aires
    0.14
    igate
    0.14
    Act Density 0.002%

    No Known Activations