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

    Neuronpedia

    INDEX
    Explanations

    underscore-prefixed or double-underscore-prefixed terms, commonly used for private or special attributes in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fromnode
    -0.67
    parsedMessage
    -0.64
    fauna
    -0.60
    MessageOf
    -0.60
    Coordenadas
    -0.60
    帖最后由
    -0.59
    انجليز
    -0.58
    tonsoft
    -0.58
    fanart
    -0.58
    lained
    -0.58
    POSITIVE LOGITS
    tagHelperRunner
    1.08
    _.
    0.84
     (__
    0.75
     (!__
    0.74
    /__
    0.72
    ->__
    0.71
    (__
    0.70
     *__
    0.70
    _,
    0.70
    tagHelper
    0.69
    Act Density 0.143%

    No Known Activations