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

    Neuronpedia

    INDEX
    Explanations

    occurrences of contractions and informal language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    author or writer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.60
    ConstraintMaker
    -0.52
     ModelExpression
    -0.50
    WriteAttribute
    -0.50
    Personensuche
    -0.49
     monsters
    -0.46
     CreateTagHelper
    -0.46
    RenderAtEndOf
    -0.46
    openConnection
    -0.46
    \{\\
    -0.46
    POSITIVE LOGITS
     writer
    0.66
     author
    0.65
    這位
    0.56
     forfatter
    0.54
    writer
    0.53
    这位
    0.53
     article
    0.52
     作者
    0.52
    author
    0.51
    一位
    0.51
    Act Density 0.057%

    No Known Activations