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

    Neuronpedia

    INDEX
    Explanations

    specific keywords and phrases associated with legal and formal contexts

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

    ECOA Discrimination

    np_acts-logits-general · gemini-2.5-flash-lite

    word fragments attached to punctuation (especially apostrophes/hyphens) and nearby function words immediately preceding numbers, dates, or enumerations.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    .
    -0.37
    M
    -0.37
    Susan
    -0.34
    <strong>
    -0.32
    MD
    -0.32
    MET
    -0.31
    UM
    -0.31
    WS
    -0.30
    </blockquote>
    -0.30
    ™
    -0.30
    POSITIVE LOGITS
    ftagPool
    1.05
     Taktlose
    0.94
    ConstraintMaker
    0.86
     <>",
    0.85
    WriteTagHelper
    0.85
     Administrativna
    0.84
    tagHelperRunner
    0.81
    MessageOf
    0.81
     للاسماء
    0.77
     Italijani
    0.76
    Act Density 0.017%

    No Known Activations