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

    Neuronpedia

    INDEX
    Explanations

    punctuation and qualifiers that indicate emphasis or opinion

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

    closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -0.81
    請繼續往下閱讀
    -0.57
     ब्रेकडाउन
    -0.56
    IsMutable
    -0.54
     uſe
    -0.53
     Anſ
    -0.52
     Italijani
    -0.51
    🟤
    -0.51
    исленность
    -0.50
    KommentareTeilen
    -0.48
    POSITIVE LOGITS
    principalColumn
    0.50
     accusing
    0.34
     implying
    0.34
     blaming
    0.32
    Saying
    0.31
     referirse
    0.30
     Einwilligung
    0.30
     blamed
    0.30
     implied
    0.30
    MessageOf
    0.29
    Act Density 0.017%

    No Known Activations