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

    Neuronpedia

    INDEX
    Explanations

    a conjunction of clauses suggesting contrast or exception

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

    concessive though

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    simpleType
    -0.56
     HFILL
    -0.50
    CascadeType
    -0.47
     ब्रेकडाउन
    -0.47
     ویکی‌پدی
    -0.47
     PNC
    -0.46
     للاسماء
    -0.45
     intStringLen
    -0.45
    utilisons
    -0.45
    VIAF
    -0.45
    POSITIVE LOGITS
     banget
    0.47
    tough
    0.44
     though
    0.42
     הער
    0.42
     Anyway
    0.42
     THOUGHTS
    0.42
     toughness
    0.41
     Tough
    0.41
     jeito
    0.41
     Però
    0.41
    Act Density 0.009%

    No Known Activations