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

    Neuronpedia

    INDEX
    Explanations

    there

    np_max-act · gemini-2.0-flash

    situations involving spanking as a form of punishment or pleasure.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     peanuts
    -0.07
    ód
    -0.07
    predicate
    -0.06
    uts
    -0.06
     recurs
    -0.06
    ap
    -0.06
     convinced
    -0.06
    _old
    -0.06
     Gregory
    -0.06
     mc
    -0.06
    POSITIVE LOGITS
     brutally
    0.07
     tolerated
    0.07
     Mö
    0.06
    endsWith
    0.06
     clarification
    0.06
    engin
    0.06
     there
    0.06
     Anglo
    0.06
     balancing
    0.06
     purported
    0.06
    Act Density 0.020%

    No Known Activations