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

    Neuronpedia

    INDEX
    Explanations

    numerical values and measurements, particularly fractions and quantities related to time or other units

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Orrell
    -0.77
    es
    -0.76
     def
    -0.73
    /
    -0.69
    )
    -0.67
    def
    -0.64
     «
    -0.64
    ly
    -0.62
    ()}>
    -0.62
    hline
    -0.62
    POSITIVE LOGITS
     eighty
    1.11
     seventy
    1.08
     sixty
    1.06
     ninety
    1.05
    WEBPACK
    1.00
     Ninety
    0.98
     forty
    0.97
     fifty
    0.97
     nineteen
    0.97
     thirty
    0.96
    Act Density 0.119%

    No Known Activations