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

    Neuronpedia

    INDEX
    Explanations

    fractional expressions and numerical conversions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Deum
    -0.67
    phée
    -0.58
     Alhambra
    -0.55
    transQ
    -0.52
    ########.
    -0.52
    سع
    -0.52
    ίδι
    -0.52
    +:+
    -0.52
     Duo
    -0.52
    madamente
    -0.51
    POSITIVE LOGITS
     fraction
    0.98
    fraction
    0.91
     quarter
    0.83
    Fraction
    0.79
     Fraction
    0.79
     fractions
    0.79
     fractional
    0.79
     tenth
    0.77
     ISNI
    0.75
     Quarter
    0.73
    Act Density 0.480%

    No Known Activations