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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or variables in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.66
     насељу
    -0.64
    BufferException
    -0.62
     bed
    -0.61
    dymyr
    -0.56
    OCCURRED
    -0.56
    AlterField
    -0.55
     slept
    -0.54
    featureID
    -0.52
    bed
    -0.52
    POSITIVE LOGITS
    frac
    1.14
    mfrac
    1.10
    dfrac
    1.05
     frac
    0.87
     fraction
    0.78
     Fraction
    0.76
     fractions
    0.75
     @"/
    0.74
     ratio
    0.72
    Frac
    0.70
    Act Density 0.995%

    No Known Activations