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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and code structures related to calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ü
    -0.67
     Cosponsors
    -0.66
     cringe
    -0.64
     swearing
    -0.62
     unmist
    -0.62
     VIDE
    -0.61
    haps
    -0.60
    htaking
    -0.58
     ribbon
    -0.57
     predominantly
    -0.57
    POSITIVE LOGITS
     multiplied
    1.07
    /(
    1.01
    cycles
    0.88
     Divide
    0.83
    Factor
    0.82
    factor
    0.81
    frac
    0.80
     calculated
    0.79
     squared
    0.78
    (-
    0.77
    Act Density 1.062%

    No Known Activations