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

    Neuronpedia

    INDEX
    Explanations

    statistical data and percentages regarding performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enderror
    -0.49
    verifyException
    -0.44
    saraba
    -0.44
    #+#
    -0.43
     profiled
    -0.42
    twimg
    -0.42
    -0.41
     defaultstate
    -0.40
    Einzelnachweise
    -0.39
     confined
    -0.39
    POSITIVE LOGITS
     percentage
    0.77
     notches
    0.69
    percentage
    0.63
     basis
    0.58
     fold
    0.57
     notch
    0.54
     factor
    0.54
    fold
    0.53
     magnitudes
    0.52
     Percentage
    0.52
    Act Density 0.429%

    No Known Activations