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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and parameters related to limits and thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     higher
    -0.42
     capri
    -0.41
     hog
    -0.40
     aure
    -0.40
     mast
    -0.39
     larger
    -0.38
    Balloon
    -0.38
    encodeWith
    -0.38
     taller
    -0.37
     bigger
    -0.37
    POSITIVE LOGITS
     rendah
    0.71
     lowest
    0.62
    lowest
    0.59
     low
    0.58
     Lowest
    0.57
     laag
    0.57
     dingin
    0.56
     nisk
    0.56
    low
    0.54
     bajos
    0.54
    Act Density 1.143%

    No Known Activations