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

    Neuronpedia

    INDEX
    Explanations

    references to statistical ranges and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mooney
    -0.90
     Hül
    -0.86
     blessé
    -0.85
     Witkin
    -0.83
     Nutt
    -0.80
    letus
    -0.77
     bookId
    -0.77
     Mistakes
    -0.76
     Nunn
    -0.75
     Eleventh
    -0.75
    POSITIVE LOGITS
     ranges
    1.86
     range
    1.81
     Range
    1.74
     RANGE
    1.66
    range
    1.62
    ranges
    1.58
    Range
    1.57
     Ranges
    1.53
    RANGE
    1.50
    Ranges
    1.47
    Act Density 0.101%

    No Known Activations