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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns related to scores or statistics in a sports context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of fractions or ratios, specifically formatted as "number-number"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rom
    -0.74
     Roh
    -0.62
     prof
    -0.60
     Sik
    -0.59
     Brut
    -0.58
     festive
    -0.58
     tender
    -0.58
     Viet
    -0.57
     Mant
    -0.57
     fri
    -0.56
    POSITIVE LOGITS
    none
    1.02
    zero
    0.96
    one
    0.95
    four
    0.94
    nothing
    0.93
    ones
    0.92
    three
    0.92
    numbered
    0.91
    equal
    0.90
    seven
    0.89
    Act Density 0.032%

    No Known Activations