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

    Neuronpedia

    INDEX
    Explanations

    ordinal numbers indicating position in a sequence

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Statistics
    -0.70
    mbuds
    -0.69
    bos
    -0.68
    uploads
    -0.63
     Monsters
    -0.61
    Downloadha
    -0.61
    bda
    -0.60
    info
    -0.60
    Attributes
    -0.59
    values
    -0.59
    POSITIVE LOGITS
     inning
    1.05
    ousand
    1.02
    irty
    1.01
     century
    1.00
     installment
    0.97
     Amendment
    0.97
     baseman
    0.96
     percentile
    0.93
    century
    0.89
     harmonic
    0.89
    Act Density 0.709%

    No Known Activations