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

    Neuronpedia

    INDEX
    Explanations

    words related to numerical data and statistics

    oai_token-act-pair · gpt-3.5-turbo

    repeated use of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,''
    -0.68
    âĢİ
    -0.64
    America
    -0.63
    watching
    -0.63
     Mormonism
    -0.62
    stocks
    -0.62
    cape
    -0.61
    Share
    -0.60
    bill
    -0.59
    sure
    -0.59
    POSITIVE LOGITS
     latter
    1.67
     remainder
    1.48
     rest
    1.25
     same
    1.16
     second
    1.04
     heaviest
    1.04
     smallest
    1.04
     weakest
    1.03
     final
    1.02
     corresponding
    1.01
    Act Density 0.651%

    No Known Activations