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

    Neuronpedia

    INDEX
    Explanations

    references to time frames

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "another."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olas
    -0.86
    effects
    -0.80
    alties
    -0.79
    isters
    -0.78
    hips
    -0.78
    ships
    -0.77
    bows
    -0.75
    encies
    -0.73
    encers
    -0.73
    bats
    -0.73
    POSITIVE LOGITS
    worldly
    1.25
     installment
    1.14
     batch
    1.09
     dimension
    1.04
     round
    1.03
     iteration
    0.97
     layer
    0.94
     avenue
    0.93
     decade
    0.93
     edition
    0.92
    Act Density 0.063%

    No Known Activations