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

    Neuronpedia

    INDEX
    Explanations

    words related to observations and findings in various studies, cases, or situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "a"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Edit
    -0.80
    Contents
    -0.75
     Jagu
    -0.71
     Estimates
    -0.70
    anism
    -0.70
     knows
    -0.69
    achu
    -0.69
    ographs
    -0.68
    ESPN
    -0.67
    tests
    -0.67
    POSITIVE LOGITS
     lot
    1.21
     plethora
    1.07
     glimpse
    1.05
     multitude
    1.03
     significant
    1.02
     few
    1.01
     flurry
    1.00
     bunch
    1.00
     tremendous
    0.99
     dramatic
    0.97
    Act Density 0.302%

    No Known Activations