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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    the word "then" used in a temporal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    toe
    -0.71
    illon
    -0.68
     sty
    -0.60
     triangles
    -0.60
     fulfillment
    -0.59
    upuncture
    -0.59
    azor
    -0.59
    acts
    -0.58
     reservation
    -0.58
    mson
    -0.58
    POSITIVE LOGITS
    -'
    0.80
     Yugoslav
    0.78
     Yugoslavia
    0.73
    oslov
    0.68
     unsuccessfully
    0.68
     unpublished
    0.68
    ————————————————
    0.67
    adays
    0.67
    ceed
    0.66
    nih
    0.65
    Act Density 0.042%

    No Known Activations