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

    Neuronpedia

    INDEX
    Explanations

    numbers related to the 90s

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the number 90 in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    board
    -0.75
    wan
    -0.73
    lay
    -0.72
    lish
    -0.71
    seeing
    -0.70
    stand
    -0.70
    pocket
    -0.69
    Redd
    -0.68
    maid
    -0.68
    wered
    -0.66
    POSITIVE LOGITS
    %"
    0.87
     ILCS
    0.86
    %:
    0.86
    80
    0.86
    idth
    0.85
     degrees
    0.84
    orsi
    0.81
    ruciating
    0.80
    yip
    0.80
    º
    0.80
    Act Density 0.050%

    No Known Activations