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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time and numerical limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    🤣🤣
    -0.66
     EDR
    -0.59
    '
    -0.59
     PDT
    -0.59
    -------
    -0.58
    vin
    -0.57
     neighborhood
    -0.56
     Toujours
    -0.56
    Linn
    -0.56
     ALA
    -0.56
    POSITIVE LOGITS
     upto
    1.14
    Hasta
    1.14
    upto
    1.07
    Até
    1.02
     hasta
    0.97
     Até
    0.95
     Hasta
    0.95
    awtextra
    0.93
     Hingga
    0.91
     ועד
    0.91
    Act Density 0.087%

    No Known Activations