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

    Neuronpedia

    INDEX
    Explanations

    phrases that contrast or provide an alternative perspective

    oai_token-act-pair · gpt-3.5-turbo

    references to alternative options or comparisons to "other" things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olt
    -0.67
     1915
    -0.67
     1906
    -0.57
    uberty
    -0.57
     reprodu
    -0.56
    udence
    -0.55
     2024
    -0.55
     1903
    -0.55
     1924
    -0.54
     1962
    -0.54
    POSITIVE LOGITS
    worldly
    2.07
    wise
    1.20
     than
    0.98
    world
    0.88
    parts
    0.87
    Redd
    0.86
    ials
    0.81
    than
    0.80
    quickShipAvailable
    0.79
    dimensional
    0.78
    Act Density 0.075%

    No Known Activations