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

    Neuronpedia

    INDEX
    Explanations

    phrases related to nighttime activities

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of night

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achev
    -0.81
     Canaver
    -0.79
    pta
    -0.75
    essors
    -0.69
    elsen
    -0.68
    cules
    -0.67
    berman
    -0.67
    xon
    -0.67
    ignty
    -0.66
    ttle
    -0.65
    POSITIVE LOGITS
    cap
    1.04
    mar
    1.01
    fall
    0.99
    life
    0.95
    light
    0.91
    night
    0.88
    mares
    0.81
    urnal
    0.81
    stand
    0.75
     sky
    0.75
    Act Density 0.033%

    No Known Activations