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

    Neuronpedia

    INDEX
    Explanations

    phrases related to an activity or situation happening behind the scenes

    oai_token-act-pair · gpt-3.5-turbo

    negative contextual phrases related to "off-the-grid" or nontraditional lifestyles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thanking
    -0.67
     Mechdragon
    -0.62
     ashore
    -0.60
     Rica
    -0.58
     Tik
    -0.57
    terday
    -0.57
    awaru
    -0.57
    anamo
    -0.57
     fade
    -0.56
     revel
    -0.56
    POSITIVE LOGITS
    same
    1.11
    prem
    0.98
    purpose
    0.95
    best
    0.93
    middle
    0.92
    distance
    0.92
    door
    0.90
    perfect
    0.87
    growth
    0.87
    highest
    0.86
    Act Density 0.014%

    No Known Activations