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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being "off-the-grid"

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases or expressions related to performance or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ihar
    -0.72
    awaru
    -0.69
    anamo
    -0.67
    terday
    -0.62
     dismissing
    -0.62
     Rica
    -0.62
    ongyang
    -0.61
    theless
    -0.61
    DragonMagazine
    -0.60
    Ô
    -0.60
    POSITIVE LOGITS
    same
    1.09
    purpose
    0.93
    middle
    0.92
    highest
    0.90
    prem
    0.88
    best
    0.88
    distance
    0.86
    cycle
    0.84
    upper
    0.84
    arms
    0.83
    Act Density 0.018%

    No Known Activations