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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to behavior or attitudes

    oai_token-act-pair · gpt-3.5-turbo

    qualifiers that emphasize realism, seriousness, and constructive attitudes in discussions or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ranked
    -0.66
    formance
    -0.64
    ruction
    -0.61
     Gle
    -0.61
    aleb
    -0.61
    omination
    -0.60
    Bet
    -0.60
    href
    -0.59
    Bur
    -0.59
    UCT
    -0.58
    POSITIVE LOGITS
    nell
    0.75
     enough
    0.72
    ryu
    0.71
    ptic
    0.70
    ãĥ¼ãĤ¯
    0.69
    retty
    0.67
    leep
    0.66
    enough
    0.66
    ikes
    0.66
    asso
    0.64
    Act Density 0.266%

    No Known Activations