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

    Neuronpedia

    INDEX
    Explanations

    mentions of action-related terms in descriptive contexts such as "action-packed," "fast-paced," or references to events happening rapidly

    oai_token-act-pair · gpt-3.5-turbo

    references to action-related content in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mbuds
    -0.71
    gling
    -0.68
    IX
    -0.66
    uran
    -0.65
    mining
    -0.64
    under
    -0.64
    ©¶æ
    -0.63
    orns
    -0.61
    yah
    -0.61
    YL
    -0.60
    POSITIVE LOGITS
    bender
    0.91
     action
    0.85
    ername
    0.81
    action
    0.75
    bucks
    0.75
    ngth
    0.74
    netflix
    0.73
     Replay
    0.71
    dad
    0.70
    ulus
    0.68
    Act Density 0.023%

    No Known Activations