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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions, decisions, and contributions

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or present participles indicating actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eria
    -0.77
    youtube
    -0.72
    eg
    -0.68
    peg
    -0.68
    tg
    -0.67
    ember
    -0.66
    UI
    -0.66
    wow
    -0.65
    CDC
    -0.65
    .?
    -0.64
    POSITIVE LOGITS
     instead
    0.69
     untold
    0.67
    theless
    0.66
     unsus
    0.66
     aside
    0.65
     them
    0.64
     professions
    0.63
     apologies
    0.62
     only
    0.62
     comparisons
    0.61
    Act Density 0.318%

    No Known Activations