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

    Neuronpedia

    INDEX
    Explanations

    instances where individuals or groups are involved in specific actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be" in various tenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Highlights
    -0.69
     Highlands
    -0.65
    ertodd
    -0.65
    inav
    -0.64
     override
    -0.61
    heny
    -0.60
    Õ
    -0.60
     Shall
    -0.60
    =-=-
    -0.59
     Space
    -0.59
    POSITIVE LOGITS
     supposed
    1.14
     accustomed
    1.03
     doing
    0.98
     able
    0.98
     going
    0.97
     experiencing
    0.92
     destined
    0.92
     trying
    0.91
     aware
    0.89
     gonna
    0.88
    Act Density 0.164%

    No Known Activations