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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accumulation or completion

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating aggregation or accumulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rouse
    -0.77
    Reviewed
    -0.67
    Released
    -0.66
    cknowled
    -0.65
    Anne
    -0.65
     invention
    -0.65
    ni
    -0.64
    oway
    -0.64
    opher
    -0.64
    ially
    -0.61
    POSITIVE LOGITS
    ©¶æ¥µ
    0.82
    MpServer
    0.78
    skirts
    0.76
    river
    0.74
    grading
    0.71
    number
    0.66
    ulpt
    0.66
    rights
    0.65
    dating
    0.65
     totals
    0.65
    Act Density 0.032%

    No Known Activations