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

    Neuronpedia

    INDEX
    Explanations

    dates and specific details of events

    oai_token-act-pair · gpt-3.5-turbo

    sentences that indicate strong opinions or assessments about political or humanitarian issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    boro
    -0.77
    utical
    -0.70
     compass
    -0.67
     adolesc
    -0.66
    ĺħ
    -0.64
    abouts
    -0.63
     endeav
    -0.62
     equip
    -0.62
     commissions
    -0.61
     solic
    -0.61
    POSITIVE LOGITS
    Asked
    1.07
    Meanwhile
    1.07
    ccording
    1.04
    Related
    1.03
    However
    1.00
    Earlier
    0.94
    Prime
    0.93
    Despite
    0.93
    Nevertheless
    0.92
    Reuters
    0.91
    Act Density 0.668%

    No Known Activations