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

    Neuronpedia

    INDEX
    Explanations

    words related to legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or commas indicating lists or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olid
    -0.72
    olo
    -0.70
    fred
    -0.68
    oslav
    -0.68
    igl
    -0.65
    cience
    -0.62
    astics
    -0.61
    lé
    -0.60
    eln
    -0.60
     bodies
    -0.59
    POSITIVE LOGITS
     namely
    1.26
     albeit
    1.17
     viz
    1.00
     however
    0.95
     though
    0.87
    albeit
    0.83
     comprising
    0.80
     although
    0.77
     consisting
    0.77
     according
    0.73
    Act Density 0.340%

    No Known Activations