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

    Neuronpedia

    INDEX
    Explanations

    references to legal institutions and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific courthouse or legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hol
    -0.65
     belt
    -0.64
     Shining
    -0.64
     withholding
    -0.62
     Hungarian
    -0.61
    OV
    -0.60
     rooting
    -0.59
     curfew
    -0.59
     donor
    -0.58
    urized
    -0.58
    POSITIVE LOGITS
    tyard
    1.53
    thouse
    1.31
    tesy
    1.15
    ser
    1.15
    sers
    1.12
    cour
    1.11
    ses
    1.06
    tes
    1.05
    rier
    1.04
    ten
    1.02
    Act Density 0.034%

    No Known Activations