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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal jargon and court proceedings

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal judgments and court decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    toggle
    -0.78
    illion
    -0.72
    fortune
    -0.68
    mares
    -0.66
    nces
    -0.64
    ruary
    -0.64
    isSpecialOrderable
    -0.64
    FOX
    -0.62
    slaught
    -0.62
     whispers
    -0.62
    POSITIVE LOGITS
     violated
    1.19
     unfit
    1.15
     insufficient
    1.10
     unfairly
    1.10
     unconstitutional
    1.10
     deserved
    1.09
     ineligible
    1.07
     unacceptable
    1.04
     warranted
    1.04
     sufficiently
    1.01
    Act Density 0.605%

    No Known Activations