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

    Neuronpedia

    INDEX
    Explanations

    legal terms related to being cleared of wrongdoing or charges

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with legal verdicts and exonerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPER
    -0.77
    Hop
    -0.74
    emetery
    -0.71
    CRE
    -0.70
    Op
    -0.69
    BD
    -0.69
    KEY
    -0.69
    oppy
    -0.68
    hare
    -0.67
    DAY
    -0.66
    POSITIVE LOGITS
     acquitted
    1.11
     verdict
    0.92
    wright
    0.86
     exoner
    0.85
     unanimously
    0.82
     manslaughter
    0.79
     convict
    0.79
     indict
    0.78
    ittal
    0.78
     indicted
    0.77
    Act Density 0.025%

    No Known Activations