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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal activities and legal proceedings

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    adish
    -0.78
    clips
    -0.70
    angular
    -0.69
    estamp
    -0.68
    tip
    -0.67
    pid
    -0.67
    atos
    -0.63
    edia
    -0.63
    own
    -0.62
    rising
    -0.62
    POSITIVE LOGITS
     verdict
    0.91
     plea
    0.90
     Guilty
    0.86
     guilty
    0.84
     manslaughter
    0.83
     sentencing
    0.83
     to
    0.82
     probation
    0.80
     voluntarily
    0.78
    Prosecut
    0.77
    Act Density 0.034%

    No Known Activations