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

    Neuronpedia

    INDEX
    Explanations

    crimes or legal charges involving physical harm or endangerment

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ROM
    -0.71
    opa
    -0.70
    SAM
    -0.69
    soDeliveryDate
    -0.68
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.66
    Enlarge
    -0.63
     ãĤµ
    -0.63
    Grad
    -0.62
    amous
    -0.62
    Reviewer
    -0.61
    POSITIVE LOGITS
     manslaughter
    1.27
     offences
    1.09
     aggravated
    1.03
     misdemeanor
    1.00
     felony
    0.99
     causing
    0.99
     offenses
    0.96
     charges
    0.95
     stemming
    0.94
     punishable
    0.93
    Act Density 0.134%

    No Known Activations