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

    Neuronpedia

    INDEX
    Explanations

    testimonies involving interactions and statements made during legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    a defendant

    np_acts-logits-general · gemini-2.0-flash

    defendant had done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RouterModule
    -0.87
    ArgsConstructor
    -0.71
     yummy
    -0.71
    Espèce
    -0.69
     gracefully
    -0.68
     delightfully
    -0.68
     deliciously
    -0.67
     voilà
    -0.66
    łaszcza
    -0.66
    PRNewswire
    -0.65
    POSITIVE LOGITS
     defendant
    0.80
     Defendant
    0.70
     supuestamente
    0.69
     marihuana
    0.60
    defendant
    0.60
     appellant
    0.59
     defendants
    0.58
     allegedly
    0.58
    Defendant
    0.57
     consens
    0.57
    Act Density 1.427%

    No Known Activations