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

    Neuronpedia

    INDEX
    Explanations

    phrases and terminology related to legal pleas and guilty verdicts

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

    guilty pleas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.66
    RectangleBorder
    -0.57
     الحره
    -0.55
     Италијани
    -0.54
     estekak
    -0.51
    ########.
    -0.51
    bootstrapcdn
    -0.50
    SequentialGroup
    -0.50
     Italijanski
    -0.49
     مشين
    -0.48
    POSITIVE LOGITS
    XmlRootElement
    0.47
    SerializedName
    0.42
     guilty
    0.39
     wireType
    0.35
    TagHelper
    0.35
     arraigned
    0.35
    guilty
    0.34
    pyx
    0.34
    Guilty
    0.34
     Musiker
    0.33
    Act Density 0.293%

    No Known Activations