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

    Neuronpedia

    INDEX
    Explanations

    names of people involved in legal situations

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

    Following commas, periods, or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    legal arrest and charges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    thâu
    -0.64
    +#+#
    -0.61
    featureID
    -0.61
    ValueStyle
    -0.60
    EnableWeb
    -0.57
     BorderSide
    -0.56
    tamol
    -0.56
    jsii
    -0.56
    parsedMessage
    -0.54
    ModelForm
    -0.53
    POSITIVE LOGITS
     allegedly
    0.82
     alleged
    0.80
     accused
    0.72
     pleaded
    0.72
    alleg
    0.62
     charged
    0.61
     arrested
    0.61
     defendant
    0.61
     reportedly
    0.59
     convicted
    0.58
    Act Density 0.272%

    No Known Activations