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

    Neuronpedia

    INDEX
    Explanations

    legal concepts related to probable cause and justifications for actions

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

    justification or reason

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UserScript
    -0.52
    contentLoaded
    -0.48
    sidemargin
    -0.46
    httphttps
    -0.43
    styleType
    -0.41
    TagMode
    -0.40
    OpenHelper
    -0.39
    (!__
    -0.39
     CURLOPT
    -0.38
     незавершена
    -0.38
    POSITIVE LOGITS
     justification
    0.78
     Justification
    0.78
     justified
    0.77
    justified
    0.72
     reason
    0.72
     Reasons
    0.72
     gius
    0.70
     justifies
    0.70
     Reason
    0.68
     excuse
    0.68
    Act Density 0.322%

    No Known Activations