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

    Neuronpedia

    INDEX
    Explanations

    keywords related to legal criteria and arguments in judicial contexts

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

    justified reasons and arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.61
     itſelf
    -0.60
    ſelf
    -0.60
    ſelves
    -0.58
     Houſe
    -0.57
    IsContent
    -0.57
     betweenstory
    -0.56
     houſe
    -0.55
    TestingModule
    -0.54
     fubject
    -0.52
    POSITIVE LOGITS
     reasons
    0.54
    TargetException
    0.47
     Reasons
    0.42
    理由は
    0.40
    Reasons
    0.40
     motivos
    0.40
     reasoned
    0.39
     jus
    0.39
     arguments
    0.38
     mutat
    0.37
    Act Density 0.152%

    No Known Activations