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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "swear" and its variations

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

    swear, sworn, allegiance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CTP
    -0.61
     RTI
    -0.58
     IMC
    -0.55
     Hancock
    -0.54
     RTC
    -0.54
     STC
    -0.52
     PPI
    -0.51
    ộc
    -0.51
    mika
    -0.50
     ATL
    -0.50
    POSITIVE LOGITS
     swear
    1.99
     swears
    1.75
     swore
    1.72
     swearing
    1.52
     sworn
    1.13
     oath
    0.90
     oaths
    0.88
     jura
    0.86
     Oath
    0.72
     formales
    0.71
    Act Density 0.003%

    No Known Activations