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

    Neuronpedia

    INDEX
    Explanations

    references to oaths and sworn statements

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

    oath or sworn statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chico
    -0.42
    find
    -0.42
     chico
    -0.41
     Min
    -0.41
     find
    -0.41
     Seri
    -0.41
     Terri
    -0.40
     Herrera
    -0.40
     жив
    -0.39
    ylase
    -0.39
    POSITIVE LOGITS
     oath
    2.22
     Oath
    2.14
     oaths
    1.67
     sworn
    0.98
     swore
    0.84
     swearing
    0.80
     jura
    0.80
     vow
    0.79
     vows
    0.76
     Pledge
    0.75
    Act Density 0.007%

    No Known Activations