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

    Neuronpedia

    INDEX
    Explanations

    references to workplace safety and regulations

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

    safety and accidents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.44
     idéia
    -0.39
     BrowserModule
    -0.36
    เผ
    -0.35
     Ανακτήθηκε
    -0.35
     parvenir
    -0.35
     mußten
    -0.35
     résister
    -0.34
    ringing
    -0.34
     thẩm
    -0.34
    POSITIVE LOGITS
    Safety
    0.68
     Safety
    0.68
     safety
    0.64
    safety
    0.56
     SAFETY
    0.55
    SAFETY
    0.52
     Sécurité
    0.49
     accidents
    0.48
     Accident
    0.47
    ymce
    0.47
    Act Density 0.006%

    No Known Activations