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

    Neuronpedia

    INDEX
    Explanations

    references to toxicity

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

    toxicity testing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.41
    erv
    -0.39
    олові
    -0.38
     Ат
    -0.38
    JspWriter
    -0.36
     ویکی‌پدی
    -0.36
     natin
    -0.36
     Empres
    -0.36
    erialized
    -0.36
    getDeclared
    -0.36
    POSITIVE LOGITS
     toxicity
    2.39
     Toxicity
    2.25
    Toxicity
    2.08
    toxicity
    1.50
     cytotoxicity
    1.38
     TOXIC
    1.13
     toxicological
    1.09
    xicity
    1.05
     toxicology
    1.05
     toxic
    1.00
    Act Density 0.011%

    No Known Activations