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

    Neuronpedia

    INDEX
    Explanations

    terms related to health risks and safety of food or substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plug
    -0.17
    onas
    -0.17
    837
    -0.15
    ırak
    -0.15
     stick
    -0.15
     en
    -0.15
    åĬ¡
    -0.15
     Ant
    -0.15
    lease
    -0.15
     plug
    -0.15
    POSITIVE LOGITS
     dangers
    0.16
     Gould
    0.15
    unsafe
    0.15
    danger
    0.15
    çķ
    0.15
    hiba
    0.15
    Pack
    0.15
    ToLocal
    0.15
     dangerous
    0.14
    antha
    0.14
    Act Density 0.098%

    No Known Activations