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

    Neuronpedia

    INDEX
    Explanations

    references to health concerns related to chemicals in products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     اÙĨج
    -0.15
    dyn
    -0.15
     oxygen
    -0.14
     Oxygen
    -0.14
    ãĤ±
    -0.14
     Ecc
    -0.14
    quality
    -0.14
    pond
    -0.14
    _COLL
    -0.14
    åĿĬ
    -0.14
    POSITIVE LOGITS
     bis
    0.30
     Bis
    0.28
     exposures
    0.24
     flame
    0.22
     Exposure
    0.21
     exposure
    0.21
    bis
    0.21
     horm
    0.20
     Flame
    0.19
     plastic
    0.18
    Act Density 0.048%

    No Known Activations