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

    Neuronpedia

    INDEX
    Explanations

    chemical substances or compounds

    oai_token-act-pair · gpt-3.5-turbo

    references to toxic and hazardous chemicals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ership
    -0.92
    Fal
    -0.81
    oÄŁ
    -0.77
    ĺħ
    -0.76
    ļé
    -0.72
    esan
    -0.71
    resents
    -0.70
     Braves
    -0.70
     Fellowship
    -0.69
    heit
    -0.68
    POSITIVE LOGITS
     chemicals
    1.00
     chemically
    0.99
     dioxide
    0.95
     additives
    0.93
     sprayed
    0.92
     compounds
    0.87
     oxid
    0.87
    amines
    0.86
     contamin
    0.84
     pollutants
    0.84
    Act Density 0.033%

    No Known Activations