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

    Neuronpedia

    INDEX
    Explanations

    terms related to ethnicity and chemical compounds

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Westinghouse
    -0.82
     الحره
    -0.73
     Welle
    -0.73
     Hera
    -0.72
    OpenHelper
    -0.72
     Catharine
    -0.70
     διά
    -0.70
     Geller
    -0.70
    randrange
    -0.69
    prese
    -0.68
    POSITIVE LOGITS
     eth
    1.08
     Eth
    1.00
    eth
    0.93
    Eth
    0.86
     ETH
    0.84
    setVerticalGroup
    0.76
    odils
    0.76
    ETH
    0.75
    protoc
    0.74
     BoxFit
    0.70
    Act Density 0.006%

    No Known Activations