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

    Neuronpedia

    INDEX
    Explanations

    terms related to exposure to hazardous substances or pollutants

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     reveal
    -0.57
    TestRunner
    -0.57
    yos
    -0.57
     revealing
    -0.56
     revealed
    -0.55
    veness
    -0.54
    ficial
    -0.54
    y
    -0.54
     uncovered
    -0.53
     exposed
    -0.52
    POSITIVE LOGITS
    Vidite
    0.86
     fidé
    0.68
     ainfi
    0.65
     historiques
    0.63
     EconPapers
    0.63
     fraî
    0.61
     rembour
    0.61
     hjemme
    0.61
    JAMIN
    0.61
     réguli
    0.60
    Act Density 0.003%

    No Known Activations