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

    Neuronpedia

    INDEX
    Explanations

    terms related to flying or movement in the air

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Henson
    -0.87
     EClass
    -0.83
     fjord
    -0.79
     Corde
    -0.78
     дописавши
    -0.77
     Coe
    -0.75
     esboço
    -0.73
    setVerticalGroup
    -0.73
     Kazim
    -0.73
     aDecoder
    -0.72
    POSITIVE LOGITS
     FLY
    1.23
     fly
    1.21
     Fly
    1.21
    FLY
    1.17
     flies
    1.16
    fly
    1.11
    Fly
    1.09
     Flies
    1.03
    rosophila
    0.97
    ogaster
    0.90
    Act Density 0.011%

    No Known Activations