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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "energy"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.42
    afficheront
    -0.33
     zapato
    -0.32
     száz
    -0.32
    AddTagHelper
    -0.32
    WillAppear
    -0.31
     laajenta
    -0.30
     Joachim
    -0.30
    classmethod
    -0.30
     ویکی‌پدیای
    -0.29
    POSITIVE LOGITS
    Ener
    0.93
    ener
    0.93
     bundle
    0.85
     bundles
    0.84
     energies
    0.81
     Ener
    0.79
     energy
    0.76
    ENER
    0.76
    energy
    0.76
     ENERGY
    0.75
    Act Density 0.329%

    No Known Activations