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

    Neuronpedia

    INDEX
    Explanations

    terms related to material composition and structural layers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     faute
    -0.36
    ActionResult
    -0.35
     sujet
    -0.33
    unchecked
    -0.33
    zete
    -0.33
     ries
    -0.33
     Grandfather
    -0.33
    }`).
    -0.32
    textAppearance
    -0.32
    зар
    -0.32
    POSITIVE LOGITS
     layers
    0.91
     layer
    0.88
     Layers
    0.82
     Schichten
    0.81
     thickness
    0.76
     Layer
    0.73
     Schicht
    0.71
     layering
    0.70
    principalTable
    0.67
     LAYER
    0.67
    Act Density 1.032%

    No Known Activations