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

    Neuronpedia

    INDEX
    Explanations

    names and titles of scientific works or references related to physical sciences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.85
    enumii
    -0.84
    aarrggbb
    -0.82
    HasAnnotation
    -0.81
     TextAppearance
    -0.79
    OGND
    -0.79
     BorderSide
    -0.78
     InputDecoration
    -0.77
    MLLoader
    -0.76
     nakalista
    -0.74
    POSITIVE LOGITS
     W
    1.04
    W
    0.94
     w
    0.92
    w
    0.88
    первых
    0.88
    wo
    0.83
     Wi
    0.83
     Wach
    0.80
     WAR
    0.79
     Wo
    0.77
    Act Density 0.985%

    No Known Activations