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

    Neuronpedia

    INDEX
    Explanations

    various instances and descriptions of locations or positional attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThemeOverlay
    -0.44
    AndView
    -0.38
    tenths
    -0.35
    первых
    -0.33
    Horiz
    -0.32
    ieza
    -0.32
    ContentAlignment
    -0.31
    EndTag
    -0.31
    ものです
    -0.31
    ̍t
    -0.31
    POSITIVE LOGITS
     opposite
    0.94
     sides
    0.77
     outside
    0.74
    opposite
    0.73
     edge
    0.68
     Rückseite
    0.68
     underside
    0.68
     side
    0.68
     top
    0.68
     backside
    0.66
    Act Density 0.547%

    No Known Activations