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

    Neuronpedia

    INDEX
    Explanations

    code snippets related to graphical rendering and settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     positioning
    -0.14
    ané
    -0.14
    position
    -0.13
    centre
    -0.13
     Position
    -0.12
     centre
    -0.12
    ίδ
    -0.12
    positions
    -0.12
    Position
    -0.11
     vá»ĭ
    -0.11
    POSITIVE LOGITS
     color
    0.44
     Color
    0.43
    Color
    0.40
    color
    0.40
     colors
    0.38
    -color
    0.38
    _color
    0.36
     COLOR
    0.36
    (color
    0.35
     getColor
    0.35
    Act Density 0.102%

    No Known Activations