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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and details about wire products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nuts
    -0.17
    ocuk
    -0.15
    addin
    -0.15
    çŁ³
    -0.15
    -scrollbar
    -0.14
    hots
    -0.14
    irim
    -0.14
    iram
    -0.14
    é²ľ
    -0.14
    irit
    -0.13
    POSITIVE LOGITS
     brushes
    0.42
     brush
    0.41
     Brushes
    0.35
     Brush
    0.32
    Brush
    0.31
    brush
    0.30
     strokes
    0.27
     brushing
    0.27
     synthetic
    0.27
     br
    0.27
    Act Density 0.015%

    No Known Activations