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

    Neuronpedia

    INDEX
    Explanations

    references to word puzzles and games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibling
    -0.16
    erti
    -0.15
    icorn
    -0.15
     Radius
    -0.15
     radius
    -0.14
    GBK
    -0.14
    curve
    -0.14
    ibar
    -0.14
    /Card
    -0.13
    adian
    -0.13
    POSITIVE LOGITS
     grid
    0.33
     grids
    0.28
     cells
    0.28
     Grid
    0.28
    grid
    0.27
     matrix
    0.27
    Grid
    0.27
    -grid
    0.26
     GRID
    0.25
     Matrix
    0.25
    Act Density 0.150%

    No Known Activations