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

    Neuronpedia

    INDEX
    Explanations

    references to a grid or grid-like structures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çݯ
    -0.15
    çĴ°
    -0.14
    adla
    -0.14
    اÙī
    -0.14
    esses
    -0.14
    à¸µà¸Ľ
    -0.14
    âķij
    -0.14
    ora
    -0.14
    triangle
    -0.14
    ãĥĨãĥ«
    -0.14
    POSITIVE LOGITS
    iron
    0.33
    lock
    0.25
    IRON
    0.23
    der
    0.23
    BagConstraints
    0.23
    /grid
    0.22
    DED
    0.22
    locked
    0.20
    locks
    0.19
    .Grid
    0.19
    Act Density 0.012%

    No Known Activations