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

    Neuronpedia

    INDEX
    Explanations

    occurrences of parentheses and braces in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #/
    -0.15
    δά
    -0.15
    fec
    -0.14
    /loose
    -0.14
    ToLeft
    -0.14
    ighb
    -0.14
    arga
    -0.14
    ãĤŃãĥ¥
    -0.14
    witter
    -0.14
    ucer
    -0.14
    POSITIVE LOGITS
    icks
    0.16
     Mour
    0.15
    hou
    0.15
    ingham
    0.15
     Fruit
    0.14
    еÑĢк
    0.14
    inkle
    0.14
     screenSize
    0.14
     acomp
    0.14
    ussen
    0.14
    Act Density 0.016%

    No Known Activations