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

    Neuronpedia

    INDEX
    Explanations

    code structure and control flow elements, specifically those related to returning values and end blocks in functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucks
    -0.18
    itt
    -0.16
    eries
    -0.16
    imens
    -0.13
     Fly
    -0.13
    906
    -0.13
    rien
    -0.13
    Merit
    -0.13
    enko
    -0.13
    Ú
    -0.13
    POSITIVE LOGITS
    zig
    0.15
    éģ
    0.14
    ÑĢ
    0.14
     DISCLAIMS
    0.14
    .stack
    0.14
    IGHL
    0.13
    -fetch
    0.13
     äºİ
    0.13
    ctal
    0.13
    ufe
    0.13
    Act Density 0.116%

    No Known Activations