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

    Neuronpedia

    INDEX
    Explanations

    programming commands and control flow structures in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ali
    -0.15
    /fixtures
    -0.15
    ìĬ¤ì½Ķ
    -0.14
    uld
    -0.14
    zelf
    -0.14
    _itr
    -0.14
    alis
    -0.14
    /the
    -0.13
    >NN
    -0.13
    ongo
    -0.13
    POSITIVE LOGITS
    958
    0.17
    0.16
    928
    0.16
    _tac
    0.15
    828
    0.15
     squ
    0.15
    913
    0.15
    324
    0.14
    932
    0.14
    249
    0.14
    Act Density 0.119%

    No Known Activations