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

    Neuronpedia

    INDEX
    Explanations

    function names and method calls in a programming context

    oai_token-act-pair · gpt-3.5-turbo

    function definitions and calls in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stal
    -0.83
    flame
    -0.74
    meat
    -0.72
    bred
    -0.66
    liner
    -0.66
    azine
    -0.66
    liness
    -0.65
    manship
    -0.64
    lette
    -0.64
    æĪ¦
    -0.63
    POSITIVE LOGITS
     async
    0.80
     method
    0.75
     {}
    0.74
    eor
    0.73
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.73
     Fired
    0.73
     externalToEVAOnly
    0.73
     ->
    0.72
     {"
    0.72
     function
    0.72
    Act Density 0.018%

    No Known Activations