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

    Neuronpedia

    INDEX
    Explanations

    functions being called or implemented in a programming context

    oai_token-act-pair · gpt-3.5-turbo

    function definitions or calls in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stal
    -1.00
    moon
    -0.74
    sea
    -0.72
    rail
    -0.71
    meat
    -0.69
    worm
    -0.69
    mong
    -0.67
    liner
    -0.66
    wire
    -0.66
    wo
    -0.66
    POSITIVE LOGITS
     externalToEVAOnly
    0.82
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.78
    eor
    0.76
    ãĤ´ãĥ³
    0.73
    /-
    0.71
     Fired
    0.70
     payable
    0.69
    #$
    0.67
    ){
    0.67
     {"
    0.67
    Act Density 0.026%

    No Known Activations