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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to variables and conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illance
    -0.17
    ungle
    -0.16
    iced
    -0.16
    insky
    -0.16
    [++
    -0.15
    astics
    -0.15
    ynn
    -0.15
    Å¡il
    -0.15
    erule
    -0.14
    "&
    -0.14
    POSITIVE LOGITS
    dings
    0.16
    :↵
    0.16
    outh
    0.15
    aget
    0.15
    igen
    0.14
    gnore
    0.14
    :
    0.14
     Rim
    0.14
    ,,,
    0.14
    opot
    0.14
    Act Density 0.125%

    No Known Activations