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

    Neuronpedia

    INDEX
    Explanations

    variable names, type checks, and logical conditions in code syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ==
    -0.19
    ##
    -0.17
    ==↵
    -0.15
     ##
    -0.15
    oom
    -0.15
     nor
    -0.15
    utra
    -0.14
    ==$
    -0.14
    (getClass
    -0.14
    ))==
    -0.14
    POSITIVE LOGITS
     ===
    0.38
     !==
    0.33
    ===
    0.24
    ==='
    0.23
    ==="
    0.20
    ===↵
    0.20
    !==
    0.18
     ###
    0.17
    .includes
    0.16
     typeof
    0.16
    Act Density 0.208%

    No Known Activations