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

    Neuronpedia

    INDEX
    Explanations

    code structure and function calls within a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EMA
    -0.15
    lash
    -0.15
    ard
    -0.15
    394
    -0.15
     blank
    -0.14
    ary
    -0.14
    ema
    -0.14
    wik
    -0.14
     pret
    -0.14
    weak
    -0.14
    POSITIVE LOGITS
     exit
    0.22
    éĢĢåĩº
    0.19
    exit
    0.18
    .exit
    0.18
     Exit
    0.18
    itore
    0.17
    .Exit
    0.17
    Exit
    0.17
     quitting
    0.17
     Exiting
    0.17
    Act Density 0.049%

    No Known Activations