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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords indicating the end of processes or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quez
    -0.17
     minded
    -0.17
    oenix
    -0.16
    intage
    -0.16
    696
    -0.15
    -minded
    -0.15
    kills
    -0.14
    âĢĮشدÙĩ
    -0.14
    pery
    -0.14
    duck
    -0.14
    POSITIVE LOGITS
    owment
    0.33
    earing
    0.30
    urance
    0.29
    /start
    0.28
    ogenous
    0.27
    ear
    0.27
    angered
    0.27
    ocrine
    0.27
    orses
    0.27
    ereço
    0.26
    Act Density 0.099%

    No Known Activations