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

    Neuronpedia

    INDEX
    Explanations

    patterns related to function definitions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ļĮ
    -0.17
    ÙĤرار
    -0.14
    oca
    -0.14
    ruk
    -0.14
    óc
    -0.13
     naken
    -0.13
     Valent
    -0.13
    .bukkit
    -0.13
    ;break
    -0.13
     Hust
    -0.13
    POSITIVE LOGITS
     done
    0.35
    done
    0.33
     Done
    0.30
    Done
    0.27
    (done
    0.27
    -done
    0.27
     DONE
    0.26
    DONE
    0.26
    .done
    0.25
    _done
    0.25
    Act Density 0.010%

    No Known Activations