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

    Neuronpedia

    INDEX
    Explanations

    phrases related to task completion and execution status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    completion or cessation messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.36
     useAppContext
    -0.32
     himo
    -0.32
    correct
    -0.31
    자인
    -0.31
     كورة
    -0.31
    Rè
    -0.30
    Adds
    -0.29
     richtige
    -0.29
    matisch
    -0.29
    POSITIVE LOGITS
     finished
    1.23
     Finished
    1.11
     completed
    1.09
     selesai
    1.09
     done
    1.04
    finished
    1.00
    Finished
    0.99
     Done
    0.98
    Done
    0.97
     finishes
    0.94
    Act Density 0.018%

    No Known Activations