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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate conclusions or endings

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

    ending or closing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BeforeMethod
    -0.39
     dź
    -0.36
     oglą
    -0.33
    useEffect
    -0.30
    ofluorescence
    -0.29
     hatta
    -0.29
    Indeed
    -0.28
     keç
    -0.28
    Actually
    -0.28
     vieja
    -0.28
    POSITIVE LOGITS
     ending
    0.71
     concl
    0.71
     closing
    0.69
     concludes
    0.69
     concluding
    0.69
     concluded
    0.68
     Closing
    0.68
     ended
    0.68
     finish
    0.67
     closed
    0.67
    Act Density 0.065%

    No Known Activations