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

    Neuronpedia

    INDEX
    Explanations

    terms related to conclusions or resolutions in narratives

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

    ending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ')")
    -0.59
    '))
    -0.56
    '));
    -0.56
    >);
    -0.54
    )))))
    -0.54
    ')))
    -0.53
     })}
    -0.50
    serviceWorker
    -0.48
    >())
    -0.48
    '])
    -0.48
    POSITIVE LOGITS
     ending
    2.17
     Ending
    2.09
    Ending
    1.92
     endings
    1.56
    ending
    1.50
    ENDING
    1.13
     terminating
    0.97
     Finishing
    0.89
    finishing
    0.89
     finishing
    0.86
    Act Density 0.004%

    No Known Activations