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

    Neuronpedia

    INDEX
    Explanations

    moments of resolution or completion in narratives

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

    "finally"

    np_acts-logits-general · gemini-2.0-flash

    finally and concluding events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelf
    -0.72
     <<<<<<<<<<<<<<
    -0.71
     ſeveral
    -0.70
    ſelves
    -0.65
     leſs
    -0.65
     pleaſure
    -0.63
     myſelf
    -0.62
    يميديا
    -0.62
     onely
    -0.62
    zelfde
    -0.60
    POSITIVE LOGITS
     finally
    1.04
     Finally
    0.98
    finally
    0.94
    Finally
    0.94
     FINALLY
    0.85
    终于
    0.76
     finalmente
    0.75
     enfin
    0.73
    終於
    0.73
    Finalmente
    0.72
    Act Density 0.108%

    No Known Activations