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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transitional phrases indicating progression or relationships between ideas

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

    instances of waiting or anticipation in a narrative context

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

    point of conclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     immédiatement
    -0.50
     inmediato
    -0.49
    CDCl
    -0.46
    erebbe
    -0.46
    nsis
    -0.46
     immédi
    -0.46
     ":
    -0.45
    まっている
    -0.44
     '-':
    -0.43
    대로
    -0.42
    POSITIVE LOGITS
     finally
    3.23
     eventually
    3.19
    Eventually
    2.90
     Eventually
    2.86
    eventually
    2.84
     ultimately
    2.82
    finally
    2.81
     Finally
    2.66
     finalmente
    2.65
     uiteindelijk
    2.63
    Act Density 0.593%

    No Known Activations