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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or limitations in research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     дописавши
    -0.63
     totiž
    -0.61
     kasarigan
    -0.60
    ponses
    -0.59
    átku
    -0.59
     entanto
    -0.56
    +:+
    -0.56
    ]):
    -0.55
    Primero
    -0.52
    ]=>
    -0.52
    POSITIVE LOGITS
     finally
    3.32
     Finally
    3.28
    Finally
    3.18
     lastly
    3.09
     Lastly
    3.03
    Lastly
    2.99
    finally
    2.90
     enfin
    2.73
     Enfin
    2.59
     infine
    2.47
    Act Density 0.436%

    No Known Activations