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

    Neuronpedia

    INDEX
    Explanations

    key concepts related to systems, processes, and their evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     specifically
    -0.14
     Uncle
    -0.13
    oven
    -0.13
     overall
    -0.13
    mouseenter
    -0.13
    úb
    -0.13
     alternate
    -0.13
    iren
    -0.12
     included
    -0.12
    afort
    -0.12
    POSITIVE LOGITS
     continuation
    0.33
     continuing
    0.31
     continue
    0.29
     continues
    0.28
    continue
    0.27
     continued
    0.27
    继ç»Ń
    0.27
     пÑĢодолж
    0.27
     continu
    0.26
    contin
    0.26
    Act Density 0.016%

    No Known Activations