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

    Neuronpedia

    INDEX
    Explanations

    strings that indicate formatting or structured data outputs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     further
    -0.44
    -
    -0.42
    vá
    -0.41
    mainAxisSize
    -0.41
     only
    -0.40
     "
    -0.40
     não
    -0.39
     throughout
    -0.39
     or
    -0.39
     has
    -0.39
    POSITIVE LOGITS
    ագրություններ
    1.31
    enumi
    1.17
    NameInMap
    1.12
     >=",
    1.11
     Италијани
    1.10
    AddTagHelper
    1.09
     kasarigan
    1.08
     nahilalakip
    1.07
    Tembelea
    1.07
     ExecuteAsync
    1.07
    Act Density 0.040%

    No Known Activations