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

    Neuronpedia

    INDEX
    Explanations

    code formatting elements and syntax indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    classnames
    -0.53
     rhestr
    -0.48
    ftagPool
    -0.47
    cetes
    -0.45
     ujednoznacz
    -0.43
     CreateTagHelper
    -0.42
     autorytatywna
    -0.42
    newArrayList
    -0.41
    tagPool
    -0.40
    нгред
    -0.40
    POSITIVE LOGITS
    TagMode
    0.54
     nothwendig
    0.46
     Meksiku
    0.45
    AccessorTable
    0.42
     nemlig
    0.42
    InstrumentedTest
    0.42
     препратки
    0.41
    FunctionFlags
    0.41
     indígen
    0.40
    numerusform
    0.39
    Act Density 1.214%

    No Known Activations