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

    Neuronpedia

    INDEX
    Explanations

    indicators of uncertainty or variability in statements and claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.49
     дописавши
    -0.39
     Parish
    -0.36
    isContained
    -0.36
    writeField
    -0.36
     wireType
    -0.36
    TabStop
    -0.35
    EndProject
    -0.34
     dAtA
    -0.34
     Edwin
    -0.34
    POSITIVE LOGITS
     Jednak
    0.60
    However
    0.59
     However
    0.59
     Yet
    0.57
     namun
    0.57
    Yet
    0.57
     however
    0.56
     однако
    0.54
     però
    0.54
    днако
    0.53
    Act Density 1.271%

    No Known Activations