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

    Neuronpedia

    INDEX
    Explanations

    terms related to monitoring and adjustments in processes or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esModule
    -0.78
    TagHelper
    -0.78
    vanced
    -0.71
    MessageTagHelper
    -0.70
    addCriterion
    -0.70
    tagHelper
    -0.68
     protoimpl
    -0.67
    OrBuilder
    -0.66
    liani
    -0.66
    AntiForgeryToken
    -0.65
    POSITIVE LOGITS
     sometimes
    0.98
     usually
    0.97
     often
    0.90
    Sometimes
    0.86
    Usually
    0.85
    sometimes
    0.84
     oftentimes
    0.80
    usually
    0.80
     Usually
    0.80
     Sometimes
    0.79
    Act Density 0.749%

    No Known Activations