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

    Neuronpedia

    INDEX
    Explanations

    sections of the document distinguished by formatting or separators, indicating structural elements in technical writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     שוליים
    -0.91
    featureID
    -0.81
     snippetHide
    -0.81
    AndEndTag
    -0.79
     GenerationType
    -0.77
     وتسجيلات
    -0.75
    Datuak
    -0.71
     AppComponent
    -0.69
     оригіналу
    -0.69
     CreateTagHelper
    -0.69
    POSITIVE LOGITS
    ================
    0.95
    cmd
    0.77
     cmd
    0.62
    CMD
    0.59
    ===========
    0.55
     CMD
    0.54
     alla
    0.51
    ============
    0.50
    ====
    0.49
    =============
    0.49
    Act Density 0.080%

    No Known Activations