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

    Neuronpedia

    INDEX
    Explanations

    words with the prefix "un-" indicating negation or the opposite of a condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.69
    tagHelper
    -0.58
     الرياضيه
    -0.58
     CascadeType
    -0.57
     Chwiliwch
    -0.56
    ckså
    -0.56
    RenderAtEndOf
    -0.56
    ulipas
    -0.56
    Personendaten
    -0.55
    WithIOException
    -0.55
    POSITIVE LOGITS
     un
    1.52
     Un
    1.39
    Un
    1.33
    un
    1.14
     UN
    1.00
    Uns
    0.85
     Uns
    0.85
     uns
    0.82
    UN
    0.81
     Una
    0.81
    Act Density 0.166%

    No Known Activations