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

    Neuronpedia

    INDEX
    Explanations

    occurrences of various types of quotation marks and parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code delimiters followed by content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.60
    帖最后由
    -0.58
     ſta
    -0.58
     Houſe
    -0.58
     Reſ
    -0.57
     Anſ
    -0.56
    aarrggbb
    -0.56
     houſe
    -0.56
     ſeveral
    -0.56
    dafx
    -0.54
    POSITIVE LOGITS
     Nashville
    0.39
    weile
    0.39
    grü
    0.35
    Nashville
    0.35
    gado
    0.34
    hdys
    0.34
    assung
    0.32
    isabeth
    0.32
     Dallas
    0.32
    스터
    0.31
    Act Density 0.093%

    No Known Activations