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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "keywords" and its variations

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

    keyword / keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fjspx
    -0.50
    ']){
    -0.50
    ArrowToggle
    -0.49
    )}$.
    -0.49
    ]')
    -0.49
    ]){
    -0.48
    ])));
    -0.48
    Jereo
    -0.48
    (!(
    -0.47
    )];
    -0.47
    POSITIVE LOGITS
     keywords
    1.51
     keyword
    1.50
     Keyword
    1.34
    Keyword
    1.23
    keywords
    1.21
    keyword
    1.12
     Keywords
    1.09
    KEYWORD
    1.02
    关键词
    0.85
    Keywords
    0.83
    Act Density 0.007%

    No Known Activations