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

    Neuronpedia

    INDEX
    Explanations

    references to specific items or categories repeatedly indicated by the term "these."

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

    these followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.60
     onPostExecute
    -0.50
     للاسماء
    -0.47
     EconPapers
    -0.47
     useRef
    -0.46
     Italijanski
    -0.45
     Vikipedi
    -0.45
    EndInit
    -0.44
    PreferredItem
    -0.43
    libft
    -0.43
    POSITIVE LOGITS
     these
    0.56
    These
    0.54
     These
    0.54
     THESE
    0.49
    這些
    0.47
    这些
    0.47
     estos
    0.40
     following
    0.40
    these
    0.40
    addPreferredGap
    0.40
    Act Density 0.080%

    No Known Activations