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

    Neuronpedia

    INDEX
    Explanations

    the repetition of the word "many" and related quantifiers

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

    many followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pettico
    -0.42
     czego
    -0.37
     job
    -0.37
    lections
    -0.36
     tight
    -0.35
    екси
    -0.34
     apron
    -0.33
     BUN
    -0.33
     stopper
    -0.33
     stuff
    -0.33
    POSITIVE LOGITS
    enumii
    0.68
    parsedMessage
    0.64
     individuals
    0.55
    Personensuche
    0.54
     others
    0.51
    Архівовано
    0.50
    Others
    0.50
    fromnode
    0.49
    others
    0.48
    AsUp
    0.48
    Act Density 0.034%

    No Known Activations