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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the word "of"

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

    number of plurals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.47
    ValueGenerated
    -0.44
     rêves
    -0.44
    WritableDatabase
    -0.44
     crux
    -0.41
     Belajar
    -0.41
    belt
    -0.40
    SOUNDBITE
    -0.40
    dreams
    -0.40
     Fazit
    -0.40
    POSITIVE LOGITS
    getNumberOf
    0.94
    NumberOf
    0.90
     numberOf
    0.89
     noOf
    0.88
     aantal
    0.87
    numberOf
    0.84
     antal
    0.83
    Cuántos
    0.76
     getNum
    0.76
    noOf
    0.75
    Act Density 0.037%

    No Known Activations