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

    Neuronpedia

    INDEX
    Explanations

    references to the number four

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

    the number four

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elis
    -0.54
    ZL
    -0.54
    belline
    -0.52
    genesis
    -0.52
     Ideology
    -0.50
    tent
    -0.50
    enton
    -0.50
    zine
    -0.50
    iculo
    -0.49
    chitis
    -0.49
    POSITIVE LOGITS
     four
    1.60
    four
    1.41
     Four
    1.34
    Four
    1.33
     FOUR
    1.32
     cuatro
    1.14
    FOUR
    1.14
     quatro
    1.14
     quatre
    1.14
     vier
    1.13
    Act Density 0.016%

    No Known Activations