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

    Neuronpedia

    INDEX
    Explanations

    specific patterns or structures in the text, particularly related to measurements or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GenerationType
    -0.72
    expandindo
    -0.71
     Meksiku
    -0.70
     estatales
    -0.69
     مصرى
    -0.69
    TestBed
    -0.69
    Rüyada
    -0.68
    पया
    -0.68
     Cinque
    -0.68
     hemsida
    -0.66
    POSITIVE LOGITS
     bits
    2.09
    bits
    1.92
     Bits
    1.83
    Bits
    1.71
    BITS
    1.22
     BITS
    1.22
     pieces
    1.13
     snippets
    1.05
     fragments
    1.01
     tid
    1.01
    Act Density 0.146%

    No Known Activations