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

    Neuronpedia

    INDEX
    Explanations

    references to products and their associated qualities or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     esche
    -0.71
     ujednoznacz
    -0.70
    —”
    -0.67
    —“
    -0.66
     Wiktionnaire
    -0.61
    —"
    -0.61
    !—
    -0.60
    ymce
    -0.58
     speckled
    -0.57
     ostensibly
    -0.57
    POSITIVE LOGITS
     have
    0.99
     are
    0.91
     is
    0.82
     has
    0.77
     give
    0.75
     were
    0.74
     gives
    0.74
     was
    0.72
     gonna
    0.71
     got
    0.71
    Act Density 1.087%

    No Known Activations