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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.67
    ufact
    -0.64
    ategory
    -0.61
     associates
    -0.61
    cks
    -0.59
    fg
    -0.58
    hov
    -0.57
     whence
    -0.57
     exting
    -0.56
    aded
    -0.55
    POSITIVE LOGITS
     slightest
    1.06
     same
    1.00
     requisite
    0.90
     impression
    0.88
     necessary
    0.86
     distinction
    0.85
    ses
    0.83
     utmost
    0.83
     latter
    0.82
     unthinkable
    0.81
    Act Density 0.108%

    No Known Activations