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

    Neuronpedia

    INDEX
    Explanations

    references to specific page numbers and citations in a document

    oai_token-act-pair · gpt-3.5-turbo

    numerical references and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disposable
    -0.69
     steady
    -0.63
    direction
    -0.63
     loyal
    -0.61
     scrut
    -0.60
     relentless
    -0.59
     wage
    -0.58
     tides
    -0.58
     stead
    -0.57
     tut
    -0.57
    POSITIVE LOGITS
     ff
    1.14
     âĨij
    0.98
    ff
    0.86
    69
    0.85
     seq
    0.85
    68
    0.83
    71
    0.83
    663
    0.82
    74
    0.81
    67
    0.81
    Act Density 0.081%

    No Known Activations