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

    Neuronpedia

    INDEX
    Explanations

    specific details or particulars mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    references to specific details or particulars in discussions or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rams
    -0.66
     Gates
    -0.62
    =-=-=-=-=-=-=-=-
    -0.61
    ipel
    -0.61
     Greenwood
    -0.60
     Sus
    -0.59
     Jong
    -0.59
    tre
    -0.59
    INTER
    -0.58
    Station
    -0.57
    POSITIVE LOGITS
     specifics
    1.13
     details
    0.99
     particulars
    0.94
    uggest
    0.93
     detail
    0.87
    details
    0.86
    metadata
    0.79
     IMAGES
    0.78
    wcs
    0.78
     wording
    0.77
    Act Density 0.008%

    No Known Activations