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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases introducing content

    oai_token-act-pair · gpt-3.5-turbo

    the end of text tokens or represent empty content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anamo
    -0.71
    76561
    -0.70
     Izan
    -0.68
    onto
    -0.67
    nown
    -0.66
    adle
    -0.66
    aths
    -0.62
    witz
    -0.62
    omo
    -0.61
    ially
    -0.61
    POSITIVE LOGITS
     week
    0.88
     article
    0.86
     month
    0.80
     particular
    0.78
     year
    0.78
     item
    0.78
     recipe
    0.78
     amazing
    0.76
     wiki
    0.75
     nifty
    0.75
    Act Density 0.168%

    No Known Activations