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

    Neuronpedia

    INDEX
    Explanations

    the word "ink" followed by a number

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ£
    -0.81
    è¦ļéĨĴ
    -0.78
    ccording
    -0.74
    blance
    -0.69
    ODUCT
    -0.65
    ppa
    -0.64
     goose
    -0.63
    APH
    -0.61
    ignty
    -0.60
    Interstitial
    -0.59
    POSITIVE LOGITS
    erman
    1.10
    ery
    1.06
    ering
    1.03
    edin
    0.98
    ansen
    0.97
     wink
    0.95
    ert
    0.90
    erm
    0.89
    enstein
    0.87
    owski
    0.86
    Act Density 0.023%

    No Known Activations