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

    Neuronpedia

    INDEX
    Explanations

    patterns representing numerical information, such as phone numbers or addresses

    oai_token-act-pair · gpt-3.5-turbo

    long sequences of special characters, dashes, and equals signs, indicating sections or dividers in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iller
    -0.82
    agos
    -0.70
     divers
    -0.67
    fish
    -0.66
     Canad
    -0.63
     Wiggins
    -0.63
    Eye
    -0.61
    anu
    -0.61
    ifice
    -0.60
     Ridley
    -0.60
    POSITIVE LOGITS
    ------------
    1.21
    -------------
    1.16
    --------------
    1.14
    ---
    1.09
    -|
    1.09
    ---------
    1.06
    ==
    1.06
    ====
    1.05
    ---------------
    1.05
    ===
    1.02
    Act Density 0.018%

    No Known Activations