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

    Neuronpedia

    INDEX
    Explanations

    references to formal or official statements or declarations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "The."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cum
    -0.80
    lled
    -0.72
     aka
    -0.71
    ãĤ´ãĥ³
    -0.71
    !.
    -0.70
    *.
    -0.70
    /"
    -0.70
    Ò
    -0.69
    android
    -0.68
    kai
    -0.67
    POSITIVE LOGITS
    resa
    1.26
    oret
    1.14
     notion
    1.10
     idea
    1.08
     importance
    1.02
     purpose
    1.01
     aim
    1.00
     greatest
    0.99
     biggest
    0.98
     implication
    0.97
    Act Density 0.281%

    No Known Activations