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

    Neuronpedia

    INDEX
    Explanations

    questions posed in the form of statements that end with a question mark

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly question marks and sentences ending with periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     receptive
    -0.63
     booted
    -0.62
    ailability
    -0.61
    interstitial
    -0.60
     fist
    -0.60
     notor
    -0.58
     freight
    -0.57
     rall
    -0.56
     bonded
    -0.56
     induct
    -0.55
    POSITIVE LOGITS
    [/
    1.21
     [/
    1.17
     ..."
    1.15
    >"
    1.10
    */
    1.07
     */
    1.05
    »
    1.05
     âĢ¦"
    1.02
    ãĢį
    0.97
    ãħĭãħĭ
    0.93
    Act Density 0.549%

    No Known Activations