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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate repetition or emphasis in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     indeed
    -0.20
    nga
    -0.17
     genuine
    -0.15
    Äħ
    -0.15
     Kendrick
    -0.15
     ``
    -0.14
     Indeed
    -0.14
    ç«Ł
    -0.14
    ICODE
    -0.14
    OOT
    -0.14
    POSITIVE LOGITS
    ucci
    0.17
    enaire
    0.15
     -*-č↵
    0.15
    again
    0.15
    hod
    0.15
     Again
    0.14
    adeon
    0.14
     again
    0.14
    MAR
    0.14
    ucket
    0.14
    Act Density 0.024%

    No Known Activations