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

    Neuronpedia

    INDEX
    Explanations

    punctuation and markers indicative of citations or references within academic texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ork
    -0.16
    warts
    -0.16
     favor
    -0.15
    tr
    -0.15
     trav
    -0.14
     kinds
    -0.14
    wen
    -0.14
    lotte
    -0.14
    Î
    -0.14
    en
    -0.13
    POSITIVE LOGITS
    maal
    0.15
    ardy
    0.14
    lparr
    0.14
    ủi
    0.14
    eterminate
    0.14
     gul
    0.14
     chatt
    0.13
    ÅĻ
    0.13
    eydi
    0.13
     Hüs
    0.13
    Act Density 0.011%

    No Known Activations