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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and certain sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inosaur
    -0.15
    ixel
    -0.14
    à¹
    -0.14
    iosk
    -0.14
    hiro
    -0.14
    _VERBOSE
    -0.14
    abbo
    -0.14
     ÙĤاب
    -0.14
    avax
    -0.14
    quo
    -0.13
    POSITIVE LOGITS
     Macro
    0.16
    /display
    0.14
     että
    0.14
     Chatt
    0.14
    ØŃاد
    0.14
     Fut
    0.14
     Ep
    0.14
    æİ¥çĿĢ
    0.14
     chute
    0.13
     Wall
    0.13
    Act Density 0.018%

    No Known Activations