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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically periods and question marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sting
    -0.15
    etes
    -0.14
    essa
    -0.14
    onda
    -0.14
    ogan
    -0.14
    lr
    -0.13
    iler
    -0.13
    onian
    -0.13
     godt
    -0.13
    ÑĢаÑģ
    -0.13
    POSITIVE LOGITS
    andel
    0.17
    *)_
    0.16
    _OC
    0.15
    udget
    0.15
    andler
    0.14
    avi
    0.14
     Khu
    0.13
    ozem
    0.13
    obao
    0.13
    allis
    0.13
    Act Density 0.002%

    No Known Activations