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

    Neuronpedia

    INDEX
    Explanations

    punctuation, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ULO
    -0.17
    nech
    -0.16
     hum
    -0.16
    _qp
    -0.15
    udes
    -0.15
    ÙħÙĬ
    -0.14
    lest
    -0.14
    pheric
    -0.14
     toc
    -0.14
    quential
    -0.14
    POSITIVE LOGITS
    andel
    0.15
    erea
    0.15
    undle
    0.14
    aley
    0.14
    립
    0.14
     Bis
    0.14
    addon
    0.14
     Ramp
    0.14
     diz
    0.14
    ẳn
    0.14
    Act Density 0.003%

    No Known Activations