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

    Neuronpedia

    INDEX
    Explanations

    specific punctuation marks that denote the end of thoughts or sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usercontent
    -0.18
    unte
    -0.16
    isode
    -0.15
     Piece
    -0.14
    iba
    -0.14
    433
    -0.14
    unken
    -0.14
    оÑģÑĢед
    -0.13
    culus
    -0.13
     piece
    -0.13
    POSITIVE LOGITS
    ym
    0.17
    missible
    0.16
    ãĤ¶ãĥ¼
    0.15
    zh
    0.15
    ati
    0.15
    eless
    0.15
     Slut
    0.14
    emand
    0.14
    essen
    0.14
    amm
    0.14
    Act Density 0.000%

    No Known Activations