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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence structure indicators within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifu
    -0.16
    ordo
    -0.15
    iaux
    -0.15
    DEX
    -0.14
    abilit
    -0.14
    ább
    -0.14
    abyrinth
    -0.14
    bern
    -0.14
    æ¢
    -0.14
    autop
    -0.14
    POSITIVE LOGITS
    ients
    0.17
    Æ°u
    0.15
    ITY
    0.14
    iesel
    0.14
    phant
    0.14
    SSI
    0.14
    linkplain
    0.14
    856
    0.14
    iggs
    0.13
    ScreenWidth
    0.13
    Act Density 1.320%

    No Known Activations