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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols indicating structure and breakpoints in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nyder
    -0.15
    igon
    -0.15
    ugas
    -0.15
     Cartesian
    -0.15
    igg
    -0.15
    ayne
    -0.15
    okay
    -0.15
    andard
    -0.14
    omas
    -0.14
    una
    -0.14
    POSITIVE LOGITS
    scribe
    0.15
    ãĥ¼ãĥª
    0.15
    OOK
    0.15
     Stap
    0.15
    _USED
    0.15
     Welch
    0.15
    IPH
    0.14
     Tos
    0.14
    grese
    0.14
     Niet
    0.14
    Act Density 0.238%

    No Known Activations