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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their interaction with sentence structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icamente
    -0.16
    landers
    -0.14
    ÙİÙĩ
    -0.14
    igor
    -0.14
     Pu
    -0.14
    binations
    -0.13
    .GetItem
    -0.13
    vsp
    -0.13
    _DYNAMIC
    -0.13
    ê¸Ī
    -0.13
    POSITIVE LOGITS
    idis
    0.15
    isposable
    0.14
    azar
    0.14
     suff
    0.14
     suf
    0.14
    sense
    0.14
    ofilm
    0.14
    directive
    0.13
    rell
    0.13
    ahun
    0.13
    Act Density 0.325%

    No Known Activations