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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their usage within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abis
    -0.17
     Hus
    -0.16
    ype
    -0.16
    sect
    -0.15
    ertz
    -0.15
    aeda
    -0.15
    iples
    -0.15
    Ñıем
    -0.15
    .FLAG
    -0.14
    zn
    -0.14
    POSITIVE LOGITS
     nods
    0.14
     Mand
    0.14
    oman
    0.14
     construction
    0.14
     rolled
    0.14
    ÏĢο
    0.14
    .bc
    0.14
     offline
    0.13
    eba
    0.13
    construction
    0.13
    Act Density 0.000%

    No Known Activations