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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation or commas, indicating lists or items in a sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okies
    -0.14
    ī´
    -0.14
    ieri
    -0.14
     æĿ
    -0.14
    beits
    -0.14
    unter
    -0.14
    ubbo
    -0.13
    uzzi
    -0.13
    irim
    -0.13
    Nova
    -0.13
    POSITIVE LOGITS
    hip
    0.17
    .answers
    0.15
     term
    0.15
     Publishers
    0.14
     Kraj
    0.14
    uso
    0.14
    áŀ¶áŀ
    0.14
    æĽ°
    0.14
    hin
    0.13
    .disc
    0.13
    Act Density 0.057%

    No Known Activations