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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence-ending markers in dialogue and conversational text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    447
    -0.15
     "-//
    -0.14
    Permanent
    -0.14
     Burton
    -0.14
    och
    -0.14
     Permanent
    -0.14
    iferay
    -0.14
    ume
    -0.13
    itant
    -0.13
    uckles
    -0.13
    POSITIVE LOGITS
    all
    0.15
    rove
    0.14
    Ỽi
    0.14
    à¸Ļว
    0.13
     '/';↵
    0.13
    kart
    0.13
    erry
    0.13
     Gam
    0.12
    atti
    0.12
    ilde
    0.12
    Act Density 0.316%

    No Known Activations