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

    Neuronpedia

    INDEX
    Explanations

    punctuations and sentence structures indicating dialogue and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uelle
    -0.15
    uckle
    -0.15
    aleza
    -0.14
    haft
    -0.14
    abar
    -0.14
    ienne
    -0.14
     Clintons
    -0.13
     ourselves
    -0.13
    ocument
    -0.13
     cref
    -0.13
    POSITIVE LOGITS
     Asked
    0.22
    Asked
    0.20
     Said
    0.18
     Thursday
    0.18
     asked
    0.18
     Saturday
    0.18
     Tuesday
    0.17
     Wednesday
    0.17
     Monday
    0.17
    _ask
    0.15
    Act Density 0.057%

    No Known Activations