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

    Neuronpedia

    INDEX
    Explanations

    quotes in a conversation

    oai_token-act-pair · gpt-3.5-turbo

    the presence of quoted speech or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.78
    »Ĵ
    -0.73
    ¬¼
    -0.73
    ²¾
    -0.72
    ingu
    -0.70
    ĪĴ
    -0.70
    anuts
    -0.69
    ·
    -0.68
    İĭ
    -0.65
    rats
    -0.65
    POSITIVE LOGITS
     reads
    1.13
    said
    1.11
     said
    1.08
     says
    1.06
     wrote
    0.97
     recalls
    0.89
     writes
    0.87
     joked
    0.85
     exclaimed
    0.84
     commented
    0.84
    Act Density 0.091%

    No Known Activations