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

    Neuronpedia

    INDEX
    Explanations

    phrases related to verbal communication or speech

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation, particularly quotation marks and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.90
    Ĥª
    -0.86
    ¬¼
    -0.83
    ibrary
    -0.83
    £ı
    -0.83
    İĭ
    -0.82
    »Ĵ
    -0.75
    itionally
    -0.72
    ĻĤ
    -0.72
    ramid
    -0.71
    POSITIVE LOGITS
     says
    1.18
     whispered
    1.06
     said
    1.02
     muttered
    1.01
    said
    1.01
     replied
    1.00
     reads
    0.99
     exclaimed
    0.98
     murm
    0.96
     joked
    0.94
    Act Density 0.100%

    No Known Activations