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

    Neuronpedia

    INDEX
    Explanations

    phrases containing quotations

    oai_token-act-pair · gpt-3.5-turbo

    punctuation that indicates quoted speech or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chnology
    -0.69
    ingu
    -0.66
    etheless
    -0.64
    eday
    -0.63
    omach
    -0.63
     contrace
    -0.61
    ģ«
    -0.61
    ablish
    -0.61
     uncond
    -0.60
    egu
    -0.58
    POSITIVE LOGITS
    said
    1.11
     said
    1.09
     says
    1.08
     tweeted
    1.08
     wrote
    1.06
     exclaimed
    1.05
     replied
    1.03
     remarked
    1.03
     commented
    0.99
     reads
    0.99
    Act Density 0.068%

    No Known Activations