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

    Neuronpedia

    INDEX
    Explanations

    spoken dialogue with punctuation

    oai_token-act-pair · gpt-3.5-turbo

    references to communication or dialogues in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     adop
    -0.69
     dared
    -0.68
     bidder
    -0.67
     accuses
    -0.67
     awaits
    -0.65
     delet
    -0.64
    endif
    -0.63
    "/>
    -0.63
     deems
    -0.63
     whence
    -0.62
    POSITIVE LOGITS
    Absolutely
    1.29
    Well
    1.23
     Honestly
    1.19
    Yeah
    1.17
    Honestly
    1.14
     Absolutely
    1.14
     Well
    1.13
     Firstly
    1.10
     Yeah
    1.10
     Definitely
    1.08
    Act Density 0.168%

    No Known Activations