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

    Neuronpedia

    INDEX
    Explanations

    words related to strong emotional reactions or calls to action

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to media or entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actionDate
    -0.71
    ©¶æ
    -0.68
    hibit
    -0.64
     largeDownload
    -0.63
    obook
    -0.63
    onduct
    -0.62
     paraph
    -0.60
    weeney
    -0.60
    nec
    -0.59
    anut
    -0.59
    POSITIVE LOGITS
    !
    2.11
    !.
    1.87
    !'
    1.86
    !"
    1.76
    !,
    1.76
    !:
    1.76
    !".
    1.68
    !",
    1.61
    !)
    1.60
    !!
    1.59
    Act Density 0.186%

    No Known Activations