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

    Neuronpedia

    INDEX
    Explanations

    quotations within sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include direct quotations or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.73
    ļéĨĴ
    -0.67
    OTHER
    -0.63
    Widget
    -0.63
    ĻĤ
    -0.62
    lp
    -0.61
    onet
    -0.61
    ~~~~
    -0.61
    ãĥĻ
    -0.59
    Enlarge
    -0.57
    POSITIVE LOGITS
     he
    1.46
     said
    1.36
     she
    1.24
     joked
    1.13
    said
    1.12
     replied
    1.11
     wrote
    1.09
     explained
    1.05
     says
    1.03
     exclaimed
    1.01
    Act Density 0.103%

    No Known Activations