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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology updates and product releases

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     allowance
    -0.78
     enrol
    -0.77
     undet
    -0.77
     sob
    -0.77
     cellar
    -0.76
    ling
    -0.73
     occupational
    -0.73
     intervene
    -0.73
     occupation
    -0.72
    untarily
    -0.72
    POSITIVE LOGITS
     Thankfully
    1.17
     Unfortunately
    1.17
     However
    1.12
     Granted
    1.11
     Whereas
    1.10
     Sadly
    1.09
     Notably
    1.09
     Considering
    1.09
     Additionally
    1.08
     Hopefully
    1.08
    Act Density 0.750%

    No Known Activations