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

    Neuronpedia

    INDEX
    Explanations

    phrases related to transportation and travel

    oai_token-act-pair · gpt-3.5-turbo

    sentences and phrases indicating specific actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     passionately
    -0.78
     tyrann
    -0.75
     eloqu
    -0.74
     embodied
    -0.74
     imagined
    -0.72
     beautifully
    -0.72
     persu
    -0.72
     convinc
    -0.72
     murdering
    -0.71
     brilliantly
    -0.71
    POSITIVE LOGITS
     Officials
    1.26
     Previously
    1.22
    Officials
    1.17
     Those
    1.14
     However
    1.13
    Previously
    1.08
     Additionally
    1.05
     Customers
    1.05
     Earlier
    1.01
     Meanwhile
    1.00
    Act Density 0.569%

    No Known Activations