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

    Neuronpedia

    INDEX
    Explanations

    information about upcoming events or announcements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciating
    -0.74
     Bars
    -0.71
    rones
    -0.65
     dare
    -0.60
    osa
    -0.59
    rawdownloadcloneembedreportprint
    -0.58
     Grape
    -0.57
    odder
    -0.57
     Doesn
    -0.56
     Mund
    -0.56
    POSITIVE LOGITS
     able
    0.97
     seen
    0.95
     replaced
    0.91
     considered
    0.88
     forgiven
    0.85
     deemed
    0.85
     taken
    0.84
     judged
    0.84
    heading
    0.83
     subjected
    0.83
    Act Density 0.304%

    No Known Activations