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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating that the reader is currently reading something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "this" and its context in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akable
    -0.77
    hesda
    -0.74
    chwitz
    -0.73
    asia
    -0.72
    posure
    -0.70
    htar
    -0.69
    atro
    -0.69
    aires
    -0.68
    oved
    -0.68
    Ton
    -0.67
    POSITIVE LOGITS
     aloud
    1.36
     excerpts
    0.88
     drafts
    0.84
     instructions
    0.83
     papers
    0.83
     newspapers
    0.82
     passages
    0.80
     articles
    0.79
    papers
    0.79
    é¾įå¥ij士
    0.78
    Act Density 0.134%

    No Known Activations