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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to the reader or audience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ả
    -0.17
     aren
    -0.16
     weren
    -0.16
    roupon
    -0.15
    ewis
    -0.15
    atern
    -0.15
    435
    -0.14
    idge
    -0.14
    /posts
    -0.14
    weet
    -0.14
    POSITIVE LOGITS
    ãĥ«ãĥĪ
    0.18
    uxe
    0.17
    ĶåĽŀ
    0.15
     vic
    0.15
    orsk
    0.15
    HX
    0.14
    FOUNDATION
    0.14
    ÙĩÙĦ
    0.14
    steller
    0.13
    SEG
    0.13
    Act Density 0.114%

    No Known Activations