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

    Neuronpedia

    INDEX
    Explanations

    phrases related to privacy policies and data collection practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .wordpress
    -0.15
     pohod
    -0.14
    ÅĻes
    -0.14
    ÃŃž
    -0.14
     vá»ijn
    -0.14
     CÆ¡
    -0.14
    kili
    -0.14
     tức
    -0.14
    wnd
    -0.14
    coverage
    -0.14
    POSITIVE LOGITS
     their
    0.25
     our
    0.23
     any
    0.23
     its
    0.22
     the
    0.21
     some
    0.21
     these
    0.21
     your
    0.21
     an
    0.21
     it
    0.20
    Act Density 0.481%

    No Known Activations