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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating good or bad news about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opensource
    -0.17
    ootball
    -0.16
    ETCH
    -0.14
    ingerprint
    -0.14
    odable
    -0.13
    å½¹
    -0.13
    ΩΣ
    -0.13
     privilege
    -0.13
    FirstChild
    -0.13
    ritable
    -0.13
    POSITIVE LOGITS
     news
    0.38
    -news
    0.31
    news
    0.29
     News
    0.27
     NEWS
    0.25
     overall
    0.24
    News
    0.23
     signs
    0.23
    (news
    0.21
    NEWS
    0.21
    Act Density 0.050%

    No Known Activations