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

    Neuronpedia

    INDEX
    Explanations

    references to skyscrapers and significant architectural landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hete
    -0.16
    .scalablytyped
    -0.16
    eral
    -0.15
    718
    -0.15
    azio
    -0.15
    zman
    -0.14
    INU
    -0.14
    _factory
    -0.14
    æ£ļ
    -0.14
    ød
    -0.14
    POSITIVE LOGITS
     tower
    0.30
     Tower
    0.25
     towers
    0.24
     tallest
    0.23
    Tower
    0.21
    tower
    0.19
     Towers
    0.17
    å±
    0.17
     Building
    0.17
     building
    0.17
    Act Density 0.061%

    No Known Activations