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

    Neuronpedia

    INDEX
    Explanations

    keywords and character names from titles and entertainment-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trap
    -0.17
    Trap
    -0.15
    otope
    -0.14
    ı
    -0.14
     traps
    -0.14
    asc
    -0.13
    ãģĦãĤĭ
    -0.13
    ibel
    -0.13
    ="__
    -0.13
    paragus
    -0.13
    POSITIVE LOGITS
    ober
    0.16
    eyh
    0.16
    eview
    0.15
    etest
    0.14
    etheless
    0.14
    ome
    0.14
    лÑıн
    0.14
    ÑŁ
    0.13
    ynos
    0.13
    etros
    0.13
    Act Density 0.437%

    No Known Activations