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

    Neuronpedia

    INDEX
    Explanations

    phrases linked to repercussions or legal consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    енÑĮ
    -0.17
    emente
    -0.15
    works
    -0.15
    à¹Ģà¸Ī
    -0.15
    αι
    -0.14
    ören
    -0.14
    Stamp
    -0.13
    imiz
    -0.13
    ůj
    -0.13
    å¢Ĺ
    -0.13
    POSITIVE LOGITS
    agers
    0.19
    ToLocal
    0.17
    Æł
    0.15
    iba
    0.15
    km
    0.14
     Banc
    0.14
     raised
    0.14
    eder
    0.13
    lights
    0.13
     secre
    0.13
    Act Density 0.246%

    No Known Activations