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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causation or conditional relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itia
    -0.17
    bart
    -0.15
    621
    -0.14
    .gdx
    -0.14
    imb
    -0.14
     Initialized
    -0.14
    rtc
    -0.14
     -------------------------------------------------------------------------↵
    -0.14
    .KeyCode
    -0.14
    placeholders
    -0.13
    POSITIVE LOGITS
     Vice
    0.14
    æľŃ
    0.14
    oux
    0.14
    anders
    0.14
    ients
    0.14
     vice
    0.14
    oud
    0.14
    ¥IJ
    0.14
    ules
    0.13
    aza
    0.13
    Act Density 0.135%

    No Known Activations