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

    Neuronpedia

    INDEX
    Explanations

    references to innovative ideas or frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    алÑĥ
    -0.18
    ãĤ·ãĥ§
    -0.14
    iÄħ
    -0.14
     meal
    -0.14
    êu
    -0.14
     Meal
    -0.13
    aug
    -0.13
    -await
    -0.13
    ÄĻż
    -0.13
    amm
    -0.13
    POSITIVE LOGITS
    \TestCase
    0.17
    abis
    0.16
    ively
    0.15
    kov
    0.15
    zzo
    0.15
    ertino
    0.14
    avers
    0.14
     Colbert
    0.14
     eins
    0.14
    stasy
    0.14
    Act Density 0.016%

    No Known Activations