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

    Neuronpedia

    INDEX
    Explanations

    references to digitization and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itu
    -0.17
     Rae
    -0.15
    ullen
    -0.15
    erton
    -0.15
    sing
    -0.15
    arger
    -0.15
    speaker
    -0.15
    iances
    -0.14
    ей
    -0.14
    arding
    -0.14
    POSITIVE LOGITS
    ally
    0.32
    als
    0.26
    ALLY
    0.24
    álnÃŃ
    0.23
    ized
    0.20
    álnÄĽ
    0.18
    ically
    0.17
    ãĤ¿ãĥ«
    0.17
    ously
    0.17
    ürk
    0.17
    Act Density 0.005%

    No Known Activations