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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating superiority or uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NU
    -0.15
     buck
    -0.14
    onda
    -0.14
    #Region
    -0.14
     Brake
    -0.14
    utow
    -0.14
    ABCDEFG
    -0.14
    kre
    -0.14
    bons
    -0.13
    ská
    -0.13
    POSITIVE LOGITS
     treff
    0.17
    defgroup
    0.15
    uja
    0.15
    Ïģοι
    0.15
    agas
    0.15
    ãĤ·ãĥ¼
    0.14
    lessly
    0.14
    éĢ¸
    0.14
     quality
    0.14
    -quality
    0.14
    Act Density 0.139%

    No Known Activations