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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing distinctive approaches and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uhn
    -0.15
    acos
    -0.14
    Ÿ
    -0.14
    KERNEL
    -0.14
    оиÑĤ
    -0.14
    оÑĤÑĭ
    -0.13
    navigate
    -0.13
    misc
    -0.13
     CHARSET
    -0.13
    alama
    -0.13
    POSITIVE LOGITS
     ways
    0.47
     way
    0.47
     manner
    0.42
     Ways
    0.33
    æĸ¹å¼ı
    0.32
     fashion
    0.32
     sposób
    0.30
    way
    0.29
    ways
    0.29
     Way
    0.28
    Act Density 0.154%

    No Known Activations