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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Published"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igli
    -0.16
    adro
    -0.16
    dio
    -0.15
    ourke
    -0.15
    -sdk
    -0.15
     AT
    -0.14
    coli
    -0.14
    enge
    -0.14
    tom
    -0.14
    lain
    -0.14
    POSITIVE LOGITS
    اÙĨس
    0.15
    askell
    0.15
    anch
    0.14
    ancode
    0.14
    rie
    0.14
    ÑĢовиÑĩ
    0.14
    ITTLE
    0.14
    neh
    0.14
    onces
    0.13
    pha
    0.13
    Act Density 0.002%

    No Known Activations