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

    Neuronpedia

    INDEX
    Explanations

    phrases related to structural elements and connections in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /ag
    -0.26
    /App
    -0.25
    /Application
    -0.23
    /ad
    -0.22
    /AP
    -0.21
    /al
    -0.21
     ActionType
    -0.21
     Avery
    -0.21
     Ashton
    -0.21
    /Area
    -0.20
    POSITIVE LOGITS
    ãĤ¢
    0.38
     ãĤ¢
    0.37
    _A
    0.31
    -A
    0.29
    ãĥ»ãĤ¢
    0.29
    Äģ
    0.28
     ìķĦ
    0.28
     ÐIJ
    0.28
     á
    0.27
    াà¦
    0.27
    Act Density 1.435%

    No Known Activations