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

    Neuronpedia

    INDEX
    Explanations

    references to human behaviors and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸ı
    -0.16
    tsy
    -0.15
    ắng
    -0.15
    rame
    -0.14
    ziej
    -0.14
    asu
    -0.14
    é³´
    -0.14
    wner
    -0.14
    ileo
    -0.14
    imet
    -0.13
    POSITIVE LOGITS
     who
    0.16
    /com
    0.14
     widely
    0.14
    Ĺi
    0.14
    OfSize
    0.14
     Weld
    0.14
     Shields
    0.14
     flock
    0.14
    ainless
    0.14
    ãĥ³ãĥIJ
    0.14
    Act Density 0.362%

    No Known Activations