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

    Neuronpedia

    INDEX
    Explanations

    direct address to the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ut
    -0.15
    nob
    -0.15
    avel
    -0.15
    jah
    -0.14
    might
    -0.14
     Might
    -0.14
    jist
    -0.14
    utron
    -0.14
     wid
    -0.14
     رب
    -0.13
    POSITIVE LOGITS
     ever
    0.22
     haven
    0.21
     hasn
    0.17
     Haven
    0.17
     hadn
    0.17
    à¹ĥà¸Ķ
    0.16
    652
    0.16
     EVER
    0.15
    534
    0.15
    squ
    0.15
    Act Density 0.057%

    No Known Activations