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

    Neuronpedia

    INDEX
    Explanations

    references to academic or literary resources and their content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Shapes
    -0.16
    è¨Ī
    -0.15
    rud
    -0.14
     wink
    -0.14
     Kinh
    -0.14
    еннÑĸ
    -0.14
    adic
    -0.14
    æ¢
    -0.13
    计
    -0.13
    redit
    -0.13
    POSITIVE LOGITS
    ken
    0.16
    stab
    0.15
    pend
    0.14
     swallow
    0.14
    ãĥ¶
    0.14
    ượng
    0.14
    pending
    0.14
    ÑĸллÑı
    0.14
    endas
    0.14
    _THROW
    0.14
    Act Density 0.005%

    No Known Activations