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

    Neuronpedia

    INDEX
    Explanations

    connections between various elements or components within a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anta
    -0.16
    ault
    -0.16
    enci
    -0.14
    lix
    -0.14
    ekli
    -0.14
    uckle
    -0.14
    oppel
    -0.14
    iners
    -0.14
    awan
    -0.14
    ding
    -0.13
    POSITIVE LOGITS
     these
    0.19
     latter
    0.19
    è¿Ļ个
    0.18
    該
    0.18
     this
    0.18
     Äijó
    0.17
     thereof
    0.17
    该
    0.17
    è¿ĻäºĽ
    0.16
     therein
    0.16
    Act Density 0.337%

    No Known Activations