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

    Neuronpedia

    INDEX
    Explanations

    specific names or terms related to scientific studies and research, particularly in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ?,↵
    -0.17
    _,↵
    -0.17
    ï¼Į↵
    -0.16
    ãĢĭ↵
    -0.16
    8
    -0.15
    enties
    -0.14
    ,↵
    -0.14
    (),↵
    -0.14
    6
    -0.14
    /,↵
    -0.14
    POSITIVE LOGITS
     et
    0.24
     ãģĿãģ®ä»ĸ
    0.21
    oucher
    0.20
    _et
    0.19
    @mail
    0.17
     Orc
    0.16
     ìĻ¸
    0.16
    lee
    0.15
    ohan
    0.15
    alli
    0.15
    Act Density 0.005%

    No Known Activations