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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating acknowledgment or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ur
    -0.17
    CTYPE
    -0.16
    kl
    -0.14
    _frm
    -0.14
    vang
    -0.14
    è¾¼ãģ¿
    -0.14
    WL
    -0.14
    est
    -0.13
     diam
    -0.13
     dish
    -0.13
    POSITIVE LOGITS
    entai
    0.17
     zoekt
    0.16
     nÃły
    0.14
    Į¨
    0.14
    /rss
    0.14
    ugal
    0.14
    ombine
    0.14
    ë¶Ģ
    0.14
    omba
    0.14
     this
    0.14
    Act Density 0.124%

    No Known Activations