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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate core concepts and logical connections within discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    екаÑĢ
    -0.15
     mart
    -0.14
    alarından
    -0.14
     circum
    -0.14
    ĥn
    -0.13
    à¥ģà¤ľ
    -0.13
    throp
    -0.13
    سÙĨÚ¯
    -0.13
    zk
    -0.13
    zz
    -0.13
    POSITIVE LOGITS
     Gron
    0.15
    antee
    0.15
    à¸Ĺย
    0.13
    سط
    0.13
    /color
    0.13
     centr
    0.13
    nice
    0.13
    noc
    0.13
    دÙĩ
    0.13
     Maur
    0.13
    Act Density 0.120%

    No Known Activations