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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and variables related to sets and partitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    brig
    -0.20
    лаÑĪ
    -0.17
     fused
    -0.15
    izard
    -0.15
    tur
    -0.14
    kj
    -0.14
    nze
    -0.14
    ég
    -0.14
    inan
    -0.14
    боÑĢ
    -0.14
    POSITIVE LOGITS
    ERSION
    0.16
     Gun
    0.15
    ฤ
    0.14
     Sum
    0.14
    auses
    0.14
    eras
    0.14
    ENCIL
    0.14
    ause
    0.14
    Ń
    0.13
     lit
    0.13
    Act Density 0.114%

    No Known Activations