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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "going."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MatrixMode
    -0.15
    amble
    -0.15
     Shape
    -0.14
     Grat
    -0.14
    shape
    -0.14
    orphism
    -0.14
     shape
    -0.14
     Provision
    -0.14
    еÑĢалÑĮ
    -0.14
     nextState
    -0.14
    POSITIVE LOGITS
    esta
    0.16
    esti
    0.15
    ALES
    0.15
     Dann
    0.15
    Ïģκ
    0.14
    emi
    0.14
    _union
    0.14
    AQ
    0.14
    ANNEL
    0.14
    REET
    0.14
    Act Density 0.023%

    No Known Activations