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

    Neuronpedia

    INDEX
    Explanations

    phrases related to performance metrics and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    za
    -0.21
    ZA
    -0.19
    ekli
    -0.16
    ULO
    -0.15
    زا
    -0.15
    Pear
    -0.15
    æĵ
    -0.15
     Britann
    -0.14
    steder
    -0.14
    it
    -0.14
    POSITIVE LOGITS
     Nut
    0.16
     nut
    0.16
    LAY
    0.15
    serter
    0.15
    /INFO
    0.15
    ivia
    0.15
    Nut
    0.14
    UM
    0.14
    setLayout
    0.14
    AMY
    0.14
    Act Density 0.028%

    No Known Activations