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

    Neuronpedia

    INDEX
    Explanations

    terms related to advanced mathematical concepts and frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .digest
    -0.15
    bul
    -0.14
     sing
    -0.14
    rias
    -0.13
    iste
    -0.13
     Sokol
    -0.13
     dah
    -0.13
    nat
    -0.13
     Flush
    -0.13
    تÙĪاÙĨ
    -0.13
    POSITIVE LOGITS
     proport
    0.17
    imary
    0.16
    otten
    0.16
    urer
    0.16
    elu
    0.15
    vals
    0.15
    agus
    0.15
     ê²
    0.14
    eprom
    0.14
     ãģı
    0.14
    Act Density 0.005%

    No Known Activations