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

    Neuronpedia

    INDEX
    Explanations

    references to religious figures and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aje
    -0.16
    ajes
    -0.15
     Frost
    -0.14
    æı®
    -0.14
    antu
    -0.14
    ATCH
    -0.14
     destabil
    -0.14
    lag
    -0.14
    atch
    -0.13
     hypothetical
    -0.13
    POSITIVE LOGITS
    hani
    0.14
    imeline
    0.14
    aÄįnÃŃ
    0.14
    onya
    0.14
    .timeScale
    0.14
    loyd
    0.14
     radiant
    0.13
    ãĥ¼ãĤ¹ãĥĪ
    0.13
    ниÑĨÑı
    0.13
    alion
    0.13
    Act Density 0.087%

    No Known Activations