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

    Neuronpedia

    INDEX
    Explanations

    references to spiritual or religious themes and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    881
    -0.15
    afen
    -0.14
    Monster
    -0.14
    alien
    -0.14
    EMPL
    -0.14
    aca
    -0.14
    ÑĤим
    -0.13
    quez
    -0.13
     Monsters
    -0.13
    ÏĦοÏį
    -0.13
    POSITIVE LOGITS
     Sah
    0.25
     sah
    0.21
    -Sah
    0.20
     vibrations
    0.17
     guru
    0.16
     Guru
    0.16
     seekers
    0.16
    夫
    0.16
     Pu
    0.16
    ogan
    0.16
    Act Density 0.001%

    No Known Activations