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

    Neuronpedia

    INDEX
    Explanations

    references to religious concepts and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jehovah
    -0.15
    apo
    -0.15
     Claus
    -0.14
    ÙĬØ´
    -0.14
    aleb
    -0.14
     заÑģÑĤав
    -0.14
    سÙĥ
    -0.14
     Reactive
    -0.13
     worsh
    -0.13
     DISCLAIM
    -0.13
    POSITIVE LOGITS
     Catholic
    0.31
     catholic
    0.24
     Catholics
    0.23
     Vatican
    0.22
     Ign
    0.22
    atholic
    0.22
     St
    0.22
     Mary
    0.21
     Dominican
    0.20
    cate
    0.20
    Act Density 0.527%

    No Known Activations