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

    Neuronpedia

    INDEX
    Explanations

    references to religious or spiritual figures, specifically related to exorcisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģŁãģĹ
    -0.16
    __/
    -0.15
    ighton
    -0.15
    дов
    -0.15
     Muss
    -0.15
    upert
    -0.14
    izza
    -0.14
    illon
    -0.14
    ùa
    -0.14
    istrovstvÃŃ
    -0.14
    POSITIVE LOGITS
    hiro
    0.18
    indi
    0.17
    ropdown
    0.15
    perm
    0.15
     Pir
    0.14
     ur
    0.14
    ATOR
    0.14
    Lane
    0.14
    inspace
    0.14
    #index
    0.13
    Act Density 0.030%

    No Known Activations