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

    Neuronpedia

    INDEX
    Explanations

    references to religious beliefs and themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    359
    -0.16
    lesia
    -0.15
    ileo
    -0.15
    652
    -0.15
    355
    -0.14
     ceremonial
    -0.14
    Looper
    -0.14
    deen
    -0.14
     bachelor
    -0.14
    845
    -0.14
    POSITIVE LOGITS
     appar
    0.34
     Fat
    0.30
    Fat
    0.26
     FAT
    0.24
    .Fat
    0.23
     fat
    0.22
    fat
    0.22
    -fat
    0.22
     Our
    0.19
     devotion
    0.19
    Act Density 0.062%

    No Known Activations