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

    Neuronpedia

    INDEX
    Explanations

    references to religious texts and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Italijanski
    -0.50
    сылкі
    -0.49
    ніципалі
    -0.44
    attro
    -0.43
     competitive
    -0.43
    您
    -0.42
     upsetting
    -0.42
     Helf
    -0.41
     Keine
    -0.41
     Ehren
    -0.41
    POSITIVE LOGITS
     figliu
    0.53
     unto
    0.52
     avoient
    0.50
     enfans
    0.48
     quæ
    0.48
     saith
    0.47
     Grecs
    0.47
    KJV
    0.47
     hath
    0.45
     églises
    0.45
    Act Density 0.140%

    No Known Activations