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

    Neuronpedia

    INDEX
    Explanations

    references to places or entities with the word "Holy" in them

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    phrine
    -0.78
    ickr
    -0.77
    orph
    -0.77
    schild
    -0.76
    PsyNetMessage
    -0.76
    ĸļ
    -0.75
    earcher
    -0.74
    xual
    -0.73
    icult
    -0.73
    atown
    -0.70
    POSITIVE LOGITS
     Grail
    1.07
     Scripture
    0.90
     gra
    0.85
     Scriptures
    0.83
     Trinity
    0.82
    father
    0.81
     scripture
    0.81
     communion
    0.78
     smokes
    0.77
     Commun
    0.74
    Act Density 0.016%

    No Known Activations