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

    Neuronpedia

    INDEX
    Explanations

    references to saints and expressions of gratitude or requests for intercession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istik
    -0.14
    /uploads
    -0.14
    ÏħÏĥ
    -0.14
     Secrets
    -0.14
    ecret
    -0.13
    arez
    -0.13
    unei
    -0.13
    ongan
    -0.13
     Turnbull
    -0.13
     ÑģвÑıÑī
    -0.13
    POSITIVE LOGITS
     patron
    0.56
     Patron
    0.48
     patrons
    0.40
     saint
    0.33
     Saint
    0.33
     Saints
    0.32
     saints
    0.31
    atron
    0.30
    Saint
    0.29
    pat
    0.27
    Act Density 0.120%

    No Known Activations