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

    Neuronpedia

    INDEX
    Explanations

    references to supernatural beings like angels

    oai_token-act-pair · gpt-3.5-turbo

    references to "angels" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -1.13
    anyahu
    -0.79
    llah
    -0.72
    lé
    -0.70
    nr
    -0.70
    iddled
    -0.70
    vous
    -0.68
    guyen
    -0.68
    ilde
    -0.68
    alf
    -0.67
    POSITIVE LOGITS
     Angels
    1.34
     Templ
    0.89
    enos
    0.86
     Raiders
    0.84
     Rays
    0.82
    wings
    0.80
     Devils
    0.80
     Wings
    0.78
     Angel
    0.74
    adelphia
    0.73
    Act Density 0.005%

    No Known Activations