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

    Neuronpedia

    INDEX
    Explanations

    religious figures or references

    oai_token-act-pair · gpt-3.5-turbo

    references to Jesus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    circ
    -0.71
     Volks
    -0.64
    asio
    -0.64
    ulates
    -0.63
    £ı
    -0.62
    à¨
    -0.60
     inference
    -0.60
    nai
    -0.59
     pointer
    -0.59
    orescent
    -0.59
    POSITIVE LOGITS
    itably
    0.78
     admitting
    0.70
    ideos
    0.64
    ouston
    0.64
    CG
    0.63
    HER
    0.62
    hips
    0.62
     Bots
    0.60
     Clara
    0.60
     Osw
    0.60
    Act Density 0.000%

    No Known Activations