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

    Neuronpedia

    INDEX
    Explanations

    references to the Hindu religion

    oai_token-act-pair · gpt-3.5-turbo

    references to Hinduism and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iasco
    -0.66
    CAP
    -0.64
    argo
    -0.64
    ellen
    -0.64
     (#
    -0.63
    odes
    -0.62
    cker
    -0.62
    oppers
    -0.61
     Strike
    -0.61
     Weiss
    -0.60
    POSITIVE LOGITS
     Hindu
    3.82
     Hindus
    3.11
     Sikh
    2.23
     Sanskrit
    2.12
     Hindi
    2.00
     Buddhist
    1.96
     Gujar
    1.90
     Shiva
    1.82
     Indian
    1.82
    indu
    1.81
    Act Density 0.014%

    No Known Activations