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

    Neuronpedia

    INDEX
    Explanations

    phrases related to non-belief or skepticism

    oai_token-act-pair · gpt-3.5-turbo

    references to belief systems, particularly in relation to non-believers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Noon
    -0.73
    hire
    -0.70
     eclipse
    -0.66
    isition
    -0.63
    ONS
    -0.62
    lease
    -0.61
     Regulation
    -0.60
    ograp
    -0.59
     phased
    -0.58
    assetsadobe
    -0.58
    POSITIVE LOGITS
    ievers
    1.17
    iever
    1.12
    ieve
    1.10
    ieving
    1.10
    iev
    1.00
    ief
    0.96
    bel
    0.94
    ichick
    0.94
    ieved
    0.89
    ieves
    0.89
    Act Density 0.006%

    No Known Activations