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

    Neuronpedia

    INDEX
    Explanations

    references to religion

    oai_token-act-pair · gpt-3.5-turbo

    references to religion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kus
    -0.83
     Lans
    -0.70
    berries
    -0.66
    ptives
    -0.66
    ription
    -0.66
    hyde
    -0.66
    berry
    -0.66
    apple
    -0.65
     Rober
    -0.63
     Lag
    -0.62
    POSITIVE LOGITS
    ophobia
    1.02
    ophobic
    0.95
    ophob
    0.88
    istical
    0.88
    fulness
    0.85
    hood
    0.84
     affiliation
    0.82
    ically
    0.81
    ists
    0.80
     tenets
    0.79
    Act Density 0.039%

    No Known Activations