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

    Neuronpedia

    INDEX
    Explanations

    discussions related to belief systems and the distortion of truths in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -0.87
     Efq
    -0.84
     myſelf
    -0.81
     itſelf
    -0.77
     houſe
    -0.73
     preſent
    -0.68
     pleaſure
    -0.68
    ſelf
    -0.67
    neſs
    -0.67
     Chrift
    -0.67
    POSITIVE LOGITS
     croire
    0.90
     claims
    0.78
     claim
    0.77
     belief
    0.75
     believe
    0.69
     rằng
    0.69
    RegressionTest
    0.67
     Belief
    0.67
     believes
    0.66
     Claims
    0.65
    Act Density 0.677%

    No Known Activations