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

    Neuronpedia

    INDEX
    Explanations

    references to sins or sinful behavior

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Explorer
    -0.68
     Mechanical
    -0.66
    upp
    -0.64
     Booster
    -0.64
     Train
    -0.64
    rew
    -0.63
    ETF
    -0.63
     Uzbek
    -0.62
    unda
    -0.62
    usters
    -0.61
    POSITIVE LOGITS
     sin
    3.94
     sins
    2.39
    sin
    2.29
     Sin
    2.02
     Sins
    2.00
     sinful
    1.95
    Sin
    1.83
     sinners
    1.83
     transgress
    1.16
     righteousness
    1.15
    Act Density 0.028%

    No Known Activations