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

    Neuronpedia

    INDEX
    Explanations

    phrases related to religious beliefs and moral concepts

    oai_token-act-pair · gpt-3.5-turbo

    expressions of moral judgment and concepts related to justice and suffering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.95
     GOODMAN
    -0.94
     Timeline
    -0.86
    updated
    -0.79
    Ready
    -0.78
    Baby
    -0.76
     helicop
    -0.76
    uably
    -0.75
    wow
    -0.75
     Aerospace
    -0.74
    POSITIVE LOGITS
     sinful
    1.62
     sins
    1.58
     sinners
    1.48
     wicked
    1.46
     sin
    1.43
     evils
    1.43
     unbel
    1.42
     folly
    1.41
     malice
    1.36
     blasp
    1.36
    Act Density 0.234%

    No Known Activations