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

    Neuronpedia

    INDEX
    Explanations

    phrases related to wisdom

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of wisdom

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ches
    -0.76
    ching
    -0.76
    alien
    -0.74
    ched
    -0.72
    heter
    -0.70
    iger
    -0.68
    Monitor
    -0.67
    por
    -0.67
    chy
    -0.67
    Interstitial
    -0.67
    POSITIVE LOGITS
     wisdom
    1.41
    smanship
    0.95
     Wisdom
    0.90
    avascript
    0.86
     princ
    0.80
     tremend
    0.78
     Advice
    0.78
    fulness
    0.77
     arrogance
    0.76
     destro
    0.73
    Act Density 0.008%

    No Known Activations