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

    Neuronpedia

    INDEX
    Explanations

    expressions or mentions related to desires or requests

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to personal desires and intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adj
    -0.70
    ADVERTISEMENT
    -0.66
    ergy
    -0.65
    ulative
    -0.64
     Clim
    -0.63
     Carb
    -0.61
    hill
    -0.60
    down
    -0.59
    gly
    -0.57
    evidence
    -0.57
    POSITIVE LOGITS
     wishes
    1.27
    mares
    1.03
     wished
    0.97
     Lumpur
    0.91
     wishing
    0.89
     wish
    0.88
    reprene
    0.87
    terday
    0.86
     Pwr
    0.80
    """
    0.77
    Act Density 0.005%

    No Known Activations