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

    Neuronpedia

    INDEX
    Explanations

    expressions of satisfaction or approval

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    umes
    -0.81
    ogens
    -0.79
    UME
    -0.74
    soDeliveryDate
    -0.73
     contradicts
    -0.72
     haunt
    -0.70
     alters
    -0.69
    cum
    -0.69
     incompatible
    -0.68
    udder
    -0.67
    POSITIVE LOGITS
     accomplishments
    1.21
     accomplishment
    1.20
     successes
    1.07
     achievements
    1.06
     strides
    1.05
     progress
    1.01
     success
    1.00
     achievement
    0.98
    Congratulations
    0.97
     congr
    0.96
    Act Density 0.516%

    No Known Activations