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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing admiration, tribute, or remembrance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stras
    -0.72
    furt
    -0.70
    handle
    -0.66
    confidence
    -0.65
    thing
    -0.64
    change
    -0.63
    zee
    -0.62
    ī
    -0.62
    rooms
    -0.61
    ECK
    -0.60
    POSITIVE LOGITS
    giving
    1.02
     honoring
    0.88
     tribute
    0.79
     bestowed
    0.79
     thanking
    0.78
     plaque
    0.77
     commemor
    0.75
     thereto
    0.75
     emoji
    0.71
    cellence
    0.69
    Act Density 0.042%

    No Known Activations