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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and verbs related to emotional intensity and relationships

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.72
    ELD
    -0.72
    onday
    -0.72
    liest
    -0.71
    ipping
    -0.69
     Increasing
    -0.68
    ECTION
    -0.68
    ca
    -0.67
    ¯
    -0.66
    quickShipAvailable
    -0.65
    POSITIVE LOGITS
     shine
    1.12
     breathe
    1.00
     dictate
    0.92
     expire
    0.90
     handle
    0.86
     grow
    0.86
     flourish
    0.86
     slide
    0.86
     slip
    0.85
     soak
    0.85
    Act Density 0.066%

    No Known Activations