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

    Neuronpedia

    INDEX
    Explanations

    dates or time-related phrases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesday
    -0.80
    hement
    -0.78
     intending
    -0.70
     undermin
    -0.68
     estranged
    -0.68
     consecut
    -0.67
     endeav
    -0.67
     scrap
    -0.65
     imperson
    -0.65
     diving
    -0.64
    POSITIVE LOGITS
    ³³³
    1.13
    ³³³³³³³³
    1.05
    ³³³³
    1.00
    ³³³³³³³³³³³³³³³³
    0.98
    Posted
    0.90
    ³³
    0.88
    Rail
    0.87
    SCP
    0.85
    inventoryQuantity
    0.84
    Contents
    0.83
    Act Density 0.250%

    No Known Activations