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

    Neuronpedia

    INDEX
    Explanations

    references to sports plays and statistics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" or "an" before nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SOURCE
    -0.84
     Ideas
    -0.80
    Shape
    -0.79
    âĹ¼
    -0.78
     ®
    -0.76
    cair
    -0.75
    ATURES
    -0.75
    Shares
    -0.71
     Features
    -0.71
     Investigator
    -0.70
    POSITIVE LOGITS
    venge
    1.15
     whopping
    1.04
     terrific
    1.02
     plethora
    0.99
     postseason
    0.98
     rookie
    0.98
     pivotal
    0.96
     timely
    0.96
     depleted
    0.96
     playoff
    0.95
    Act Density 0.433%

    No Known Activations