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

    Neuronpedia

    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turbo

    specific years or dates mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stead
    -0.64
    malink
    -0.62
     monop
    -0.61
    ACTION
    -0.60
     amb
    -0.59
     Strongh
    -0.59
     hypocr
    -0.58
     metaph
    -0.58
    pressed
    -0.56
     plural
    -0.56
    POSITIVE LOGITS
     onwards
    1.08
     onward
    0.87
    å¹
    0.85
    -'
    0.81
    iversary
    0.79
    20439
    0.72
    âĢ²
    0.72
    ãģ®éŃĶ
    0.67
    berries
    0.66
    urst
    0.65
    Act Density 0.101%

    No Known Activations