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

    Neuronpedia

    INDEX
    Explanations

    descriptions or details mentioned in various documents

    oai_token-act-pair · gpt-3.5-turbo

    references to documents or reports that contain detailed descriptions or outlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lasted
    -0.88
    hesda
    -0.70
    0000000000000000
    -0.69
     succeeded
    -0.68
     waited
    -0.67
    rio
    -0.66
     luckily
    -0.65
     fought
    -0.64
     obliged
    -0.63
     assured
    -0.63
    POSITIVE LOGITS
     accordance
    0.95
    humane
    0.92
     advance
    0.89
     conjunction
    0.87
     Figures
    0.82
     Scripture
    0.82
     detail
    0.81
    effic
    0.80
    efficiency
    0.80
     Figure
    0.79
    Act Density 0.179%

    No Known Activations