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

    Neuronpedia

    INDEX
    Explanations

    academic references and citations

    oai_token-act-pair · gpt-3.5-turbo

    references to academic publications and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chests
    -0.83
     torches
    -0.79
     vape
    -0.75
     stomp
    -0.73
     chops
    -0.72
     bragging
    -0.72
     props
    -0.71
     rooft
    -0.71
     freezer
    -0.69
     blaster
    -0.69
    POSITIVE LOGITS
     Retrieved
    1.22
    ournals
    1.03
    doi
    0.92
     CrossRef
    0.86
     doi
    0.82
     Proceedings
    0.80
     Springer
    0.80
     PubMed
    0.79
    Studies
    0.79
     Biol
    0.78
    Act Density 0.676%

    No Known Activations