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

    Neuronpedia

    INDEX
    Explanations

    scientific research publications

    oai_token-act-pair · gpt-3.5-turbo

    mention of scientific studies and publications in journals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     broom
    -0.74
    crew
    -0.72
     Sorce
    -0.69
     caster
    -0.68
     imperson
    -0.68
    addon
    -0.67
     idol
    -0.66
     accustomed
    -0.66
     wrongly
    -0.65
     crou
    -0.65
    POSITIVE LOGITS
     Proceedings
    1.28
    pdf
    0.92
     PLoS
    0.91
    doi
    0.91
     journal
    0.90
     Nature
    0.90
    PDF
    0.90
    Else
    0.85
     Scientific
    0.85
    ournals
    0.85
    Act Density 0.164%

    No Known Activations