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

    Neuronpedia

    INDEX
    Explanations

    organizations, publications, or entities by their names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names and titles associated with people and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     subdiv
    -0.86
     specially
    -0.75
     supervised
    -0.74
     exclusion
    -0.72
     centrally
    -0.72
     stripping
    -0.70
     uphill
    -0.70
     pardon
    -0.69
     shielding
    -0.69
     settlements
    -0.69
    POSITIVE LOGITS
     Magazine
    1.50
     Blog
    1.29
    Blog
    1.26
    Magazine
    1.24
     Digest
    1.23
     Podcast
    1.23
     magazine
    1.20
     Gazette
    1.19
     Quarterly
    1.17
     Weekly
    1.16
    Act Density 0.363%

    No Known Activations