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

    Neuronpedia

    INDEX
    Explanations

    reports and studies published in scientific journals

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific studies and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Franch
    -0.67
    ostic
    -0.66
     Relief
    -0.65
    never
    -0.64
     hating
    -0.61
     decency
    -0.61
     sheltered
    -0.61
     lockout
    -0.60
     quotas
    -0.58
     Calais
    -0.58
    POSITIVE LOGITS
     published
    1.16
     Proceedings
    1.09
     PLoS
    1.08
    doi
    1.07
    Paper
    1.06
    Abstract
    1.04
     authors
    1.04
    Explore
    1.02
     Published
    1.01
     paper
    1.00
    Act Density 0.212%

    No Known Activations