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

    Neuronpedia

    INDEX
    Explanations

    release details such as dates and locations

    oai_token-act-pair · gpt-3.5-turbo

    locations and specifications of various releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tre
    -0.77
    CHA
    -0.68
     theoret
    -0.68
    ité
    -0.67
    $$
    -0.65
    anon
    -0.62
    gey
    -0.62
    acter
    -0.61
     convol
    -0.61
    ibur
    -0.60
    POSITIVE LOGITS
     lieu
    1.29
     conjunction
    1.26
     accordance
    1.23
    clusively
    1.11
    clusions
    1.10
     regards
    1.06
     order
    1.02
     addition
    0.99
     hopes
    0.98
    clus
    0.97
    Act Density 0.409%

    No Known Activations