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

    Neuronpedia

    INDEX
    Explanations

    phrases related to communication and community involvement

    oai_token-act-pair · gpt-3.5-turbo

    references to community-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olkien
    -0.75
    OPLE
    -0.73
    BALL
    -0.72
    AGES
    -0.70
    inning
    -0.69
    require
    -0.67
     Lank
    -0.65
     pity
    -0.65
    avorite
    -0.63
     Slayer
    -0.62
    POSITIVE LOGITS
    icator
    1.31
     commun
    1.30
    icators
    1.25
    icol
    1.04
    ique
    1.04
    icative
    1.02
    icable
    1.01
    namese
    1.00
    icip
    0.99
     Commun
    0.94
    Act Density 0.006%

    No Known Activations