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

    Neuronpedia

    INDEX
    Explanations

    references to server-related terms and technologies

    oai_token-act-pair · gpt-3.5-turbo

    references to server-related concepts and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rated
    -0.84
    ofi
    -0.74
    letters
    -0.73
     Abbott
    -0.73
    ĸļ
    -0.72
    liga
    -0.71
    anguages
    -0.70
    POL
    -0.70
    ibility
    -0.69
     Miliband
    -0.68
    POSITIVE LOGITS
     server
    1.18
     servers
    0.97
     waiter
    0.88
     waitress
    0.86
     sshd
    0.84
     client
    0.83
     handler
    0.83
     planner
    0.82
     trooper
    0.80
     admins
    0.80
    Act Density 0.008%

    No Known Activations