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

    Neuronpedia

    INDEX
    Explanations

    expressions related to achievement or recognition for effort or skill

    oai_token-act-pair · gpt-3.5-turbo

    achievement-related terms and accolades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     processes
    -0.70
    omo
    -0.64
    gae
    -0.64
    uploads
    -0.63
    rules
    -0.63
    opus
    -0.62
    agate
    -0.60
     Boards
    -0.60
    anwhile
    -0.58
    hari
    -0.58
    POSITIVE LOGITS
     notoriety
    1.12
     ire
    1.04
     foothold
    0.99
     coveted
    0.95
     accol
    0.88
     nickname
    0.86
     berth
    0.85
     fame
    0.84
     traction
    0.80
     renown
    0.80
    Act Density 0.216%

    No Known Activations