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

    Neuronpedia

    INDEX
    Explanations

    keywords related to exceptional performance or quality

    oai_token-act-pair · gpt-3.5-turbo

    terms that indicate excellence or dominance in a field

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uggage
    -0.82
    giene
    -0.82
    bis
    -0.81
    oshenko
    -0.78
    agan
    -0.78
    bris
    -0.78
    monary
    -0.76
     resil
    -0.75
    ullah
    -0.75
    erity
    -0.75
    POSITIVE LOGITS
     standout
    0.83
    ONSORED
    0.83
     darling
    0.75
     Flavoring
    0.72
     powerhouse
    0.70
     contender
    0.69
     GOODMAN
    0.68
     IF
    0.68
     Kore
    0.68
     Sek
    0.67
    Act Density 0.020%

    No Known Activations