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

    Neuronpedia

    INDEX
    Explanations

    references to methods or approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.10
     Majefty
    -1.06
     ―――――
    -1.04
     Mahmud
    -1.03
    ultuous
    -1.02
     насељу
    -1.00
     McNeil
    -0.99
     preſent
    -0.98
    Datuak
    -0.97
     Reſ
    -0.97
    POSITIVE LOGITS
     Way
    1.93
     way
    1.92
     WAY
    1.86
    Way
    1.73
     ways
    1.69
    way
    1.67
     Ways
    1.57
    WAY
    1.53
     WAYS
    1.48
    Ways
    1.42
    Act Density 0.072%

    No Known Activations