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

    Neuronpedia

    INDEX
    Explanations

    words or phrases that introduce contrast or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cæsar
    -1.11
     Majefty
    -1.08
     purpoſe
    -1.06
     Efq
    -1.05
     houſe
    -1.03
     pleaſure
    -1.02
     Theſe
    -1.01
     ſtate
    -1.00
     Monfieur
    -0.99
     quæ
    -0.99
    POSITIVE LOGITS
     but
    1.03
     due
    0.78
     Due
    0.62
     and
    0.61
     or
    0.60
     more
    0.58
    ]),
    0.57
     More
    0.56
     to
    0.55
     as
    0.55
    Act Density 0.286%

    No Known Activations