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

    Neuronpedia

    INDEX
    Explanations

    words indicating exclusivity or unique offerings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.56
    ↵↵
    -0.54
    w
    -0.52
    val
    -0.51
    ,
    -0.51
    he
    -0.51
    (
    -0.51
    lo
    -0.50
     
    -0.49
    ar
    -0.49
    POSITIVE LOGITS
     Efq
    1.18
     greateſt
    1.15
     Monfieur
    1.13
     Theſe
    1.08
     myſelf
    1.07
    exclusive
    1.05
     ſeveral
    1.04
     Majefty
    1.03
     purpoſe
    1.03
     becauſe
    1.01
    Act Density 0.091%

    No Known Activations