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

    Neuronpedia

    INDEX
    Explanations

    items or concepts that are described as "gems" or exceptional in some way

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LayoutStyle
    -0.62
     
    -0.61
    WithFormat
    -0.59
     &___
    -0.57
     the
    -0.57
    ↵↵
    -0.56
    culosis
    -0.53
     ulang
    -0.53
    monary
    -0.52
    KHR
    -0.51
    POSITIVE LOGITS
     Efq
    1.14
     Majefty
    1.07
     pleaſure
    1.02
     Jefus
    0.99
     houſe
    0.98
     $_"
    0.97
     greateſt
    0.95
     Chriftian
    0.95
     Monfieur
    0.95
     Forumite
    0.92
    Act Density 0.483%

    No Known Activations