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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns and possessive adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.76
    IsContent
    -0.61
     is
    -0.56
     ,
    -0.49
    BorderFactory
    -0.49
     for
    -0.48
     up
    -0.48
     de
    -0.48
     in
    -0.47
    ↵
    -0.46
    POSITIVE LOGITS
     CreateTagHelper
    0.94
     Савезне
    0.94
    rungsseite
    0.93
    :✨
    0.93
     Paglinawan
    0.87
    EndGlobalSection
    0.86
     estimés
    0.86
     kaarangay
    0.86
    onViewCreated
    0.85
     myſelf
    0.82
    Act Density 0.518%

    No Known Activations