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

    Neuronpedia

    INDEX
    Explanations

    elements related to transitions or changes in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.55
    FetchType
    -0.46
     answers
    -0.46
     poucos
    -0.43
     الرياضيه
    -0.43
     answer
    -0.42
     dem
    -0.42
     “…
    -0.41
    　　“
    -0.40
    なりに
    -0.40
    POSITIVE LOGITS
    ########.
    0.68
    BeginContext
    0.67
     milliers
    0.65
    nador
    0.63
     THOUS
    0.63
    RenderAtEndOf
    0.63
    قایناقلار
    0.62
    findpost
    0.62
    GEBURTSDATUM
    0.62
     Мексичка
    0.60
    Act Density 0.764%

    No Known Activations