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

    Neuronpedia

    INDEX
    Explanations

    concepts related to environmental conditions and societal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wikiseite
    -0.88
     houſe
    -0.88
     greateſt
    -0.81
     pleaſure
    -0.80
     Roskov
    -0.76
    Diwedd
    -0.75
     laſt
    -0.73
     Jefus
    -0.73
     purpoſe
    -0.72
     ſhall
    -0.72
    POSITIVE LOGITS
     that
    1.09
     whose
    0.90
     where
    0.89
     who
    0.80
     which
    0.79
     of
    0.68
    ที่
    0.62
     thats
    0.60
    whose
    0.60
     with
    0.59
    Act Density 0.750%

    No Known Activations