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

    Neuronpedia

    INDEX
    Explanations

    references to specific objects or concepts being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.90
     تضيفلها
    -0.79
    fficients
    -0.74
     decon
    -0.72
     deſt
    -0.71
     cauſe
    -0.71
    StoryboardSegue
    -0.69
     Anſ
    -0.68
     Conſ
    -0.68
     greateſt
    -0.68
    POSITIVE LOGITS
     him
    0.68
     them
    0.66
     StatefulWidget
    0.62
     sendiri
    0.61
     himself
    0.57
     THEM
    0.55
     herself
    0.55
     másik
    0.52
    Them
    0.51
    Джерела
    0.51
    Act Density 0.277%

    No Known Activations