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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating professional accomplishments and collaborations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     greateſt
    -0.74
     Cæsar
    -0.73
    PreferredItem
    -0.72
    存于互联网档案馆
    -0.71
    Portale
    -0.71
    ImageContext
    -0.70
     itſelf
    -0.70
    TacToe
    -0.69
    Personensuche
    -0.67
     pleaſure
    -0.67
    POSITIVE LOGITS
     pre
    0.63
     for
    0.63
     last
    0.58
     «
    0.57
     several
    0.57
     co
    0.56
     por
    0.54
     numerous
    0.53
     three
    0.51
    WriteTo
    0.51
    Act Density 0.277%

    No Known Activations