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

    Neuronpedia

    INDEX
    Explanations

    scientific terminology and notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.63
    HasForeignKey
    -0.61
    帖最后由
    -0.59
     ویکی‌پدیای
    -0.56
    таратура
    -0.56
    cèse
    -0.54
    Extinguishing
    -0.51
    EndInit
    -0.50
     Monaten
    -0.49
     démission
    -0.49
    POSITIVE LOGITS
     itſelf
    0.78
     himſelf
    0.76
     themſelves
    0.74
     myſelf
    0.72
     Monfieur
    0.71
     ſeveral
    0.69
     Theſe
    0.68
     Perſ
    0.67
     perſ
    0.66
     ſever
    0.65
    Act Density 0.889%

    No Known Activations