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

    Neuronpedia

    INDEX
    Explanations

    references to specific groups of people or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ArgumentParser
    -0.90
    帖最后由
    -0.89
    PerformLayout
    -0.78
    sidemargin
    -0.71
     Exacts
    -0.69
    IndentedString
    -0.68
    MigrationBuilder
    -0.67
     alberi
    -0.63
     assisti
    -0.62
     <>",
    -0.60
    POSITIVE LOGITS
     who
    1.05
    osoever
    0.97
     quienes
    0.84
     quem
    0.81
     którzy
    0.79
     those
    0.78
    who
    0.76
    those
    0.71
     quien
    0.71
    那些
    0.70
    Act Density 0.222%

    No Known Activations