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

    Neuronpedia

    INDEX
    Explanations

    key terms related to methodologies and their effectiveness in research or practices

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     myſelf
    -1.23
     ſever
    -1.08
     purpoſe
    -1.05
    تقاوى
    -1.05
     itſelf
    -1.05
     Efq
    -1.04
     Shakspeare
    -1.02
     فريبيس
    -1.02
     ſtate
    -1.02
     fubject
    -1.02
    POSITIVE LOGITS
     a
    1.01
    :
    1.01
     the
    0.87
     an
    0.83
     
    0.81
     either
    0.79
     two
    0.71
     simply
    0.69
     “
    0.66
     is
    0.63
    Act Density 4.538%

    No Known Activations