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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms related to computer networking or systems operations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.59
     class
    -0.57
     Fig
    -0.57
     Flores
    -0.56
     nghiệm
    -0.54
     use
    -0.54
     even
    -0.54
    طر
    -0.54
     Davis
    -0.53
     Madsen
    -0.53
    POSITIVE LOGITS
    PWR
    1.55
     PWR
    1.41
     myſelf
    1.00
     himſelf
    0.94
    脚注の使い方
    0.92
     itſelf
    0.91
     Anſ
    0.89
     themſelves
    0.87
     Jefus
    0.87
    pwr
    0.87
    Act Density 0.000%

    No Known Activations