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

    Neuronpedia

    INDEX
    Explanations

    comparisons related to mechanical systems and their reliability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AppComponent
    -0.63
    rinfo
    -0.59
     >=",
    -0.59
    RTLD
    -0.57
     hidratante
    -0.57
    DeleteBehavior
    -0.56
     carina
    -0.55
    BeginContext
    -0.55
     cardiaque
    -0.54
     énergétique
    -0.53
    POSITIVE LOGITS
     traditional
    0.87
     conventional
    0.81
     manual
    0.81
     homemade
    0.75
    traditional
    0.74
    conventional
    0.73
     Traditional
    0.71
    Traditional
    0.70
     direct
    0.68
     electronic
    0.67
    Act Density 1.246%

    No Known Activations