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

    Neuronpedia

    INDEX
    Explanations

    locations and directions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ofic
    -0.52
    graphicx
    -0.50
    Vag
    -0.49
    Beaucoup
    -0.48
    Cependant
    -0.48
    astron
    -0.48
    Même
    -0.48
     Pourtant
    -0.47
    Dès
    -0.47
    Parmi
    -0.47
    POSITIVE LOGITS
     Southwest
    0.91
     Southeast
    0.89
     Northeast
    0.89
     Northwest
    0.86
    Southwest
    0.86
    outheast
    0.84
    southwest
    0.82
    Northwest
    0.79
     northwest
    0.79
    Northeast
    0.78
    Act Density 0.115%

    No Known Activations