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

    Neuronpedia

    INDEX
    Explanations

    numeric values and measurements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.77
    WriteBarrier
    -0.68
     postIndex
    -0.65
    륭
    -0.65
     onAnimation
    -0.63
     onPage
    -0.62
     onCancelled
    -0.61
     Obrador
    -0.61
     Faso
    -0.60
     Bourgoin
    -0.60
    POSITIVE LOGITS
     impra
    2.00
     increa
    1.87
     maneu
    1.81
     disreg
    1.80
     suscep
    1.78
     inappro
    1.74
     unden
    1.72
     disagre
    1.72
     reluct
    1.71
     affor
    1.70
    Act Density 3.812%

    No Known Activations