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

    Neuronpedia

    INDEX
    Explanations

    references to free or open source work

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    >{@
    -0.71
    Datuak
    -0.56
     AttributeSet
    -0.49
     kaarangay
    -0.49
     proiz
    -0.49
     محفوظة
    -0.47
    antina
    -0.47
    ChildScrollView
    -0.47
    baldi
    -0.46
     behand
    -0.46
    POSITIVE LOGITS
    Попис
    0.60
     useAppContext
    0.60
    клопе
    0.58
     rospy
    0.55
    ('-'
    0.54
     Beller
    0.54
    AnchorStyles
    0.54
    leting
    0.52
    rüstung
    0.52
    versary
    0.51
    Act Density 0.001%

    No Known Activations