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

    Neuronpedia

    INDEX
    Explanations

    phrases questioning or explaining reasons and motivations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unknownFields
    -0.78
    CodedInputStream
    -0.62
    IUrlHelper
    -0.59
     CreateTagHelper
    -0.56
    ญิง
    -0.55
    ädie
    -0.54
    DeleteBehavior
    -0.53
     zewnętrzne
    -0.51
     circonst
    -0.51
     Pring
    -0.49
    POSITIVE LOGITS
     why
    0.85
     Daarom
    0.76
     Derfor
    0.75
     فريبيس
    0.74
     weshalb
    0.72
     Dlatego
    0.72
     للمعارف
    0.71
     dlatego
    0.69
    HasForeignKey
    0.66
    ViewFeatures
    0.66
    Act Density 0.255%

    No Known Activations