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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating increased intensity or frequencies in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fjspx
    -0.66
     linkovi
    -0.61
    Хьажоргаш
    -0.61
     SwitchCompat
    -0.58
     thiệu
    -0.57
     Syrians
    -0.55
     raiſ
    -0.55
     smaak
    -0.54
     propOrder
    -0.54
     Ꮎ
    -0.54
    POSITIVE LOGITS
    TagHelper
    0.62
    ContentAsync
    0.56
    AndEndTag
    0.55
    tagHelperRunner
    0.55
    点此举报
    0.53
    tega
    0.52
    ruptedException
    0.50
     mendes
    0.50
    värr
    0.50
     مشين
    0.48
    Act Density 0.166%

    No Known Activations