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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate exclusivity or emphasize additional attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.46
    ße
    -0.45
    @
    -0.44
    ↵
    -0.44
    6
    -0.44
    5
    -0.43
     manifestación
    -0.42
    gu
    -0.42
    sel
    -0.41
    ...
    -0.39
    POSITIVE LOGITS
    AddTagHelper
    1.14
     Савезне
    1.01
    verwijspagina
    0.99
     cherchés
    0.99
     محفوظة
    0.98
     Paglinawan
    0.97
    ChildScrollView
    0.97
    tagHelperRunner
    0.95
     nahilalakip
    0.94
    первых
    0.92
    Act Density 0.288%

    No Known Activations