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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating collaborative or conditional actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sequences introduced by prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     herself
    -0.41
    haupt
    -0.40
     pipes
    -0.40
    UserEntity
    -0.39
     boss
    -0.39
     Zink
    -0.38
    layoutControl
    -0.38
    Besos
    -0.37
    -0.36
    olverine
    -0.35
    POSITIVE LOGITS
     cherchés
    0.60
     ivelany
    0.54
    SequentialGroup
    0.53
    رشف
    0.51
     aDecoder
    0.50
     Bewußt
    0.49
     CreateTagHelper
    0.49
    SharedDtor
    0.49
     estekak
    0.48
     ***!
    0.48
    Act Density 0.114%

    No Known Activations