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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating public statements, announcements, or political expressions

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

    public statements

    np_acts-logits-general · gemini-2.0-flash

    publicly speaking or stating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TestingModule
    -0.40
    AndEndTag
    -0.39
    NameInMap
    -0.35
    true
    -0.32
     CreateTagHelper
    -0.31
    Примітки
    -0.31
    TagMode
    -0.31
     ModelRenderer
    -0.30
     true
    -0.30
     physical
    -0.30
    POSITIVE LOGITS
     tuyên
    0.69
     declaraciones
    0.65
    peech
    0.59
     déclarations
    0.58
     speeches
    0.58
     announcing
    0.57
     discurso
    0.57
     publicly
    0.57
     speech
    0.56
    ScopeManager
    0.56
    Act Density 0.429%

    No Known Activations