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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or awareness about missing information

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.63
     estacion
    -0.48
    itarias
    -0.48
    ГЛА
    -0.47
    RequestBuilder
    -0.47
     jari
    -0.45
    abatic
    -0.45
     duras
    -0.45
     verv
    -0.45
     iconFacebook
    -0.45
    POSITIVE LOGITS
    RegressionTest
    0.71
    InjectAttribute
    0.67
    ConstraintMaker
    0.67
    DockStyle
    0.62
     ModelExpression
    0.60
     Roskov
    0.58
    MergeFrom
    0.55
     BrowserModule
    0.53
    Sklici
    0.52
    risse
    0.52
    Act Density 0.058%

    No Known Activations