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

    Neuronpedia

    INDEX
    Explanations

    polite phrases and expressions in correspondence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.56
    -0.56
    TestingModule
    -0.55
    ValueStyle
    -0.55
     ſind
    -0.54
     queſta
    -0.52
     JADX
    -0.52
     proposons
    -0.52
    IntoConstraints
    -0.52
     فريبيس
    -0.51
    POSITIVE LOGITS
    ActionCreators
    0.43
    Sincerely
    0.35
    createdBy
    0.33
    oxo
    0.32
     Arts
    0.32
     educator
    0.31
     Sincerely
    0.31
    性は
    0.30
     bestselling
    0.30
    ThemeOverlay
    0.30
    Act Density 0.088%

    No Known Activations