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

    Neuronpedia

    INDEX
    Explanations

    words related to appropriateness and propriety in various contexts

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

    propriety and impropriety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onOptions
    -0.42
     Савезне
    -0.41
    äum
    -0.38
     Touren
    -0.35
    UserScript
    -0.35
     propOrder
    -0.35
    DeltaTime
    -0.35
     зді
    -0.34
    #![
    -0.34
     CreateTagHelper
    -0.34
    POSITIVE LOGITS
    nappropriate
    0.60
    appropriate
    0.60
     appropriate
    0.59
     APPROPRI
    0.57
     Appropriate
    0.57
     inappropriate
    0.57
    Appropriate
    0.56
     appropri
    0.52
    Inappropriate
    0.51
     appropriateness
    0.50
    Act Density 0.119%

    No Known Activations