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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical treatment effects and estimation methodologies

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

    average treatment effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jspb
    -0.54
     محفوظة
    -0.46
     صوتيه
    -0.44
    原始内容存档于
    -0.42
    BASELINE
    -0.41
    optionalTypeArgs
    -0.41
    ModelAdmin
    -0.40
    archiviato
    -0.40
    WEBPACK
    -0.40
    AlterField
    -0.40
    POSITIVE LOGITS
     queſta
    0.50
    TokenNameRPAREN
    0.47
    genodigd
    0.46
    exels
    0.45
    Disliked
    0.44
     iſt
    0.44
     userEmail
    0.42
     accommodations
    0.42
    pecially
    0.42
    idiary
    0.41
    Act Density 0.561%

    No Known Activations