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

    Neuronpedia

    INDEX
    Explanations

    the presence of introductory or framing phrases in a document

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

    unilateral calculate common

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     calendriers
    -0.79
    openzeppelin
    -0.77
    stdafx
    -0.61
     propOrder
    -0.59
     autorytatywna
    -0.59
    ibatis
    -0.56
    zyden
    -0.56
    reactivex
    -0.56
     мѣ
    -0.56
    Kjelder
    -0.55
    POSITIVE LOGITS
     themſelves
    0.79
     ſtate
    0.78
     reaſon
    0.73
     perſon
    0.70
     alſo
    0.70
     ſame
    0.69
     cauſe
    0.69
     raiſ
    0.68
     Jefus
    0.68
     againſt
    0.66
    Act Density 0.635%

    No Known Activations