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

    Neuronpedia

    INDEX
    Explanations

    complex mathematical expressions and variables related to statistical mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     are
    -0.35
    nä
    -0.34
    setup
    -0.34
    äuser
    -0.34
    og
    -0.34
    p
    -0.33
    n
    -0.33
    nt
    -0.33
     ideas
    -0.33
     du
    -0.32
    POSITIVE LOGITS
    AddTagHelper
    0.81
    Personendaten
    0.75
    __":
    0.71
     للاسماء
    0.71
    __':
    0.66
    Diweddarwch
    0.66
    ViewFeatures
    0.66
    fromnode
    0.66
     Chwiliwch
    0.65
     disambiguazione
    0.65
    Act Density 2.090%

    No Known Activations