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

    Neuronpedia

    INDEX
    Explanations

    sentences that express a strong opinion or critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.54
    <bos>
    -0.53
     $
    -0.49
    orn
    -0.47
    inska
    -0.47
     gal
    -0.47
     pal
    -0.47
     ,
    -0.46
     c
    -0.45
     (
    -0.45
    POSITIVE LOGITS
     виправивши
    1.14
     disambiguazione
    0.96
     дописавши
    0.86
    ScopeManager
    0.84
     OFDb
    0.81
     surla
    0.81
    Personensuche
    0.78
    localctx
    0.75
     مرئيه
    0.75
     bezeichneter
    0.74
    Act Density 0.013%

    No Known Activations