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

    Neuronpedia

    INDEX
    Explanations

    comparative and superlative forms of adjectives and quantifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Foire
    -0.46
     istället
    -0.45
     mogelijkheid
    -0.45
     mariée
    -0.44
     Pferde
    -0.44
     tandis
    -0.43
     gatto
    -0.40
     vaikka
    -0.40
     choć
    -0.40
     legyen
    -0.39
    POSITIVE LOGITS
     autorytatywna
    1.04
     unknownFields
    0.91
     propOrder
    0.82
    ViewFeatures
    0.79
     Chwiliwch
    0.77
    GEBURTSDATUM
    0.76
     समीक्षक
    0.75
     незавершена
    0.74
    Rüyada
    0.73
     estekak
    0.73
    Act Density 0.234%

    No Known Activations