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

    Neuronpedia

    INDEX
    Explanations

    occurrences of varying degrees of formality in language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.78
     mukana
    -0.76
    _]
    -0.71
    riman
    -0.70
     Rodrig
    -0.70
     Kaufman
    -0.69
    diğini
    -0.68
    льки
    -0.68
     Kaufmann
    -0.68
    exa
    -0.67
    POSITIVE LOGITS
     Maat
    1.04
     Aad
    0.96
     EEC
    0.94
     Steen
    0.92
     Maas
    0.89
     Muir
    0.88
    Aad
    0.88
     Baal
    0.86
     Neel
    0.86
     oon
    0.84
    Act Density 0.159%

    No Known Activations