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

    Neuronpedia

    INDEX
    Explanations

    variations and nuances in tone throughout various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Públicas
    -0.56
    EXISTS
    -0.50
     gug
    -0.46
    AlreadyExists
    -0.45
     aé
    -0.45
     domestique
    -0.44
     Jacobs
    -0.44
     Púb
    -0.43
     Vikipedi
    -0.43
    Exceeded
    -0.43
    POSITIVE LOGITS
    Tone
    1.16
     Tone
    1.13
    tone
    1.08
     tone
    1.02
     Tones
    0.96
    tones
    0.85
     tones
    0.83
    toned
    0.81
    TONE
    0.81
     tonal
    0.79
    Act Density 0.013%

    No Known Activations