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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Bri" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cordialement
    -0.50
    __':
    -0.45
     Administrator
    -0.45
     conductores
    -0.45
     Agencies
    -0.45
     organisme
    -0.43
    horabuena
    -0.42
     AGENCIES
    -0.42
     daarvan
    -0.42
     Incorrect
    -0.42
    POSITIVE LOGITS
    Bri
    0.94
     Bri
    0.85
     bri
    0.75
    bri
    0.73
     Brick
    0.58
     Brig
    0.52
    Brick
    0.52
    Brig
    0.51
     للمعارف
    0.50
     brioche
    0.50
    Act Density 0.241%

    No Known Activations