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

    Neuronpedia

    INDEX
    Explanations

    phrases introducing specific concepts or terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.72
     Houſe
    -0.69
     Majefty
    -0.67
     Stande
    -0.65
    bows
    -0.61
    >--}}
    -0.58
     exten
    -0.58
     Efq
    -0.56
     houſe
    -0.56
     frauen
    -0.55
    POSITIVE LOGITS
     called
    1.86
    called
    1.74
     CALLED
    1.74
     Called
    1.69
    Called
    1.59
     llamado
    1.47
     chamado
    1.36
     appelée
    1.30
     llamada
    1.30
    叫做
    1.29
    Act Density 0.208%

    No Known Activations