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

    Neuronpedia

    INDEX
    Explanations

    German words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    German words related to storytelling or narrative elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    resh
    -0.85
    behind
    -0.81
    inth
    -0.79
    amsung
    -0.78
    anqu
    -0.77
    owler
    -0.76
    -------------
    -0.76
    elsh
    -0.75
    sticks
    -0.75
    ramid
    -0.75
    POSITIVE LOGITS
     ré
    0.98
     Mé
    0.94
     Vie
    0.89
     Ré
    0.88
     Nou
    0.87
     Excellence
    0.86
     dé
    0.84
     Guer
    0.83
     Bou
    0.82
     Tay
    0.82
    Act Density 0.179%

    No Known Activations