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

    Neuronpedia

    INDEX
    Explanations

    quotation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Voltaje
    -0.66
    gü
    -0.62
    Potencia
    -0.61
    }^{+\
    -0.61
     Trung
    -0.56
    %;
    -0.56
    pozdrawiam
    -0.54
    spesies
    -0.54
     Duf
    -0.54
     Rom
    -0.54
    POSITIVE LOGITS
    "
    1.85
     "
    1.42
    ("
    1.34
    。"
    1.33
    ",
    1.28
    ]"
    1.24
    '"
    1.20
    ")
    1.19
    ","
    1.19
    ,'"
    1.16
    Act Density 0.422%

    No Known Activations