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

    Neuronpedia

    INDEX
    Explanations

    the presence of dialogue or quoted speech in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houd
    -0.50
    Демографія
    -0.47
     المعيارى
    -0.46
    protoc
    -0.46
     [];
    -0.43
     houſe
    -0.43
     peso
    -0.42
     Houſe
    -0.41
    IsContent
    -0.41
    loyees
    -0.40
    POSITIVE LOGITS
     said
    0.76
     explained
    0.63
     explains
    0.57
     he
    0.56
     commented
    0.55
     remarked
    0.55
     says
    0.54
     Infórmanos
    0.54
     explicó
    0.54
    said
    0.54
    Act Density 0.058%

    No Known Activations