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

    Neuronpedia

    INDEX
    Explanations

    references to specific scientific studies or publications

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.93
    ########.
    -0.90
    Abitanti
    -0.83
    +:+
    -0.77
    ✨:
    -0.74
    KURZBESCHREIBUNG
    -0.73
     beginnetje
    -0.71
    InSection
    -0.71
     pinulongan
    -0.70
     Савезне
    -0.69
    POSITIVE LOGITS
    美国
    0.75
     America
    0.75
     American
    0.74
    hdysval
    0.74
     Amerika
    0.70
    American
    0.69
     امريكا
    0.69
    America
    0.67
    美国的
    0.66
    美國
    0.64
    Act Density 0.612%

    No Known Activations