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

    Neuronpedia

    INDEX
    Explanations

    information related to legal and political matters, including government actions, court rulings, and investigations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     sacrific
    -0.78
     silhou
    -0.70
     disadvant
    -0.70
     seiz
    -0.68
     Slug
    -0.66
     Alban
    -0.65
    GGGGGGGG
    -0.65
     leaps
    -0.65
     smugglers
    -0.63
     rack
    -0.61
    POSITIVE LOGITS
    ï¸ı
    1.12
    tre
    1.05
    sbm
    0.86
    many
    0.83
    strong
    0.82
    sure
    0.82
    very
    0.81
    said
    0.80
    owners
    0.80
    via
    0.80
    Act Density 9.968%

    No Known Activations