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

    Neuronpedia

    INDEX
    Explanations

    keywords related to politics, law, and historical events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    risome
    -0.79
    idable
    -0.74
    tten
    -0.66
    inarily
    -0.61
    igmatic
    -0.60
    edient
    -0.58
    idth
    -0.58
    ernaut
    -0.58
    etitive
    -0.58
    ospel
    -0.57
    POSITIVE LOGITS
    ï¸ı
    0.77
    SPA
    0.70
    姫
    0.63
    URES
    0.63
    vals
    0.63
     syndrome
    0.63
     HW
    0.62
    Offline
    0.62
    WARE
    0.61
    Drive
    0.61
    Act Density 24.110%

    No Known Activations