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

    Neuronpedia

    INDEX
    Explanations

    names and titles of people related to legal cases and medical professionals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Scient
    -0.64
    ALLY
    -0.63
     Wilmington
    -0.62
     Franch
    -0.61
    ICE
    -0.59
     Lomb
    -0.59
    ãĤī
    -0.59
    CDC
    -0.56
     Osc
    -0.56
     Canaver
    -0.56
    POSITIVE LOGITS
    aji
    0.76
     Alam
    0.70
    ulk
    0.68
    ini
    0.68
    lords
    0.68
    ahs
    0.67
    zeb
    0.67
    oran
    0.67
    olics
    0.67
    roo
    0.66
    Act Density 8.580%

    No Known Activations