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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or regulatory proceedings

    oai_token-act-pair · gpt-3.5-turbo

    references to public hearings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jc
    -0.79
    football
    -0.74
    animate
    -0.74
    rip
    -0.73
    resp
    -0.70
    heres
    -0.68
    Commerce
    -0.66
    Password
    -0.66
    err
    -0.65
    cer
    -0.65
    POSITIVE LOGITS
     hearings
    1.71
     Hearing
    1.23
     hearing
    1.05
     Hear
    0.98
     "$:/
    0.91
     proceedings
    0.87
     briefings
    0.86
    terness
    0.85
    imony
    0.84
     screenings
    0.84
    Act Density 0.007%

    No Known Activations