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

    Neuronpedia

    INDEX
    Explanations

    legal terms and references

    oai_token-act-pair · gpt-3.5-turbo

    mentions of court-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸ı
    -0.76
    yip
    -0.69
     Pyro
    -0.69
    jiang
    -0.68
    resso
    -0.67
    mson
    -0.66
     sow
    -0.65
     Saban
    -0.64
    Tang
    -0.64
    oute
    -0.63
    POSITIVE LOGITS
    rooms
    1.34
    esan
    1.14
    room
    1.11
    auld
    1.05
     proceedings
    0.98
     filings
    0.92
     hearings
    0.89
     martial
    0.88
     filing
    0.84
     transcripts
    0.83
    Act Density 0.041%

    No Known Activations