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

    Neuronpedia

    INDEX
    Explanations

    clauses mentioned within text

    oai_token-act-pair · gpt-3.5-turbo

    references to legal clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oppable
    -0.83
    aukee
    -0.76
    ersen
    -0.75
    ritz
    -0.74
    ESCO
    -0.67
     Popular
    -0.66
    VERTIS
    -0.64
    algia
    -0.64
    Rated
    -0.64
     Pixar
    -0.64
    POSITIVE LOGITS
    witz
    1.64
     clauses
    0.92
     stip
    0.82
     clause
    0.77
    rences
    0.76
    ttes
    0.75
     loophole
    0.72
    iao
    0.71
     clinch
    0.71
     delim
    0.70
    Act Density 0.005%

    No Known Activations