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

    Neuronpedia

    INDEX
    Explanations

    words related to legal actions and specific names, including surnames

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ADRA
    -0.72
    raints
    -0.67
    popular
    -0.64
    liest
    -0.63
    ulating
    -0.62
    kok
    -0.59
    UAL
    -0.59
     quo
    -0.59
    SIM
    -0.58
    abis
    -0.58
    POSITIVE LOGITS
    istics
    0.96
    oad
    0.95
    gren
    0.92
    ogue
    0.85
    oaded
    0.83
    ibrary
    0.82
    iffe
    0.81
    anguage
    0.78
    gage
    0.76
    agic
    0.75
    Act Density 12.182%

    No Known Activations