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

    Neuronpedia

    INDEX
    Explanations

    legal terms and concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    gae
    -0.78
     renaissance
    -0.76
     giants
    -0.73
    ebted
    -0.72
    inav
    -0.71
    thood
    -0.70
     grows
    -0.70
     Growing
    -0.70
    iku
    -0.68
    joice
    -0.68
    POSITIVE LOGITS
     violated
    1.08
     improperly
    1.01
     improper
    1.00
     incrim
    0.98
     unlawfully
    0.98
     appellant
    0.98
     beforehand
    0.98
     contempor
    0.97
     misinterpret
    0.96
    Had
    0.94
    Act Density 5.014%

    No Known Activations