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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal actions, law enforcement, and political activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pose
    -0.87
    FORE
    -0.81
     Hole
    -0.78
    nings
    -0.76
    çĦ
    -0.74
    MER
    -0.74
    enegger
    -0.73
     Dragonbound
    -0.73
     Cage
    -0.69
    ãĤ¤ãĥĪ
    -0.67
    POSITIVE LOGITS
    recated
    1.29
    ository
    1.27
    raved
    1.19
    artments
    1.17
    artment
    1.14
    ravity
    1.13
    uty
    1.13
    orters
    1.13
    utation
    1.11
    uties
    1.11
    Act Density 0.068%

    No Known Activations