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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government actions or regulations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.69
     Construct
    -0.68
     Incarnation
    -0.66
    hof
    -0.66
     sacrament
    -0.65
     Jinn
    -0.64
     Oval
    -0.63
    ãĤ¤ãĥĪ
    -0.63
    \">
    -0.62
     Upton
    -0.62
    POSITIVE LOGITS
     crackdown
    1.11
     viol
    0.86
     enforced
    0.86
     enforcement
    0.82
    alos
    0.78
     imposed
    0.78
     harshly
    0.78
     enforcing
    0.78
    riminal
    0.75
     exerted
    0.74
    Act Density 0.051%

    No Known Activations