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

    Neuronpedia

    INDEX
    Explanations

    words related to political discussions and negotiations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.85
     Dangerous
    -0.80
    hower
    -0.70
    ¿½
    -0.67
    CRIPTION
    -0.65
    =-=-
    -0.65
    ÙIJ
    -0.64
     Beir
    -0.61
     Apostle
    -0.61
    hoe
    -0.61
    POSITIVE LOGITS
    ulators
    1.19
    ulatory
    1.16
    rett
    1.14
    ulations
    1.14
    ardless
    1.10
    arded
    1.10
    nant
    1.09
    isters
    1.08
    ulus
    1.07
    roup
    1.04
    Act Density 0.008%

    No Known Activations