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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political events or policies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     tyr
    -0.69
     arsen
    -0.64
    avorite
    -0.60
    antine
    -0.60
    Export
    -0.60
    antry
    -0.60
     Minotaur
    -0.60
     Inqu
    -0.59
    oreal
    -0.57
     Metallic
    -0.57
    POSITIVE LOGITS
    stretched
    1.36
    fitted
    1.34
    smart
    1.12
    wards
    1.10
    casts
    1.07
    doors
    1.07
    fitting
    1.05
    bur
    0.99
    skirts
    0.99
    posts
    0.99
    Act Density 0.981%

    No Known Activations