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

    Neuronpedia

    INDEX
    Explanations

    information related to policy-making and legislation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    riot
    -0.70
    mong
    -0.70
    ndum
    -0.70
    pired
    -0.69
    worker
    -0.67
     Shutterstock
    -0.67
    cit
    -0.66
    roth
    -0.64
    rim
    -0.64
    ulic
    -0.63
    POSITIVE LOGITS
     specifics
    1.27
     motivations
    1.21
     particulars
    1.20
     whereabouts
    1.19
     extent
    1.14
     characteristics
    1.13
     reasons
    1.09
     exact
    1.08
     motives
    1.05
     details
    1.05
    Act Density 1.975%

    No Known Activations