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

    Neuronpedia

    INDEX
    Explanations

    phrases related to advocacy and lobbying activities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    agers
    -0.58
    orah
    -0.57
    ochet
    -0.52
    agher
    -0.50
    xus
    -0.50
    endon
    -0.48
    osuke
    -0.47
    士
    -0.46
     Eucl
    -0.45
    ilet
    -0.45
    POSITIVE LOGITS
     efforts
    0.62
     advocacy
    0.60
     effort
    0.55
     coordinator
    0.52
     organizations
    0.50
     campaigns
    0.49
     services
    0.49
     firm
    0.49
     expenditures
    0.49
     theater
    0.48
    Act Density 9.067%

    No Known Activations