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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social and environmental activism

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    prints
    -0.82
    ittal
    -0.81
    etry
    -0.79
    lite
    -0.73
    cade
    -0.73
    ĸļ
    -0.73
    Champ
    -0.69
    yi
    -0.68
    ometers
    -0.67
     cheered
    -0.67
    POSITIVE LOGITS
     deficiencies
    1.13
     pesky
    1.05
     backlog
    1.05
     misconceptions
    1.04
     adversity
    1.00
     inequalities
    0.99
     grievances
    0.99
     problems
    0.98
     shortcomings
    0.98
     boredom
    0.97
    Act Density 1.821%

    No Known Activations