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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social issues like poverty, education, opportunities, and access to resources

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     puzz
    -0.74
     hint
    -0.68
     overest
    -0.68
     ado
    -0.68
     curiously
    -0.67
     sins
    -0.66
     cursing
    -0.66
     tabl
    -0.65
     unlucky
    -0.65
     mysteriously
    -0.65
    POSITIVE LOGITS
     sustainable
    1.15
     equitable
    1.04
     inclusive
    1.02
    cellence
    0.99
     responsibly
    0.96
    ordable
    0.95
     achievable
    0.89
     unbiased
    0.89
     productive
    0.88
     meaningful
    0.88
    Act Density 3.465%

    No Known Activations