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

    Neuronpedia

    INDEX
    Explanations

    terms related to social and political issues, such as racism, slavery, and controversial government policies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     regrets
    -0.67
     trust
    -0.66
     CONTR
    -0.65
     Donation
    -0.64
     depends
    -0.63
     deficit
    -0.59
     sums
    -0.59
     IPM
    -0.58
     Decision
    -0.58
     fid
    -0.57
    POSITIVE LOGITS
     abound
    1.41
     prolifer
    1.24
     rampant
    1.09
     everywhere
    1.04
     popping
    1.02
     emerge
    0.99
     prevail
    0.99
     thrive
    0.96
     bloom
    0.96
     circulate
    0.95
    Act Density 0.783%

    No Known Activations