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

    Neuronpedia

    INDEX
    Explanations

    phrases related to economic development and social disparities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic disparities and socioeconomic indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nope
    -0.81
    didn
    -0.74
     hadn
    -0.73
    sorry
    -0.70
     docs
    -0.70
    ?!"
    -0.69
     stash
    -0.68
     booze
    -0.67
     dudes
    -0.67
    Want
    -0.66
    POSITIVE LOGITS
     principally
    0.90
     predominant
    0.85
     consist
    0.84
     characteristic
    0.84
     predomin
    0.83
     customary
    0.82
     considerable
    0.81
     approximately
    0.79
     varied
    0.78
     mainly
    0.77
    Act Density 1.193%

    No Known Activations