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

    Neuronpedia

    INDEX
    Explanations

    words related to social and political structures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to oppression and social hierarchies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quotes
    -0.80
     nails
    -0.76
     lamps
    -0.75
     markings
    -0.74
     understatement
    -0.74
     Eps
    -0.73
     lamp
    -0.72
     request
    -0.72
     tops
    -0.71
     Boots
    -0.70
    POSITIVE LOGITS
    dependent
    1.31
    olitical
    1.29
    capitalist
    1.25
    ocratic
    1.24
    olithic
    1.20
    uggish
    1.17
    inational
    1.16
    iberal
    1.16
    dominated
    1.15
    ethnic
    1.15
    Act Density 0.295%

    No Known Activations