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

    Neuronpedia

    INDEX
    Explanations

    terms related to social or political change

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of change and its various implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     LIMITED
    -0.72
    ç«
    -0.71
     Whale
    -0.68
    amina
    -0.66
     Bei
    -0.66
     SAR
    -0.66
     DRAGON
    -0.64
     ducks
    -0.64
    -+-+
    -0.64
    vern
    -0.64
    POSITIVE LOGITS
    overs
    0.87
    making
    0.87
    over
    0.86
    agents
    0.80
    able
    0.78
     wrought
    0.77
    upt
    0.75
    ogue
    0.75
    ives
    0.74
    buck
    0.73
    Act Density 0.044%

    No Known Activations