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

    Neuronpedia

    INDEX
    Explanations

    references to a specific location or structure, possibly related to industry or infrastructure, such as refineries

    oai_token-act-pair · gpt-3.5-turbo

    references to oil refineries and their related infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppings
    -0.81
    acted
    -0.73
     Lives
    -0.70
    Americans
    -0.70
    ACTED
    -0.69
    bits
    -0.69
    thin
    -0.65
    legged
    -0.65
    evil
    -0.63
     Matter
    -0.63
    POSITIVE LOGITS
     annex
    0.87
    ounter
    0.84
    yard
    0.79
     keeper
    0.76
     builder
    0.76
     barracks
    0.75
     empire
    0.75
     occupancy
    0.75
     layouts
    0.74
     precinct
    0.73
    Act Density 0.031%

    No Known Activations