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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating isolation or security locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hurricanes
    -0.74
    wolves
    -0.69
     memes
    -0.69
    ULTS
    -0.67
     commercials
    -0.65
     acron
    -0.65
     genomes
    -0.64
     empires
    -0.64
    deals
    -0.64
    iots
    -0.64
    POSITIVE LOGITS
     location
    1.73
     spot
    1.48
     place
    1.38
     vantage
    1.32
     area
    1.27
     position
    1.23
     room
    1.19
     locations
    1.17
     corner
    1.11
    location
    1.09
    Act Density 0.287%

    No Known Activations