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

    Neuronpedia

    INDEX
    Explanations

    specific locations or establishments frequented by people for various activities

    oai_token-act-pair · gpt-3.5-turbo

    locations and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obs
    -0.68
    ratulations
    -0.67
     passports
    -0.63
    anson
    -0.62
     coherent
    -0.62
     lyr
    -0.62
    sle
    -0.60
     campaigner
    -0.59
     puzzle
    -0.58
     glimps
    -0.58
    POSITIVE LOGITS
    itent
    0.86
    grounds
    0.77
     headquarters
    0.77
     Headquarters
    0.76
    aimon
    0.74
     premises
    0.74
    orage
    0.73
     Simulator
    0.72
     helm
    0.72
     plaza
    0.70
    Act Density 0.253%

    No Known Activations