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

    Neuronpedia

    INDEX
    Explanations

    locations mentioned in news articles

    oai_token-act-pair · gpt-3.5-turbo

    place names and geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AMS
    -0.77
    measures
    -0.77
    efficients
    -0.77
    ogens
    -0.75
    ptoms
    -0.73
    redits
    -0.71
    orders
    -0.70
    éĹĺ
    -0.70
    votes
    -0.68
    drops
    -0.68
    POSITIVE LOGITS
     native
    1.22
     suburb
    1.19
     resident
    1.06
     courtroom
    0.98
     teenager
    0.97
     businessman
    0.97
     homeowner
    0.96
     restaur
    0.95
     teen
    0.95
     dentist
    0.92
    Act Density 0.117%

    No Known Activations