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

    Neuronpedia

    INDEX
    Explanations

    names of cities or locations

    oai_token-act-pair · gpt-3.5-turbo

    names of cities and geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thia
    -0.81
    thood
    -0.80
    vana
    -0.77
    cedes
    -0.76
    uria
    -0.76
    vier
    -0.73
    isSpecialOrderable
    -0.72
    verbs
    -0.72
    oldemort
    -0.70
    duty
    -0.70
    POSITIVE LOGITS
     Police
    1.04
     skyline
    1.03
     Legislature
    0.95
     metropolitan
    0.94
     Regional
    0.92
     chapter
    0.91
     Metropolitan
    0.91
     Gazette
    0.90
     legislature
    0.90
     suburbs
    0.90
    Act Density 0.182%

    No Known Activations