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

    Neuronpedia

    INDEX
    Explanations

    specific references to city names, particularly "City Hall"

    oai_token-act-pair · gpt-3.5-turbo

    references to various city locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etsk
    -0.87
    iotic
    -0.84
    itude
    -0.82
    rity
    -0.81
    terday
    -0.79
    iosis
    -0.78
    orescence
    -0.76
    icides
    -0.74
    arians
    -0.73
    pmwiki
    -0.73
    POSITIVE LOGITS
     Council
    1.06
    scape
    1.05
    hall
    0.99
     Limits
    0.98
    wide
    0.97
     Hall
    0.95
    Lab
    0.91
     Coun
    0.88
     Halls
    0.87
     Islanders
    0.86
    Act Density 0.036%

    No Known Activations