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

    Neuronpedia

    INDEX
    Explanations

    references to subway stations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of subway systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ul
    -0.74
     Williamson
    -0.71
    IRD
    -0.69
    Copyright
    -0.67
    yer
    -0.65
    Remote
    -0.64
     Odin
    -0.64
    wine
    -0.63
     Bret
    -0.63
    ================================================================
    -0.63
    POSITIVE LOGITS
     subway
    1.25
     Subway
    1.01
    avorite
    1.00
    ngth
    1.00
    orough
    0.85
     entrances
    0.83
     commute
    0.81
     Railroad
    0.79
     station
    0.79
     fare
    0.78
    Act Density 0.010%

    No Known Activations