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

    Neuronpedia

    INDEX
    Explanations

    references to locations within a specific village

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or "villages" within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cies
    -0.99
    etr
    -0.84
    etric
    -0.83
    odynam
    -0.82
    manship
    -0.82
    etrical
    -0.81
    stroke
    -0.81
    iscopal
    -0.80
    irection
    -0.79
    cedes
    -0.75
    POSITIVE LOGITS
     Village
    1.00
    rats
    0.84
     Voice
    0.83
    Walk
    0.80
     Halls
    0.80
     Cemetery
    0.80
     Plaza
    0.77
     Weekend
    0.75
     Clinic
    0.75
     Yard
    0.75
    Act Density 0.010%

    No Known Activations