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

    Neuronpedia

    INDEX
    Explanations

    locations or cities

    oai_token-act-pair · gpt-3.5-turbo

    names of major cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥł
    -0.74
    hops
    -0.73
    ilater
    -0.72
    ãĤ½
    -0.69
    ãģĻ
    -0.68
    inav
    -0.65
    pees
    -0.64
     assum
    -0.63
    mentioned
    -0.63
    nings
    -0.62
    POSITIVE LOGITS
     firefighters
    0.88
     skyline
    0.87
     Police
    0.85
     resident
    0.84
     rapper
    0.84
     Mayor
    0.83
     police
    0.80
     Zoo
    0.80
     natives
    0.79
     firefighter
    0.78
    Act Density 0.188%

    No Known Activations