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

    Neuronpedia

    INDEX
    Explanations

    names from professional fields or scientific contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    dress
    -0.83
     Agents
    -0.67
     mileage
    -0.63
    tenance
    -0.63
     Agent
    -0.62
     Etsy
    -0.62
     agent
    -0.61
    dates
    -0.61
     Continental
    -0.60
    IAL
    -0.60
    POSITIVE LOGITS
    Ko
    1.13
    elsen
    1.06
    agara
    1.05
    emi
    1.02
    uggets
    1.01
    ña
    1.00
    elson
    0.99
    urnal
    0.98
    isance
    0.97
    emonic
    0.94
    Act Density 0.015%

    No Known Activations