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

    Neuronpedia

    INDEX
    Explanations

    references to the United States Postal Service

    oai_token-act-pair · gpt-3.5-turbo

    references to various government service agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umin
    -0.72
    luaj
    -0.68
    icted
    -0.68
    åĮ
    -0.67
    kered
    -0.65
    arest
    -0.65
    theless
    -0.65
    netflix
    -0.64
    00007
    -0.64
    ongyang
    -0.63
    POSITIVE LOGITS
     Employees
    1.12
     Provider
    1.11
     Service
    1.00
     Dogs
    0.90
     Corps
    0.90
     Animals
    0.87
     Desk
    0.87
     Advis
    0.85
     Agent
    0.84
     Worker
    0.82
    Act Density 0.015%

    No Known Activations