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

    Neuronpedia

    INDEX
    Explanations

    names of public institutions like libraries, schools, and public services

    oai_token-act-pair · gpt-3.5-turbo

    references to public institutions or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kson
    -0.88
    oldemort
    -0.80
    ansas
    -0.79
    orsi
    -0.74
    oused
    -0.74
    xual
    -0.73
    daq
    -0.72
    auga
    -0.70
    ikawa
    -0.69
    uana
    -0.69
    POSITIVE LOGITS
     Accountability
    0.86
     Affairs
    0.83
     Opinion
    0.82
     Policy
    0.81
     Ethics
    0.81
     Library
    0.78
     Interest
    0.78
     Service
    0.76
    policy
    0.75
    etary
    0.74
    Act Density 0.019%

    No Known Activations