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

    Neuronpedia

    INDEX
    Explanations

    mentions of public entities such as organizations or services

    oai_token-act-pair · gpt-3.5-turbo

    references to public institutions or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansas
    -0.77
    kson
    -0.76
    oldemort
    -0.74
    netflix
    -0.71
    orsi
    -0.70
    ikawa
    -0.70
    aterasu
    -0.68
    Downloadha
    -0.67
    xual
    -0.67
    audi
    -0.66
    POSITIVE LOGITS
     Affairs
    0.94
     Relations
    0.91
     Opinion
    0.91
     Service
    0.90
     Interest
    0.89
     Safety
    0.87
     Schools
    0.87
     Accountability
    0.84
    ity
    0.83
     Policy
    0.83
    Act Density 0.022%

    No Known Activations