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

    Neuronpedia

    INDEX
    Explanations

    words related to public institutions or entities

    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
     mete
    -0.65
    ikawa
    -0.61
     wink
    -0.60
    kson
    -0.58
     nails
    -0.58
     flick
    -0.58
     annex
    -0.56
     wax
    -0.56
    aterasu
    -0.56
     bare
    -0.56
    POSITIVE LOGITS
     Affairs
    1.04
     Opinion
    0.97
     Safety
    0.92
     Relations
    0.92
     Defender
    0.86
     Service
    0.86
     Works
    0.86
     Policy
    0.85
     Sector
    0.85
     servants
    0.84
    Act Density 0.032%

    No Known Activations