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

    Neuronpedia

    INDEX
    Explanations

    references to government entities and agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dede
    -0.66
    ViewInit
    -0.64
     springfox
    -0.60
     lambs
    -0.59
    ✨:
    -0.58
     Negroes
    -0.58
     orthon
    -0.57
    Mink
    -0.57
     duke
    -0.57
     diagonals
    -0.57
    POSITIVE LOGITS
     officials
    0.85
     agencies
    0.83
     AGENCIES
    0.65
     departments
    0.65
     Officials
    0.65
    ally
    0.63
     Government
    0.62
    Officials
    0.61
    enterOuterAlt
    0.60
    wide
    0.60
    Act Density 0.143%

    No Known Activations