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

    Neuronpedia

    INDEX
    Explanations

    words related to public services and infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    references to public services or public entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.82
    uana
    -0.72
    RANT
    -0.71
    Scroll
    -0.71
    kson
    -0.70
    aughs
    -0.70
    Pg
    -0.70
    vell
    -0.70
    aundering
    -0.69
    daq
    -0.68
    POSITIVE LOGITS
     relations
    0.87
     transportation
    0.84
     hazard
    0.82
     affairs
    0.82
     servants
    0.81
     outreach
    0.81
     sector
    0.80
     purse
    0.80
    izes
    0.79
     health
    0.78
    Act Density 0.045%

    No Known Activations