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

    Neuronpedia

    INDEX
    Explanations

    words related to social programs and benefits

    oai_token-act-pair · gpt-3.5-turbo

    references to social programs and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nces
    -0.83
     landfall
    -0.68
    Äĩ
    -0.67
     Shannon
    -0.64
    oning
    -0.63
    pless
    -0.63
    ilts
    -0.63
     Twain
    -0.63
     ridden
    -0.62
    mares
    -0.61
    POSITIVE LOGITS
    Health
    0.80
     Security
    0.79
     Advisor
    0.77
    Flow
    0.77
    ists
    0.77
    Work
    0.77
     Responsibility
    0.76
     Forces
    0.75
    Sys
    0.74
    Registration
    0.73
    Act Density 0.014%

    No Known Activations