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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "public."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to information becoming public or being made public

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    uana
    -0.96
    atchewan
    -0.82
    nesota
    -0.78
    outhern
    -0.75
    ansas
    -0.74
    kson
    -0.74
    nian
    -0.71
    vell
    -0.71
    pell
    -0.71
    llan
    -0.70
    POSITIVE LOGITS
     relations
    0.98
    relations
    0.88
     outcry
    0.81
    ised
    0.80
     humiliation
    0.78
     opinion
    0.77
     affairs
    0.77
    ãĥ¤
    0.76
     servants
    0.76
    izing
    0.76
    Act Density 0.043%

    No Known Activations