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

    Neuronpedia

    INDEX
    Explanations

    official statements or quotes from government officials

    oai_token-act-pair · gpt-3.5-turbo

    references to officials in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸
    -0.97
    esville
    -0.76
    ĸļ
    -0.76
    xual
    -0.70
    arcity
    -0.70
    oppers
    -0.70
    =-=-
    -0.70
     Bengal
    -0.69
    ocene
    -0.68
     Horses
    -0.68
    POSITIVE LOGITS
    dom
    0.98
    ially
    0.87
     sanctioned
    0.82
    iating
    0.80
    doms
    0.76
     official
    0.75
     overseeing
    0.75
     spokesman
    0.74
    IAL
    0.73
    iaries
    0.71
    Act Density 0.026%

    No Known Activations