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

    Neuronpedia

    INDEX
    Explanations

    phrases related to state-controlled entities

    oai_token-act-pair · gpt-3.5-turbo

    references to state-owned enterprises and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸ı
    -0.80
    ï¸
    -0.70
     Aires
    -0.67
    lihood
    -0.66
    pload
    -0.65
     Bowl
    -0.64
     Telescope
    -0.61
     Bagg
    -0.61
     Harbor
    -0.60
     Hitman
    -0.60
    POSITIVE LOGITS
    appointed
    0.77
    idency
    0.74
    imposed
    0.73
    funded
    0.71
    ciating
    0.69
    inence
    0.69
     senator
    0.68
    usted
    0.65
    sylvania
    0.64
    aligned
    0.64
    Act Density 0.070%

    No Known Activations