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

    Neuronpedia

    INDEX
    Explanations

    references to governmental or state-related entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "state" in various contexts, particularly in relation to government and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    poons
    -0.95
    poon
    -0.80
    ayson
    -0.77
    aukee
    -0.76
    odi
    -0.75
     APR
    -0.72
    CAST
    -0.72
    lio
    -0.72
    veyard
    -0.70
    ï¸ı
    -0.70
    POSITIVE LOGITS
    rooms
    0.97
    lessness
    0.93
    less
    0.91
    hood
    0.90
    room
    0.85
     apparatus
    0.84
     legislatures
    0.82
    wide
    0.82
     appar
    0.78
     repression
    0.76
    Act Density 0.054%

    No Known Activations