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

    Neuronpedia

    INDEX
    Explanations

    phrases related to unity and community among people

    oai_token-act-pair · gpt-3.5-turbo

    references to "the people" in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.74
    Operation
    -0.70
    Parent
    -0.66
    BALL
    -0.66
    itta
    -0.63
     Lank
    -0.62
    inet
    -0.62
    NI
    -0.62
    Ha
    -0.60
    IT
    -0.60
    POSITIVE LOGITS
    hood
    1.18
     smugglers
    0.91
    folk
    0.85
     inhab
    0.85
    liest
    0.77
     entrusted
    0.77
     enslaved
    0.76
    ongs
    0.76
    aces
    0.76
     uprising
    0.75
    Act Density 0.081%

    No Known Activations