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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social inequality and privilege

    oai_token-act-pair · gpt-3.5-turbo

    instances of social inequality and disparity between different groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Destination
    -0.70
    ĸļ
    -0.65
     sequence
    -0.63
     Showtime
    -0.62
     fingerprints
    -0.61
     Coliseum
    -0.60
     Regulation
    -0.59
     Proposition
    -0.59
     Solitaire
    -0.58
     workflow
    -0.58
    POSITIVE LOGITS
    educated
    1.05
    acists
    1.02
    arians
    1.00
    bred
    0.94
    outher
    0.93
    loving
    0.93
    married
    0.92
    scient
    0.91
    minded
    0.91
    ateurs
    0.91
    Act Density 0.753%

    No Known Activations