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

    Neuronpedia

    INDEX
    Explanations

    words related to elusive or mysterious concepts

    oai_token-act-pair · gpt-3.5-turbo

    words related to elites or elitism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nant
    -0.72
    NEY
    -0.65
    ãĥ´ãĤ¡
    -0.63
    LESS
    -0.63
     Rolls
    -0.62
    xit
    -0.61
     Freeze
    -0.61
    orial
    -0.61
    ãĥ¼ãĥĨãĤ£
    -0.61
    ł
    -0.60
    POSITIVE LOGITS
    izabeth
    1.29
    iquid
    1.23
    ibrary
    1.23
    ixir
    1.17
    usive
    1.13
    uding
    0.96
    uded
    0.95
    ijah
    0.95
    ipt
    0.90
    abor
    0.89
    Act Density 0.019%

    No Known Activations