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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of the abbreviation "CP" with a high level of activation

    oai_token-act-pair · gpt-3.5-turbo

    references to polling or survey results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Goo
    -0.77
    sbm
    -0.71
    ebted
    -0.68
    âĸ¬
    -0.67
    ãĥĦ
    -0.65
     Admir
    -0.64
    geons
    -0.64
    wagen
    -0.63
    tainment
    -0.63
    iyah
    -0.62
    POSITIVE LOGITS
    ython
    1.01
    ople
    0.93
    erity
    0.92
    etition
    0.86
    illon
    0.86
    ollo
    0.86
    ocalypse
    0.85
    resent
    0.84
    ropri
    0.84
    AN
    0.83
    Act Density 0.011%

    No Known Activations