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

    Neuronpedia

    INDEX
    Explanations

    the word "plain" with high activation values, possibly focusing on contexts related to simplicity or directness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "plain" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otos
    -0.90
    etheus
    -0.83
    yip
    -0.82
    allery
    -0.77
    glomer
    -0.76
    lasses
    -0.74
    bucks
    -0.73
    interstitial
    -0.73
    entric
    -0.72
    alez
    -0.71
    POSITIVE LOGITS
    plain
    1.08
    text
    1.06
    sheet
    0.97
     plain
    0.96
    sheets
    0.92
    rolled
    0.89
    cloth
    0.87
     vanilla
    0.87
    \\\\\\\\
    0.84
    ified
    0.82
    Act Density 0.018%

    No Known Activations