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

    Neuronpedia

    INDEX
    Explanations

    phrases related to simplicity or plainness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "plain"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otos
    -0.88
    yip
    -0.78
    umar
    -0.73
    glomer
    -0.73
    obal
    -0.71
    etheus
    -0.70
    onz
    -0.70
    conservancy
    -0.70
    lasses
    -0.69
    ept
    -0.69
    POSITIVE LOGITS
    plain
    1.10
    text
    1.07
    sheet
    0.91
     plain
    0.90
    \\\\\\\\
    0.90
    cloth
    0.84
    rolled
    0.83
    ified
    0.82
    sheets
    0.82
     vanilla
    0.80
    Act Density 0.014%

    No Known Activations