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

    Neuronpedia

    INDEX
    Explanations

    patterns of characters or codes that don't correspond to meaningful words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    sequences of 'x' characters followed by numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pru
    -0.75
    sburgh
    -0.75
    DERR
    -0.74
    zona
    -0.74
     Lauder
    -0.73
    ãĥĦ
    -0.68
    maid
    -0.67
    awaru
    -0.66
     Garry
    -0.66
    assetsadobe
    -0.64
    POSITIVE LOGITS
    aminer
    0.94
    Ry
    0.86
    avier
    0.85
    posed
    0.84
    iii
    0.81
    amination
    0.81
    terday
    0.80
    86
    0.79
    cb
    0.78
    kb
    0.78
    Act Density 0.022%

    No Known Activations