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

    Neuronpedia

    INDEX
    Explanations

    letters that are put together like 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical data or metrics related to counts or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.96
    ername
    -0.94
    iage
    -0.78
    terday
    -0.75
     oun
    -0.74
    terness
    -0.74
    uto
    -0.73
    hement
    -0.73
    lihood
    -0.70
    agy
    -0.66
    POSITIVE LOGITS
    Mand
    0.85
    Quotes
    0.79
    LESS
    0.78
    WIND
    0.78
    Viol
    0.77
    Trivia
    0.76
    Cla
    0.76
    OVER
    0.76
    Act
    0.75
    ORN
    0.74
    Act Density 0.499%

    No Known Activations