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

    Neuronpedia

    INDEX
    Explanations

    mentions or occurrences of the word "double"

    oai_token-act-pair · gpt-3.5-turbo

    references to "double" standards or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utical
    -0.86
    ALE
    -0.84
    onite
    -0.81
    ĸļ
    -0.78
    omo
    -0.78
    uary
    -0.75
    istry
    -0.74
    edIn
    -0.72
    ONY
    -0.72
    encer
    -0.67
    POSITIVE LOGITS
    header
    1.06
     sided
    0.98
     digit
    0.94
    headers
    0.91
     dipping
    0.89
    plet
    0.88
     digits
    0.88
     edged
    0.82
     negatives
    0.78
     eyel
    0.74
    Act Density 0.035%

    No Known Activations