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

    Neuronpedia

    INDEX
    Explanations

    repeated structural patterns in data entries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     queſta
    -1.04
    niſſe
    -0.89
    iſchen
    -0.88
    ſchaft
    -0.84
    iſche
    -0.84
     Geiſt
    -0.83
    <unused28>
    -0.82
    <unused16>
    -0.81
    <unused8>
    -0.81
    <unused3>
    -0.81
    POSITIVE LOGITS
    '
    0.37
    `
    0.36
    "
    0.32
    o
    0.32
    i
    0.30
    beforeSend
    0.30
    ‘
    0.28
     Holanda
    0.28
    a
    0.26
    ”
    0.26
    Act Density 0.286%

    No Known Activations