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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Dio" in texts

    oai_token-act-pair · gpt-3.5-turbo

    the name "Di" followed by various contexts or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manship
    -0.79
    ties
    -0.73
     spare
    -0.72
    sburgh
    -0.69
    hips
    -0.68
     CBI
    -0.67
    */(
    -0.67
    ilater
    -0.66
    ï¸ı
    -0.66
    ãĤ¤ãĥĪ
    -0.66
    POSITIVE LOGITS
    agram
    1.29
    abol
    1.25
    ploma
    1.17
    ocese
    1.17
    abetic
    1.17
    abolic
    1.15
    urnal
    1.15
    agonal
    1.11
    plom
    1.10
    ablo
    1.10
    Act Density 0.014%

    No Known Activations