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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ythe
    -0.20
    manship
    -0.15
    ovah
    -0.15
    eren
    -0.15
    λιά
    -0.15
    heid
    -0.15
    ë¹Ļ
    -0.15
    nung
    -0.14
    hyth
    -0.14
    oller
    -0.14
    POSITIVE LOGITS
    mai
    0.17
    stin
    0.16
    evin
    0.15
     Maar
    0.14
     Waters
    0.14
     bald
    0.14
    asers
    0.14
    oder
    0.14
    inton
    0.14
    assy
    0.14
    Act Density 0.023%

    No Known Activations