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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of magic or magical experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DRV
    -0.16
    tridge
    -0.15
    áp
    -0.15
    ÙĨدگاÙĨ
    -0.15
     Cant
    -0.14
    /column
    -0.14
     opposite
    -0.14
    BASH
    -0.13
    ickers
    -0.13
    ssi
    -0.13
    POSITIVE LOGITS
    aldi
    0.18
     touch
    0.18
    touch
    0.18
    -touch
    0.17
    zers
    0.15
    magic
    0.15
    926
    0.15
    831
    0.15
    ous
    0.14
     Pon
    0.14
    Act Density 0.020%

    No Known Activations