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

    Neuronpedia

    INDEX
    Explanations

    phrases and words associated with the act of referencing or quoting sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tober
    -0.15
    dings
    -0.15
    æĦıæĢĿ
    -0.15
    lingen
    -0.15
    ie
    -0.15
    orsi
    -0.15
    .itemView
    -0.14
    readcr
    -0.14
    iesz
    -0.14
    ding
    -0.13
    POSITIVE LOGITS
    erdale
    0.17
     proven
    0.16
    otas
    0.15
    akra
    0.15
    isbury
    0.15
     ruth
    0.15
     reasons
    0.14
    ncpy
    0.14
     Clare
    0.14
    ird
    0.14
    Act Density 0.026%

    No Known Activations