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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "the" and other common connectives or qualifiers within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -translate
    -0.17
    erview
    -0.16
     addCriterion
    -0.16
    inous
    -0.15
    FileSync
    -0.14
    ä»Ģ
    -0.14
    _atts
    -0.14
     Carm
    -0.14
    agic
    -0.14
    idos
    -0.13
    POSITIVE LOGITS
     title
    0.17
    lj
    0.16
    EGA
    0.15
     tone
    0.15
    arine
    0.15
    Neighbor
    0.14
    anik
    0.13
     nÃŃ
    0.13
    MIT
    0.13
    title
    0.13
    Act Density 0.135%

    No Known Activations