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

    Neuronpedia

    INDEX
    Explanations

    terms that denote specificity and guidelines in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardi
    -0.19
     Nielsen
    -0.15
     closure
    -0.15
    closure
    -0.15
    iesta
    -0.15
    inou
    -0.14
    arez
    -0.14
     Linh
    -0.14
    .btnClose
    -0.14
     Kore
    -0.14
    POSITIVE LOGITS
     language
    0.20
    language
    0.20
    -language
    0.19
    .language
    0.19
     Language
    0.18
     LANGUAGE
    0.18
    Language
    0.17
    -Language
    0.17
    anguage
    0.16
     lang
    0.16
    Act Density 0.001%

    No Known Activations