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

    Neuronpedia

    INDEX
    Explanations

    elements related to language and writing techniques, particularly adjectives and verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ekk
    -0.17
     Annotations
    -0.16
    vek
    -0.15
    rips
    -0.14
     hÆ°á»Ľng
    -0.14
    qua
    -0.14
    orig
    -0.13
    rientation
    -0.13
    oden
    -0.13
    rip
    -0.13
    POSITIVE LOGITS
     words
    0.25
     sentences
    0.23
     writing
    0.21
     sentence
    0.21
     language
    0.20
     Ñģлова
    0.20
    -word
    0.19
     word
    0.19
     expressions
    0.19
     ph
    0.18
    Act Density 0.262%

    No Known Activations