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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "list" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Insecta
    -0.16
    olla
    -0.15
    ãĤ¦ãĥĪ
    -0.14
    aney
    -0.14
    jourd
    -0.14
    enticate
    -0.14
    _CRITICAL
    -0.14
    etypes
    -0.13
    stan
    -0.13
    otu
    -0.13
    POSITIVE LOGITS
    owel
    0.29
    icle
    0.23
    verse
    0.22
    icles
    0.21
    serv
    0.20
    /Grid
    0.19
    eners
    0.19
    VERSE
    0.19
    crawler
    0.18
    ened
    0.18
    Act Density 0.016%

    No Known Activations