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

    Neuronpedia

    INDEX
    Explanations

    punctuations and their frequencies in the context of industrial processes and product descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lange
    -0.17
    инов
    -0.16
    £¼
    -0.15
    igraph
    -0.15
    ekim
    -0.14
    _medium
    -0.14
    elt
    -0.14
    contres
    -0.14
     Advocate
    -0.14
    505
    -0.14
    POSITIVE LOGITS
    oya
    0.17
    igon
    0.16
    Brandon
    0.15
     Pang
    0.15
    GLOBAL
    0.14
     Trev
    0.14
    stretch
    0.14
    çĤī
    0.14
     repmat
    0.14
    oshi
    0.14
    Act Density 0.046%

    No Known Activations