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

    Neuronpedia

    INDEX
    Explanations

    promotional phrases related to bonuses and offers for banking or trading services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    welcome bonus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.69
    CppMethod
    -0.59
    KommentareTeilen
    -0.58
     CreateTagHelper
    -0.55
    TypedDataSet
    -0.49
     tartalomajánló
    -0.48
    Havolalar
    -0.48
    Kanpo
    -0.48
     henvisninger
    -0.48
    章节错误
    -0.47
    POSITIVE LOGITS
     jid
    0.40
    FST
    0.39
     guaranteed
    0.38
     BIC
    0.38
    Promises
    0.38
     promised
    0.35
     炭
    0.35
    bray
    0.35
     liberty
    0.35
     broken
    0.35
    Act Density 0.002%

    No Known Activations