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

    Neuronpedia

    INDEX
    Explanations

    punctuation, particularly commas

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

    struct field tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isContained
    -0.38
     purpoſe
    -0.38
    ScopeManager
    -0.38
    Alicia
    -0.37
    __))
    -0.36
     HUT
    -0.36
    Hau
    -0.35
     оригіналу
    -0.35
    CrossRef
    -0.35
     ingenu
    -0.35
    POSITIVE LOGITS
    Aholisi
    0.55
     intStringLen
    0.50
    Diwedd
    0.49
     comma
    0.48
    tvguidetime
    0.46
    Jîn
    0.46
    IMDG
    0.46
    WriteTagHelper
    0.45
     IMDG
    0.45
     للاسماء
    0.45
    Act Density 0.189%

    No Known Activations