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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and quotation marks indicating dialogue or citations

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

    end of quote followed by capitalized word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ruiter
    -0.62
    Hozzáférés
    -0.60
    TestingModule
    -0.60
    "}>
    -0.59
     estekak
    -0.58
     الرياضيه
    -0.57
    '}>
    -0.57
    ༐
    -0.57
    ſicht
    -0.57
    "))
    -0.57
    POSITIVE LOGITS
     woorden
    0.34
     consciência
    0.34
     justiça
    0.33
     Forderung
    0.32
    praš
    0.30
     témoignage
    0.29
    sofá
    0.29
     defStyleAttr
    0.29
    näm
    0.29
     formação
    0.29
    Act Density 0.116%

    No Known Activations