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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms that suggest a comparison or reference to previous statements or assertions

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

    conjunctions and prepositions introducing clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -0.49
     Houſe
    -0.47
    yntaxException
    -0.46
     extranjero
    -0.44
     emperador
    -0.42
    sidemargin
    -0.42
     quoque
    -0.41
     purpoſe
    -0.40
     Diseño
    -0.40
     Anſ
    -0.39
    POSITIVE LOGITS
    setViewName
    0.58
     BytesLike
    0.53
     tail
    0.50
    pano
    0.49
    ագրություններ
    0.49
    RAZ
    0.49
     tru
    0.47
    ech
    0.47
     falou
    0.46
     divul
    0.45
    Act Density 0.260%

    No Known Activations