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

    Neuronpedia

    INDEX
    Explanations

    the phrase "ce" indicating a focus on demonstrative pronouns in French

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.98
     EconPapers
    -0.90
     esternos
    -0.87
    parsedMessage
    -0.87
     Roskov
    -0.85
    elemField
    -0.83
    帖最后由
    -0.81
    abestanden
    -0.80
    AndroidJUnit
    -0.79
    MethodManager
    -0.76
    POSITIVE LOGITS
     ce
    0.75
    jectures
    0.70
     parties
    0.69
     Ce
    0.58
     mas
    0.55
    ce
    0.52
    atsby
    0.51
    CE
    0.49
     الاطلاع
    0.49
    leuth
    0.49
    Act Density 0.097%

    No Known Activations