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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts

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

    that followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itself
    -0.76
     enfans
    -0.66
    itself
    -0.66
     itſelf
    -0.62
     Itself
    -0.55
     яке
    -0.53
     vœux
    -0.52
     inconvénients
    -0.51
     âmes
    -0.48
     которое
    -0.48
    POSITIVE LOGITS
     jotka
    0.77
     amelyek
    0.72
     themselves
    0.70
     neler
    0.67
     אלה
    0.66
     которые
    0.65
     leerlingen
    0.65
     GPs
    0.64
    setzungen
    0.61
     Tories
    0.61
    Act Density 0.135%

    No Known Activations