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

    Neuronpedia

    INDEX
    Explanations

    the word "they" and its variations in context

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

    The pronoun "They"

    np_acts-logits-general · gemini-2.0-flash

    they followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.61
     MessageBoxIcon
    -0.61
    fastjson
    -0.57
     noqa
    -0.56
     وتسجيلات
    -0.55
    dime
    -0.54
     الرياضيه
    -0.52
    zielle
    -0.51
     aikaa
    -0.51
    preuve
    -0.49
    POSITIVE LOGITS
     themselves
    0.80
    Their
    0.77
     all
    0.69
    They
    0.68
     Lordships
    0.68
     Their
    0.67
    BOTH
    0.66
     berdua
    0.65
    self
    0.64
     THEY
    0.64
    Act Density 0.186%

    No Known Activations