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

    demonstrative pronoun or specification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.51
     ſol
    -0.50
     ſer
    -0.49
     ſta
    -0.49
     ſou
    -0.49
    ➟
    -0.49
     ſever
    -0.48
     auffi
    -0.48
     canst
    -0.48
     juſ
    -0.48
    POSITIVE LOGITS
     Exacts
    0.43
     those
    0.42
     THOSE
    0.41
    的那个
    0.41
    脚注の使い方
    0.41
     uska
    0.41
     quelle
    0.40
    InteropServices
    0.40
     Those
    0.39
    ,
    0.39
    Act Density 0.042%

    No Known Activations