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

    connecting phrase after that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kaarangay
    -0.77
     ویکی‌پدی
    -0.68
    MessageTagHelper
    -0.60
    ReusableCell
    -0.57
    DockStyle
    -0.57
    ➟
    -0.56
    RegistryLite
    -0.54
    ьаж
    -0.54
    afficheront
    -0.54
     Himo
    -0.53
    POSITIVE LOGITS
    ,
    0.52
     That
    0.51
     THAT
    0.48
    That
    0.47
    THAT
    0.42
     THOSE
    0.41
     Those
    0.38
     اون
    0.38
     Schilling
    0.37
     quello
    0.36
    Act Density 0.031%

    No Known Activations