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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to contexts or conditions surrounding an event

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

    in [preposition] + noun/adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     however
    -0.67
    however
    -0.57
     However
    -0.51
     therefore
    -0.50
    却
    -0.49
    However
    -0.48
     toutefois
    -0.47
     meanwhile
    -0.45
     jedoch
    -0.45
    therefore
    -0.44
    POSITIVE LOGITS
     autorytatywna
    0.77
    OGND
    0.76
     المعيارى
    0.74
    InjectAttribute
    0.68
    rungsseite
    0.66
    ंदीखरीदारी
    0.65
     चीज़ों
    0.63
     Chwiliwch
    0.60
     CreateTagHelper
    0.60
    transQ
    0.60
    Act Density 0.160%

    No Known Activations