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

    Neuronpedia

    INDEX
    Explanations

    the word "slight" and its variations, indicating small degrees or minor changes

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

    small degree or modification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.95
    اریخ
    -0.83
    hyrchwyd
    -0.76
    majánló
    -0.75
    SharedDtor
    -0.75
     propOrder
    -0.74
     Савезне
    -0.73
     hObject
    -0.72
    ReusableCell
    -0.71
     dAtA
    -0.70
    POSITIVE LOGITS
     slight
    1.50
    Slight
    1.43
     Slight
    1.32
     leichte
    0.76
     leichten
    0.71
     slightest
    0.67
     ligero
    0.66
     légère
    0.65
     ligera
    0.63
     léger
    0.63
    Act Density 0.003%

    No Known Activations