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

    Neuronpedia

    INDEX
    Explanations

    labels and message elements in a user interface context

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

    UI labels and messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cession
    -0.56
     ſte
    -0.56
     tranſ
    -0.55
     itſelf
    -0.54
    Trip
    -0.54
     Commute
    -0.53
    Eman
    -0.53
    trip
    -0.53
     Wish
    -0.52
     ſind
    -0.52
    POSITIVE LOGITS
     lbl
    1.28
    lbl
    1.16
    Lbl
    0.82
    LBL
    0.79
     UILabel
    0.58
    UILabel
    0.52
     label
    0.50
    QLabel
    0.50
    JLabel
    0.50
     QLabel
    0.49
    Act Density 0.001%

    No Known Activations