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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing tendencies or inclinations

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

    tending to do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nephe
    -0.57
     Chwiliwch
    -0.55
     sulfu
    -0.51
     useAppContext
    -0.51
    Tikang
    -0.50
    المناصب
    -0.49
    Искәрмәләр
    -0.47
     sapon
    -0.47
     autorytatywna
    -0.46
    clearInterval
    -0.46
    POSITIVE LOGITS
     tends
    1.11
     tend
    1.10
     tended
    0.93
     tienden
    0.87
     cenderung
    0.85
    tend
    0.78
     tendency
    0.77
     tiende
    0.76
     suele
    0.75
     tending
    0.75
    Act Density 0.012%

    No Known Activations