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

    Neuronpedia

    INDEX
    Explanations

    references to lifting mechanisms or devices

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

    lift

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.55
    contentPane
    -0.51
     Coy
    -0.50
     Goy
    -0.49
     Browne
    -0.49
     Ω
    -0.48
     Keyes
    -0.48
     "
    -0.47
     Eub
    -0.47
     Jacobs
    -0.47
    POSITIVE LOGITS
     lift
    2.44
    lift
    2.42
    Lift
    2.38
     Lift
    2.38
     lifts
    2.02
     LIFT
    1.96
    lifts
    1.86
     lifting
    1.62
     lifted
    1.61
    Lifting
    1.59
    Act Density 0.009%

    No Known Activations