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

    Neuronpedia

    INDEX
    Explanations

    words related to smallness or insignificance

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "minimum."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Compass
    -0.69
     reforming
    -0.68
     Danger
    -0.67
     Dreams
    -0.64
    eering
    -0.59
     Balk
    -0.58
     Democracy
    -0.57
     compe
    -0.57
     Conquest
    -0.56
     Welfare
    -0.56
    POSITIVE LOGITS
    nesota
    1.32
    iatures
    1.28
    otaur
    1.26
    istered
    1.12
    ivan
    1.11
    isite
    1.08
    ibus
    1.07
    istries
    1.05
    usc
    1.04
    utes
    1.03
    Act Density 0.017%

    No Known Activations