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

    Neuronpedia

    INDEX
    Explanations

    terms related to stability or things being stable

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stable."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hig
    -0.86
    vernment
    -0.80
    ulhu
    -0.75
     appealed
    -0.75
    tein
    -0.73
    FactoryReloaded
    -0.71
    atche
    -0.71
    externalActionCode
    -0.71
    printed
    -0.70
    uania
    -0.70
    POSITIVE LOGITS
     isot
    1.00
     stable
    0.94
     equilibrium
    0.84
    mate
    0.84
    iable
    0.83
     stability
    0.82
    mates
    0.79
     Stability
    0.78
     fixture
    0.77
     fry
    0.77
    Act Density 0.005%

    No Known Activations