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

    Neuronpedia

    INDEX
    Explanations

    phrases related to stability and predictability

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to stability and stability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owler
    -0.91
    odor
    -0.76
    insula
    -0.73
    FactoryReloaded
    -0.70
    ovember
    -0.69
    ema
    -0.69
    awks
    -0.68
    iq
    -0.67
    azard
    -0.67
    ilet
    -0.66
    POSITIVE LOGITS
    mate
    1.08
     isot
    1.02
    mates
    0.94
     Stability
    0.82
    ament
    0.80
     stability
    0.78
    oil
    0.77
     equilibrium
    0.76
     footing
    0.75
     steady
    0.74
    Act Density 0.090%

    No Known Activations