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

    Neuronpedia

    INDEX
    Explanations

    the concept of stability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pod
    -0.65
    墨
    -0.62
    ond
    -0.59
    меча
    -0.59
    zu
    -0.58
     pouce
    -0.57
    Printf
    -0.56
    FullScreen
    -0.55
    rond
    -0.53
    sudo
    -0.53
    POSITIVE LOGITS
     Stable
    2.99
    Stable
    2.87
     stable
    2.84
    stable
    2.74
     stability
    2.59
     Stability
    2.56
    stability
    2.47
    Stability
    2.47
     stabilize
    2.38
     stabilisation
    2.36
    Act Density 0.075%

    No Known Activations