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

    Neuronpedia

    INDEX
    Explanations

    terms related to stability and instability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ond
    -0.70
    ↵
    -0.70
    op
    -0.69
    o
    -0.67
    I
    -0.65
    zu
    -0.65
    2
    -0.64
     also
    -0.64
     ju
    -0.63
    ”
    -0.63
    POSITIVE LOGITS
     Stable
    2.15
     stabilisation
    2.01
     Stability
    1.98
    Stable
    1.97
    stability
    1.92
     stability
    1.90
     Stabili
    1.89
     stable
    1.88
     stabilis
    1.88
    Stability
    1.87
    Act Density 0.105%

    No Known Activations