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

    Neuronpedia

    INDEX
    Explanations

    concepts related to stability and stability-related conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pouce
    -0.63
     Tew
    -0.59
     ju
    -0.58
    ond
    -0.57
    ”
    -0.56
     want
    -0.56
     Pod
    -0.56
     heads
    -0.56
     Cera
    -0.55
    zu
    -0.55
    POSITIVE LOGITS
     Stable
    3.30
     stable
    3.17
    Stable
    3.11
    stable
    3.07
     stability
    2.70
     Stability
    2.65
    stability
    2.57
    Stability
    2.51
     stables
    2.33
     stabilize
    2.33
    Act Density 0.053%

    No Known Activations