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

    Neuronpedia

    INDEX
    Explanations

    references to stability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.68
     '\\;'
    -0.61
    bollah
    -0.58
    隈
    -0.58
     Capitan
    -0.58
     Viitattu
    -0.55
    RegressionTest
    -0.54
    sleep
    -0.52
    GraphicsUnit
    -0.49
     Picchu
    -0.49
    POSITIVE LOGITS
    court
    0.90
     court
    0.77
     courts
    0.76
     stable
    0.71
    courts
    0.69
    CURLOPT
    0.67
    stable
    0.67
    Stable
    0.66
     Stable
    0.64
     ProtoMessage
    0.62
    Act Density 0.125%

    No Known Activations