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

    Neuronpedia

    INDEX
    Explanations

    negative numerical values or statistics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    graceful
    -0.49
    rinfo
    -0.49
    equalTo
    -0.48
     [*]
    -0.44
     lanterns
    -0.44
     pala
    -0.44
    AutoScale
    -0.44
    ядок
    -0.44
     dec
    -0.43
     SARA
    -0.42
    POSITIVE LOGITS
     okuyayım
    0.84
     jspb
    0.79
     يتيمه
    0.79
    rawDesc
    0.71
    RetentionPolicy
    0.70
    )\}
    0.69
    UnsafeEnabled
    0.68
    unnitel
    0.67
    دانشنامهٔ
    0.67
    ollectionView
    0.66
    Act Density 0.001%

    No Known Activations