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

    Neuronpedia

    INDEX
    Explanations

    concepts related to the nature and characteristics of statistical properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     o
    -0.51
    +
    -0.51
     +
    -0.47
      
    -0.45
    <eos>
    -0.45
    /
    -0.43
     logic
    -0.42
     C
    -0.42
     ev
    -0.42
     The
    -0.42
    POSITIVE LOGITS
    sizeCache
    1.03
     Bourgoin
    0.97
     beginnetje
    0.96
    AutoScaleMode
    0.96
     nahilalakip
    0.94
     ISNI
    0.92
    !*\
    0.91
     Мексичка
    0.90
    __':
    0.89
     <=",
    0.88
    Act Density 0.972%

    No Known Activations