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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocz
    -0.59
     Imag
    -0.58
    chka
    -0.56
     Archiv
    -0.56
     mats
    -0.56
     Infusion
    -0.55
     Grin
    -0.55
     Shar
    -0.55
     Bron
    -0.55
     editions
    -0.54
    POSITIVE LOGITS
    __':
    0.94
    __":
    0.81
    SharedCtor
    0.76
     vermelhas
    0.76
     propOrder
    0.71
    sizeCache
    0.67
     avulla
    0.66
     brancas
    0.65
     AttributeSet
    0.65
     kanssa
    0.64
    Act Density 1.257%

    No Known Activations