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

    Neuronpedia

    INDEX
    Explanations

    specific syntactic structures related to demonstratives and location references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Managua
    -0.52
    推荐阅读
    -0.52
     more
    -0.51
     zaidi
    -0.51
     opérateur
    -0.50
     Tasse
    -0.50
    posables
    -0.50
     Langu
    -0.49
    mente
    -0.49
    SharedCtor
    -0.49
    POSITIVE LOGITS
     este
    1.31
    THIS
    1.28
     THIS
    1.28
     this
    1.26
    this
    1.25
    Этот
    1.22
     diesem
    1.19
     THESE
    1.18
    This
    1.16
     acestui
    1.15
    Act Density 0.052%

    No Known Activations