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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this" and similar demonstrative references

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     betweenstory
    -1.01
    LookAnd
    -0.98
    writeFieldEnd
    -0.92
    httphttps
    -0.85
    InteropServices
    -0.81
     medusa
    -0.79
     Lukaku
    -0.79
     protoimpl
    -0.78
    NameInMap
    -0.77
     Protobuf
    -0.77
    POSITIVE LOGITS
     THIS
    1.20
    THIS
    1.13
    This
    1.09
     This
    1.04
    this
    1.03
     this
    1.00
     esta
    0.71
    Esta
    0.71
    Этот
    0.69
     ésta
    0.68
    Act Density 1.445%

    No Known Activations