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

    Neuronpedia

    INDEX
    Explanations

    references to New Zealand or its abbreviations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Gans
    -0.76
     Thurman
    -0.72
     STARS
    -0.68
     Mans
    -0.68
     Towne
    -0.68
    protoimpl
    -0.66
     Stars
    -0.65
     Huffman
    -0.65
    rophi
    -0.65
    kosi
    -0.65
    POSITIVE LOGITS
     Zealand
    1.89
     ZEALAND
    1.62
    1.47
     NZ
    1.34
     Kiwi
    1.32
     zealand
    1.30
     Zelanda
    1.24
    NZ
    1.19
    Auckland
    1.15
    Kiwi
    1.14
    Act Density 0.004%

    No Known Activations