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

    Neuronpedia

    INDEX
    Explanations

    references to Semitic languages and their associated terms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Par
    -0.65
    gh
    -0.64
     Per
    -0.64
    on
    -0.60
    <eos>
    -0.59
     –
    -0.58
    zz
    -0.57
     Ver
    -0.57
     D
    -0.56
    T
    -0.56
    POSITIVE LOGITS
     Hebrew
    1.26
    Hebrew
    1.20
    RenderAtEndOf
    1.16
     Hebrews
    1.09
     myſelf
    1.03
     Theſe
    0.96
     ་་
    0.96
     Malayalam
    0.91
    Hebrews
    0.90
    engertian
    0.89
    Act Density 0.003%

    No Known Activations