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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to programming and software functions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.80
    aarrggbb
    -0.79
    xdr
    -0.73
     vägen
    -0.71
     politiet
    -0.71
     tør
    -0.70
     ProtoMessage
    -0.70
     sèche
    -0.69
     refroidissement
    -0.67
     thistle
    -0.66
    POSITIVE LOGITS
     Omni
    1.12
     omp
    1.12
     om
    1.08
    om
    1.06
     Chunk
    1.06
     OM
    1.05
    chom
    1.02
     Lombard
    1.01
     chunk
    0.98
    OM
    0.98
    Act Density 0.096%

    No Known Activations