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

    Neuronpedia

    INDEX
    Explanations

    descriptions of everyday activities and situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     maksi
    -1.49
     hina
    -1.45
     lele
    -1.44
     alkoh
    -1.42
     uhr
    -1.37
     keramik
    -1.36
     Meksi
    -1.33
     optik
    -1.33
     mef
    -1.32
     haup
    -1.31
    POSITIVE LOGITS
     belonged
    0.72
     wasn
    0.72
     was
    0.69
     türlü
    0.67
    Może
    0.66
     dropped
    0.66
     znaj
    0.64
     belongs
    0.64
     turned
    0.62
     stored
    0.62
    Act Density 0.587%

    No Known Activations