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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and measurements related to experimental setups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enggak
    -1.74
     creș
    -1.66
     și
    -1.59
     ști
    -1.57
     viață
    -1.46
     ๆ
    -1.43
     Și
    -1.42
    Și
    -1.41
     uș
    -1.41
     maș
    -1.41
    POSITIVE LOGITS
     grossen
    1.95
     gröss
    1.94
     sólo
    1.90
     äusser
    1.77
     tumour
    1.77
     programme
    1.74
     colour
    1.74
    colour
    1.71
    Colour
    1.69
    Sólo
    1.67
    Act Density 1.951%

    No Known Activations