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

    Neuronpedia

    INDEX
    Explanations

    the word "respectively."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    linking items by order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.77
    GEBURTSDATUM
    -0.68
     المعيارى
    -0.67
     houſe
    -0.66
    -0.65
     lyre
    -0.61
     anſ
    -0.60
     Houſe
    -0.59
     ſind
    -0.59
    Geplaatst
    -0.59
    POSITIVE LOGITS
     respectively
    1.16
     respectivamente
    0.91
    respectively
    0.88
     respectivement
    0.82
    それぞれ
    0.59
     соответственно
    0.59
     respective
    0.53
     collectively
    0.48
     rispet
    0.44
     separately
    0.44
    Act Density 0.011%

    No Known Activations