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

    Neuronpedia

    INDEX
    Explanations

    the term "Grand" or related geographical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.96
     whoſe
    -0.93
     myſelf
    -0.92
     nôtre
    -0.92
     enfans
    -0.89
     meurt
    -0.88
     poches
    -0.85
     мәкал
    -0.85
     feroit
    -0.85
     pouvoit
    -0.85
    POSITIVE LOGITS
     Grand
    0.82
    Grand
    0.68
     makeStyles
    0.62
    ...
    0.61
     но
    0.57
     inter
    0.56
    Now
    0.55
     sto
    0.55
     dé
    0.55
     “
    0.54
    Act Density 0.101%

    No Known Activations