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

    Neuronpedia

    INDEX
    Explanations

    phrases contrasting two different situations or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     them
    -0.67
    them
    -0.61
     étoit
    -0.58
     META
    -0.55
     knots
    -0.54
     éché
    -0.53
     Maddox
    -0.51
     vuur
    -0.50
     memutus
    -0.49
     Ketch
    -0.49
    POSITIVE LOGITS
    Whereas
    1.00
     conversely
    0.97
     whereas
    0.95
    Sedangkan
    0.94
     Whereas
    0.92
    whereas
    0.88
    Conversely
    0.87
     Conversely
    0.86
     andererseits
    0.86
     dagegen
    0.85
    Act Density 0.192%

    No Known Activations