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

    Neuronpedia

    INDEX
    Explanations

    contrastive conjunctions indicating comparisons or distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.69
    ContentAsync
    -0.66
     venons
    -0.64
    CodedInputStream
    -0.60
     createState
    -0.59
    Tracce
    -0.58
     élé
    -0.57
     Democrá
    -0.57
     étoient
    -0.57
     kaarangay
    -0.57
    POSITIVE LOGITS
     despite
    1.14
    despite
    0.94
     malgré
    0.91
    Trotz
    0.89
     apesar
    0.86
     pese
    0.85
     while
    0.81
     meski
    0.81
     несмотря
    0.79
     due
    0.79
    Act Density 0.215%

    No Known Activations