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

    Neuronpedia

    INDEX
    Explanations

    references to varying or distinct groups or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     économies
    -0.92
     fumée
    -0.80
     doute
    -0.71
     nucléaire
    -0.70
     biens
    -0.69
     vectorielle
    -0.69
     contactez
    -0.67
     écou
    -0.67
     complètes
    -0.66
     żel
    -0.66
    POSITIVE LOGITS
     different
    1.89
    Different
    1.74
     Different
    1.69
    different
    1.67
     DIFFERENT
    1.38
     diferentes
    1.33
     various
    1.28
     verschiedener
    1.27
     verschiedene
    1.27
    Various
    1.25
    Act Density 0.121%

    No Known Activations