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

    Neuronpedia

    INDEX
    Explanations

    recurring phrases related to "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     each
    -0.60
     própria
    -0.52
     itself
    -0.51
     toute
    -0.49
     overall
    -0.48
    among
    -0.48
     هر
    -0.48
     genoux
    -0.48
     among
    -0.48
     celui
    -0.47
    POSITIVE LOGITS
    windowFixed
    0.83
     facets
    0.81
     permutations
    0.81
    ArrowToggle
    0.79
     تانيه
    0.78
     fuss
    0.77
    enumii
    0.75
     continúas
    0.74
     demás
    0.74
     محفوظة
    0.72
    Act Density 0.165%

    No Known Activations