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

    Neuronpedia

    INDEX
    Explanations

    instances of the Spanish word "de" indicating possession or relationship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    of or de

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     faſt
    -0.90
     raiſ
    -0.79
    ſelf
    -0.78
     myſelf
    -0.78
     kasarigan
    -0.78
     ſta
    -0.76
     itſelf
    -0.76
     pleaſure
    -0.75
     ſtand
    -0.74
     ſever
    -0.74
    POSITIVE LOGITS
     de
    1.14
     of
    0.96
     OF
    0.77
     De
    0.75
     di
    0.74
    ของ
    0.73
     Of
    0.72
     של
    0.71
    of
    0.71
    De
    0.71
    Act Density 0.002%

    No Known Activations