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

    Neuronpedia

    INDEX
    Explanations

    the word "said" in various contexts

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

    said preceding noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.53
     ſte
    -0.51
     faſt
    -0.49
     myſelf
    -0.49
     tranſ
    -0.49
     himſelf
    -0.48
     ✭✭
    -0.47
     виправивши
    -0.47
     themſelves
    -0.47
     تعدى
    -0.45
    POSITIVE LOGITS
     said
    0.83
     SAID
    0.78
     Said
    0.75
    Said
    0.67
     dicha
    0.66
     aforesaid
    0.66
     dichos
    0.65
     dichas
    0.62
    said
    0.60
     mevcut
    0.56
    Act Density 0.007%

    No Known Activations