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

    Neuronpedia

    INDEX
    Explanations

    phrases involving citations or references to previously mentioned statements

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

    said + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſte
    -0.58
     myſelf
    -0.54
     faſt
    -0.54
     ſever
    -0.53
     Anſ
    -0.53
     themſelves
    -0.52
     itſelf
    -0.51
     ſta
    -0.50
     againſt
    -0.49
     tranſ
    -0.49
    POSITIVE LOGITS
     dicha
    0.75
     dichas
    0.66
    該
    0.64
     respective
    0.64
    该
    0.62
     该
    0.62
     данного
    0.61
     dichos
    0.60
     aforesaid
    0.57
     данный
    0.55
    Act Density 0.020%

    No Known Activations