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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.56
    ⟬
    -0.52
     anſ
    -0.50
     ſtand
    -0.49
     ſche
    -0.48
    ientras
    -0.46
     iſt
    -0.46
     équi
    -0.46
     regia
    -0.45
     civiliz
    -0.43
    POSITIVE LOGITS
    ůli
    0.87
     wegen
    0.86
     devido
    0.81
     بسبب
    0.79
     vanwege
    0.78
     благодаря
    0.74
     due
    0.74
     dėl
    0.72
    Due
    0.70
    due
    0.69
    Act Density 0.330%

    No Known Activations