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

    Neuronpedia

    INDEX
    Explanations

    questions that begin with "What" or "Which"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     queſta
    -0.94
    OGND
    -0.88
    Autoritní
    -0.76
     kasarigan
    -0.73
     houſe
    -0.73
     PeEnEo
    -0.72
    ſtanding
    -0.71
    Rujuakan
    -0.71
     autorytatywna
    -0.71
     ſei
    -0.67
    POSITIVE LOGITS
     &
    0.35
     Marks
    0.33
     
    0.32
     marks
    0.32
     Investing
    0.31
    -
    0.31
     Garden
    0.30
     the
    0.30
    Marca
    0.30
     Rub
    0.30
    Act Density 0.101%

    No Known Activations