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

    Neuronpedia

    INDEX
    Explanations

    forms of the word "which."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.86
     utafitiHapana
    -0.75
    ngoing
    -0.58
     kasarigan
    -0.56
     propOrder
    -0.56
    Euer
    -0.55
    Portale
    -0.54
    libft
    -0.53
     Flames
    -0.53
     Euer
    -0.53
    POSITIVE LOGITS
     which
    1.36
    which
    1.25
     Which
    1.24
    Which
    1.22
     WHICH
    1.10
    hich
    0.95
     wich
    0.91
    ซึ่ง
    0.85
     lequel
    0.76
     οποίο
    0.75
    Act Density 0.273%

    No Known Activations