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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "which" and its variations within questions and explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ImageContext
    -0.74
     mergeFrom
    -0.70
     myſelf
    -0.67
    Filmografie
    -0.64
     ――――
    -0.62
    IsPostBack
    -0.60
    RegressionTest
    -0.58
     Brahman
    -0.58
    wieś
    -0.58
    ſelf
    -0.58
    POSITIVE LOGITS
     Which
    0.83
     WHICH
    0.83
    Which
    0.81
    hich
    0.74
     luckily
    0.74
     vilket
    0.74
    which
    0.73
     thankfully
    0.72
     which
    0.70
     fortunately
    0.69
    Act Density 0.279%

    No Known Activations