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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the purpose or reason behind actions

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

    for the sake of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initComponents
    -0.64
     tunn
    -0.46
     Whitfield
    -0.43
     cong
    -0.43
    nhung
    -0.42
     Connolly
    -0.41
     BrowserRouter
    -0.41
    Slf
    -0.41
     exhibit
    -0.40
    MCS
    -0.40
    POSITIVE LOGITS
     sake
    2.27
     Sake
    1.73
    ake
    1.13
    ValueStyle
    0.99
    akes
    0.78
    zake
    0.66
     saken
    0.64
     purposes
    0.61
    QMetaType
    0.59
    purposes
    0.57
    Act Density 0.003%

    No Known Activations