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

    Neuronpedia

    INDEX
    Explanations

    references to game-related terms and programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     w
    -0.63
    w
    -0.58
    webElementXpaths
    -0.57
     v
    -0.57
    v
    -0.51
    vw
    -0.47
    𝘄
    -0.45
    wch
    -0.45
    wv
    -0.45
    wdata
    -0.44
    POSITIVE LOGITS
     We
    0.71
     Will
    0.61
     Were
    0.61
     Willing
    0.60
     Window
    0.60
     Went
    0.59
     Well
    0.59
     You
    0.59
     Wide
    0.58
    We
    0.57
    Act Density 0.796%

    No Known Activations