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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "point," particularly in contexts suggesting listing or emphasizing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imits
    -0.17
     pointer
    -0.16
    ark
    -0.16
    -alert
    -0.16
    vert
    -0.15
    mer
    -0.15
    how
    -0.15
    he
    -0.14
    gow
    -0.14
    rb
    -0.14
    POSITIVE LOGITS
    edly
    0.27
    ill
    0.21
    aneous
    0.21
    lessly
    0.20
    wise
    0.20
     зÑĢениÑı
    0.18
    y
    0.18
    ycastle
    0.17
    éĴŁ
    0.17
    æĵĬ
    0.16
    Act Density 0.069%

    No Known Activations