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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting that indicate citations or references in reviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ema
    -0.17
    ostel
    -0.16
    arine
    -0.16
    niž
    -0.15
    oran
    -0.14
    zel
    -0.14
    nen
    -0.14
    Canon
    -0.13
    ighted
    -0.13
    lena
    -0.13
    POSITIVE LOGITS
    angu
    0.16
    loat
    0.14
    ubb
    0.13
     ÐĹав
    0.13
     itemView
    0.13
     respons
    0.13
    ØŃÙĩ
    0.13
    ÑĢаÐ
    0.13
    /slick
    0.13
    uv
    0.13
    Act Density 0.013%

    No Known Activations