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

    Neuronpedia

    INDEX
    Explanations

    references to sections or components within documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.59
    Diweddarwch
    -0.46
    ⟬
    -0.45
    </table>
    -0.43
    sidemargin
    -0.42
    astră
    -0.42
    分かります
    -0.41
    LEncoder
    -0.41
    Advertisement
    -0.41
    tagext
    -0.41
    POSITIVE LOGITS
     integrante
    0.63
    Part
    0.56
    part
    0.54
    way
    0.52
     Part
    0.52
    cular
    0.51
    ridge
    0.50
    cipation
    0.49
    ridges
    0.49
    cip
    0.48
    Act Density 0.131%

    No Known Activations