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

    Neuronpedia

    INDEX
    Explanations

    references to physical boundaries or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.62
     rhestr
    -0.59
    thums
    -0.56
     ivelany
    -0.52
     Taktlose
    -0.49
    دانشنامهٔ
    -0.48
     tartalomajánló
    -0.48
    тропо
    -0.47
     nakalista
    -0.47
    asmuch
    -0.45
    POSITIVE LOGITS
     confines
    0.61
     joys
    0.60
     depths
    0.57
     intricacies
    0.56
     glories
    0.53
     complexities
    0.52
     contours
    0.52
     workings
    0.51
     tenets
    0.50
     essence
    0.49
    Act Density 0.567%

    No Known Activations