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

    Neuronpedia

    INDEX
    Explanations

    discourse markers that indicate contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UrlResolution
    -0.68
    moveToNext
    -0.61
     bílá
    -0.58
     placée
    -0.57
    assertNotNull
    -0.57
    ValueStyle
    -0.56
    middels
    -0.56
     Theſe
    -0.56
     studenten
    -0.54
    انتهای
    -0.54
    POSITIVE LOGITS
     NSCoder
    0.61
    +#+
    0.58
     not
    0.57
     Wikimédia
    0.53
     neither
    0.53
     due
    0.53
    Espèce
    0.50
     before
    0.50
    ürm
    0.50
     ineffec
    0.49
    Act Density 0.153%

    No Known Activations