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

    Neuronpedia

    INDEX
    Explanations

    words indicating evaluations or judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.57
    ioutil
    -0.55
    ✭✭
    -0.50
     "..\..\
    -0.50
    StructField
    -0.49
     "..\..\..\
    -0.48
    かったです
    -0.47
    ümmer
    -0.47
    jedis
    -0.46
     repres
    -0.46
    POSITIVE LOGITS
     mourut
    0.73
     quelcon
    0.70
     privilégi
    0.69
     définiti
    0.68
     ainfi
    0.66
     automatiques
    0.65
     déploy
    0.63
     supérieurs
    0.63
     ferons
    0.63
     élevés
    0.63
    Act Density 0.381%

    No Known Activations