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

    Neuronpedia

    INDEX
    Explanations

    references to academic publications and authors in a structured context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     démocr
    -0.70
     bestaan
    -0.62
     sauvages
    -0.57
     finnas
    -0.55
     poitrine
    -0.54
     terminé
    -0.54
     HasFactory
    -0.53
     solusi
    -0.53
     amélior
    -0.52
     volontaire
    -0.51
    POSITIVE LOGITS
     Dalai
    0.74
    Gambas
    0.73
    Jereo
    0.71
     Nobel
    0.69
    PhysRevD
    0.67
     Doge
    0.66
    клопе
    0.65
    PMailer
    0.63
    دانشنامهٔ
    0.62
    Diweddarwch
    0.62
    Act Density 0.479%

    No Known Activations