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

    Neuronpedia

    INDEX
    Explanations

    positive and notable mentions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     habet
    -0.59
     tamen
    -0.57
     religieuses
    -0.56
     inſ
    -0.54
     médias
    -0.53
     vrst
    -0.52
     dégâts
    -0.51
     émotions
    -0.51
     sociaux
    -0.50
     Tulane
    -0.50
    POSITIVE LOGITS
     BrowserModule
    0.68
     дописавши
    0.66
    ThroughAttribute
    0.65
    ModelSerializer
    0.63
     désolés
    0.62
    marshaller
    0.61
    сылкі
    0.60
     transfieras
    0.60
     мәкал
    0.59
     CommonModule
    0.58
    Act Density 0.517%

    No Known Activations