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

    Neuronpedia

    INDEX
    Explanations

    words related to references, citations, or documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ciudadana
    -0.55
     Stirn
    -0.53
     Zwiebel
    -0.52
     firmas
    -0.46
     Türen
    -0.45
     denuncias
    -0.45
    ikirkan
    -0.44
     sisa
    -0.43
     ruido
    -0.43
     regalías
    -0.43
    POSITIVE LOGITS
    ISupport
    0.57
    useNewUrlParser
    0.55
    Datuak
    0.54
     OnTrigger
    0.51
    WriteTagHelper
    0.49
    Kanpo
    0.48
    ension
    0.47
    iſten
    0.47
    ₂,
    0.47
     ſche
    0.46
    Act Density 0.044%

    No Known Activations