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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "virtue" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     giri
    -0.61
     bact
    -0.56
     suk
    -0.56
     Lapp
    -0.55
     spé
    -0.55
     adop
    -0.53
    écu
    -0.53
    orghini
    -0.53
     confirmer
    -0.52
     Thad
    -0.51
    POSITIVE LOGITS
    seamnă
    0.71
    richTextPanel
    0.68
     Chwiliwch
    0.68
     désolés
    0.67
    middot
    0.64
    Rhestr
    0.63
    ]--;
    0.62
    jspx
    0.60
    "")
    0.59
    ValueStyle
    0.59
    Act Density 3.234%

    No Known Activations