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

    Neuronpedia

    INDEX
    Explanations

    references to specific areas of focus or responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     réfugiés
    -0.61
    rungsseite
    -0.58
     passagers
    -0.56
     juges
    -0.55
     touristes
    -0.55
    ள்
    -0.55
     fiscales
    -0.54
     journalistes
    -0.53
    twimg
    -0.53
     salva
    -0.53
    POSITIVE LOGITS
     areas
    2.06
    Areas
    1.71
     Areas
    1.70
     places
    1.66
    areas
    1.64
     AREAS
    1.58
     Places
    1.33
    places
    1.32
     PLACES
    1.27
    Places
    1.25
    Act Density 0.134%

    No Known Activations