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

    Neuronpedia

    INDEX
    Explanations

    words related to entities, particularly names and titles in a legal or official context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     So
    -0.55
    intellij
    -0.53
     …
    -0.53
    ˈ
    -0.52
    eneuve
    -0.51
     Just
    -0.50
     “
    -0.50
    izielle
    -0.50
    ല
    -0.49
     Mount
    -0.49
    POSITIVE LOGITS
     kasarigan
    0.67
     épu
    0.62
     piú
    0.61
     Majefty
    0.60
     Jefus
    0.59
     Circum
    0.58
     Reſ
    0.58
     tunik
    0.58
     caviar
    0.57
     Cæsar
    0.56
    Act Density 0.048%

    No Known Activations