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

    Neuronpedia

    INDEX
    Explanations

    names of people, specifically actors, characters, and related public figures in the context of entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
      (
    -0.55
    Amicalement
    -0.53
    ülle
    -0.52
     artificiales
    -0.49
    Encyklopedia
    -0.49
    utilisons
    -0.48
     signora
    -0.48
     homemaker
    -0.48
    老者
    -0.48
     száll
    -0.48
    POSITIVE LOGITS
    ukone
    0.68
     <=",
    0.64
    AutoScaleMode
    0.61
    StoryboardSegue
    0.60
    rungsseite
    0.59
    EClass
    0.58
    athus
    0.58
    encodeWith
    0.55
    BufferException
    0.55
     svin
    0.55
    Act Density 0.414%

    No Known Activations