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

    Neuronpedia

    INDEX
    Explanations

    references to popular culture and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unknownFields
    -0.52
    
    -0.50
    ✨:
    -0.50
    ydd
    -0.48
     gesprochen
    -0.47
    этому
    -0.44
    midler
    -0.42
    cress
    -0.42
    OuterClass
    -0.41
     mergeFrom
    -0.41
    POSITIVE LOGITS
     Seinfeld
    0.81
     Jurassic
    0.79
     Simpsons
    0.75
     Shrek
    0.73
     Spon
    0.73
     المعيارى
    0.73
     SpongeBob
    0.72
     Schindler
    0.70
     Avatar
    0.70
     Titanic
    0.70
    Act Density 0.412%

    No Known Activations