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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "debut" and related phrases indicating new beginnings or first appearances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     m
    -0.52
     y
    -0.49
     c
    -0.47
     k
    -0.46
     v
    -0.45
     p
    -0.45
     ves
    -0.44
     change
    -0.43
     l
    -0.42
     
    -0.42
    POSITIVE LOGITS
     Roskov
    1.18
     Monfieur
    1.15
     Majefty
    1.12
     pleaſure
    1.11
     houſe
    1.09
     Jefus
    1.08
     itſelf
    1.05
     myſelf
    1.05
     uſed
    1.05
     debut
    1.04
    Act Density 0.154%

    No Known Activations