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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "celebrate" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.32
    ſelf
    -1.28
     myſelf
    -1.28
     Jefus
    -1.25
     ſche
    -1.25
     purpoſe
    -1.20
     whoſe
    -1.19
     Diſ
    -1.19
    ſelves
    -1.18
     Monfieur
    -1.15
    POSITIVE LOGITS
     celebrate
    0.66
     
    0.60
    ,
    0.58
     celebrating
    0.57
     (
    0.51
     deserves
    0.49
     ki
    0.49
     is
    0.48
     celebrates
    0.48
    celebrate
    0.48
    Act Density 0.121%

    No Known Activations