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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -1.53
     Jefus
    -1.49
     Efq
    -1.39
     houſe
    -1.38
     itſelf
    -1.37
     Anſ
    -1.37
     Monfieur
    -1.37
     purpoſe
    -1.36
    ſelf
    -1.35
     Theſe
    -1.34
    POSITIVE LOGITS
    S
    0.72
     S
    0.71
    s
    0.71
       
    0.65
     I
    0.64
      
    0.64
     E
    0.62
     am
    0.62
     P
    0.61
     C
    0.61
    Act Density 0.310%

    No Known Activations