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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "is" and various forms of "to be" verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.61
     myſelf
    -1.57
     Majefty
    -1.55
     Chriftian
    -1.50
     Jefus
    -1.48
     himſelf
    -1.41
     themſelves
    -1.40
     raiſ
    -1.40
     fubject
    -1.39
     pleaſure
    -1.37
    POSITIVE LOGITS
     a
    0.95
     its
    0.90
     is
    0.86
     the
    0.84
     
    0.82
    s
    0.80
     not
    0.79
     The
    0.74
    m
    0.71
     an
    0.69
    Act Density 0.130%

    No Known Activations