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

    Neuronpedia

    INDEX
    Explanations

    references to the word "it" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -1.55
     Houſe
    -1.52
     Monfieur
    -1.52
     Majefty
    -1.48
     pleaſure
    -1.48
     Diſ
    -1.39
     Conſ
    -1.38
     ſever
    -1.35
     myſelf
    -1.35
     Efq
    -1.34
    POSITIVE LOGITS
     
    0.91
     is
    0.90
     It
    0.89
     it
    0.85
     "
    0.77
     I
    0.76
     was
    0.75
    '
    0.73
     p
    0.71
     its
    0.68
    Act Density 0.004%

    No Known Activations