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

    Neuronpedia

    INDEX
    Explanations

    the occurrences of the word "word" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.06
     photolibrary
    -0.98
     poffe
    -0.97
     himſelf
    -0.94
    "]];
    -0.94
    %]
    -0.94
    "]]
    -0.94
     Monfieur
    -0.93
     pleaſure
    -0.93
    NUMX
    -0.89
    POSITIVE LOGITS
     word
    2.13
     words
    2.04
     Word
    2.02
    Word
    1.96
     WORD
    1.91
     Words
    1.89
    word
    1.86
    Words
    1.71
     WORDS
    1.70
    words
    1.62
    Act Density 0.032%

    No Known Activations