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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "word" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.05
     Monfieur
    -0.98
    "]]
    -0.98
    %]
    -0.97
    "]];
    -0.97
     pleaſure
    -0.95
     himſelf
    -0.94
    ."));
    -0.94
     photolibrary
    -0.94
    ]-->
    -0.94
    POSITIVE LOGITS
     words
    1.70
     Words
    1.57
     word
    1.49
     Word
    1.47
    Words
    1.40
     WORDS
    1.39
     WORD
    1.39
    Word
    1.38
    words
    1.31
    word
    1.26
    Act Density 0.072%

    No Known Activations