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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.82
     houſe
    -0.77
     Efq
    -0.77
     Sega
    -0.74
     hierogly
    -0.73
     Shaksp
    -0.71
     Majefty
    -0.70
     Josephus
    -0.69
     himſelf
    -0.69
     pleaſure
    -0.69
    POSITIVE LOGITS
     the
    1.10
    "])
    0.90
     it
    0.83
     there
    0.77
    "]
    0.74
    )";
    0.71
    "]);
    0.70
    "):
    0.69
     ")
    0.69
    )")
    0.69
    Act Density 0.342%

    No Known Activations