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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to legal and medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </h3>
    -1.70
    ↵↵↵
    -1.44
    </s>
    -1.25
    </td>
    -1.16
    </h1>
    -0.95
    \'
    -0.91
    ｣
    -0.89
    </h5>
    -0.88
    ')[
    -0.87
    )',
    -0.84
    POSITIVE LOGITS
    ”
    1.52
    .”
    1.49
    ?”
    1.36
    ...”
    1.35
    ”“
    1.32
    ”]
    1.29
    !”
    1.28
    ”;
    1.26
    ”.
    1.25
    )”
    1.23
    Act Density 0.901%

    No Known Activations