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

    Neuronpedia

    INDEX
    Explanations

    content related to emotional and social connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -1.28
    ↵↵
    -1.11
    ↵↵↵
    -0.58
    ]--;
    -0.54
    ;/
    -0.53
    =$?
    -0.49
     '%'
    -0.49
    ("}");
    -0.48
     '_'
    -0.48
    ↵↵↵↵
    -0.47
    POSITIVE LOGITS
    <h3>
    2.02
    <h2>
    2.00
    <blockquote>
    1.96
    <h4>
    1.83
    <h1>
    1.75
    <strong>
    1.65
    <h5>
    1.60
    <h6>
    1.56
    <em>
    1.38
    <b>
    1.37
    Act Density 1.746%

    No Known Activations