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

    Neuronpedia

    INDEX
    Explanations

    instances of unusual formatting or characters that may indicate special emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſei
    -1.10
    LLocation
    -0.96
     ſind
    -0.95
     ſch
    -0.94
    ésultats
    -0.94
     ſeine
    -0.93
     ſta
    -0.93
    iſen
    -0.92
     indígen
    -0.92
     ſein
    -0.91
    POSITIVE LOGITS
    1.42
    ↵↵↵↵
    0.59
    ↵↵↵↵↵↵
    0.56
    ↵↵↵↵↵↵↵
    0.53
    ↵↵↵↵↵
    0.52
    ↵↵↵↵↵↵↵↵↵
    0.48
    <h5>
    0.47
    ↵↵↵↵↵↵↵↵↵↵
    0.46
    ↵↵↵↵↵↵↵↵
    0.46
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.44
    Act Density 0.009%

    No Known Activations