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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns or sequences

    oai_token-act-pair · gpt-3.5-turbo

    characters or elements from a non-Latin script or language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leilan
    -0.72
     Solitaire
    -0.71
     Ceres
    -0.68
     Franch
    -0.62
     Yankee
    -0.62
    ividual
    -0.61
    DragonMagazine
    -0.61
     FRI
    -0.61
     Myster
    -0.61
     CMS
    -0.60
    POSITIVE LOGITS
    ²
    1.57
    ´
    1.53
    Į
    1.51
    Ń
    1.50
    ¸
    1.47
    ·
    1.46
    ¦
    1.46
    º
    1.46
    £
    1.42
    °
    1.42
    Act Density 0.019%

    No Known Activations