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

    Neuronpedia

    INDEX
    Explanations

    names or usernames of individuals on social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    names and associated entities, particularly focusing on individual people and their roles or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :,
    -0.91
    ");
    -0.83
    "),
    -0.81
    ".[
    -0.81
    .",
    -0.79
    ];
    -0.79
    ],
    -0.77
    '),
    -0.76
     subdiv
    -0.74
     partly
    -0.74
    POSITIVE LOGITS
     (@
    2.40
     ðŁ
    1.55
     âľ
    1.41
    ðŁ
    1.36
     âĺ
    1.26
     ??
    1.21
     ðŁij
    1.20
     âĿ
    1.19
    âĺ
    1.19
    âľ
    1.17
    Act Density 0.111%

    No Known Activations