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

    Neuronpedia

    INDEX
    Explanations

    prominent names of authors and titles of artistic works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     .↵↵
    -0.23
    ï¼īãĢĤ↵↵
    -0.21
    .*;↵↵
    -0.21
    /.↵↵
    -0.19
     ).↵↵
    -0.19
    .↵↵
    -0.19
    ãĢĤãĢį↵↵
    -0.19
     [âĢ¦]↵↵
    -0.19
     ,↵↵
    -0.18
    ..↵↵
    -0.18
    POSITIVE LOGITS
    ↵
    0.79
    à¥Ģ↵
    0.51
    ा↵
    0.51
    à¥ĩ↵
    0.48
    à¥ĩà¤Ĥ↵
    0.48
    )↵
    0.47
    "↵
    0.45
    '↵
    0.43
    ]↵
    0.42
    ี↵
    0.42
    Act Density 2.380%

    No Known Activations