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

    Neuronpedia

    INDEX
    Explanations

    instances of emotional expressions or reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (“
    -0.16
     Zum
    -0.15
    ï¼ļ↵↵
    -0.15
    inois
    -0.15
     “[
    -0.15
    ÂĦ
    -0.14
    elles
    -0.14
    :\"
    -0.14
    ling
    -0.14
    ï¼ļ↵
    -0.13
    POSITIVE LOGITS
     Adds
    0.17
    ickets
    0.16
    ")(
    0.15
    "And
    0.15
    ince
    0.14
    ency
    0.14
     Added
    0.14
    âĸį
    0.14
    "But
    0.14
    .IsNullOr
    0.14
    Act Density 0.077%

    No Known Activations