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

    Neuronpedia

    INDEX
    Explanations

    references to the performance and reception of a specific TV series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ...
    -0.27
     ..."
    -0.19
     "...
    -0.19
     ...↵
    -0.17
     âĢ¦
    -0.17
     ...)
    -0.17
     ...↵↵
    -0.16
     "
    -0.16
     ..."↵
    -0.16
    Âĵ
    -0.16
    POSITIVE LOGITS
     ABS
    0.26
     UA
    0.23
     abs
    0.22
     Abs
    0.21
    ABS
    0.20
    UA
    0.18
     Kap
    0.18
     ‘
    0.17
    abs
    0.17
    (abs
    0.17
    Act Density 0.005%

    No Known Activations