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

    Neuronpedia

    INDEX
    Explanations

    special characters or symbols that may indicate formatting or metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [...]
    -0.33
     .....
    -0.29
     ....
    -0.28
     ...
    -0.27
     ......
    -0.27
     [...
    -0.27
     (...)
    -0.26
     ..."↵
    -0.24
     ...↵
    -0.24
     ..........
    -0.24
    POSITIVE LOGITS
     Gen
    0.24
    ,âĢ¦
    0.24
    âĢ¦"
    0.23
    .âĢ¦
    0.23
    âĢ¦↵↵
    0.23
    âĢ¦↵
    0.23
    âĢ¦↵↵↵
    0.22
    ,âĢ¦↵↵
    0.21
    âĢ¦
    0.21
    Gen
    0.19
    Act Density 0.003%

    No Known Activations