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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to statistics and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     --
    -0.19
     (...
    -0.17
     ANY
    -0.16
     ---
    -0.16
    icult
    -0.15
     ...
    -0.15
     [...]
    -0.15
     (...)
    -0.14
     [--
    -0.14
    ă
    -0.14
    POSITIVE LOGITS
     till
    0.23
     firstly
    0.21
     named
    0.18
     apart
    0.18
     moreover
    0.18
     famous
    0.18
     ‘
    0.17
     whereas
    0.17
    named
    0.17
     Firstly
    0.17
    Act Density 0.042%

    No Known Activations