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

    Neuronpedia

    INDEX
    Explanations

    concepts related to creativity and customization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ${
    -0.81
    <sup>
    -0.79
    <sub>
    -0.77
    $^{-
    -0.68
     $=
    -0.66
     $-\
    -0.65
     $<
    -0.65
     ($\
    -0.65
     $=\
    -0.64
    <u>
    -0.62
    POSITIVE LOGITS
     […]
    3.17
     …
    2.77
    […]
    2.65
     [...]
    2.51
     ...
    2.49
    ,…
    2.46
    ,...
    2.38
    …
    2.35
    .…
    2.32
    [...]
    2.29
    Act Density 7.290%

    No Known Activations