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

    Neuronpedia

    INDEX
    Explanations

    concepts related to existential questions and spiritual themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <sup>
    -0.67
     ${
    -0.53
    <sub>
    -0.46
     ${\
    -0.44
     sum
    -0.41
    łą
    -0.40
    　「
    -0.40
     $\
    -0.39
    /${
    -0.39
     cum
    -0.39
    POSITIVE LOGITS
    ,...
    1.40
     […]
    1.38
    […]
    1.32
    [...]
    1.30
     [...]
    1.22
    ,…
    1.22
    :...
    1.18
    .…
    1.16
    ...
    1.11
    !...
    1.08
    Act Density 1.303%

    No Known Activations