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

    Neuronpedia

    INDEX
    Explanations

    statistical significance and p-values in experimental results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    errupted
    -0.16
    .builders
    -0.16
    oker
    -0.15
    ><![
    -0.14
    çĽijåIJ¬é¡µéĿ¢
    -0.14
    ozor
    -0.14
    eldorf
    -0.14
     Torch
    -0.13
     ucwords
    -0.13
    avern
    -0.13
    POSITIVE LOGITS
    =
    0.29
     =
    0.27
     values
    0.23
     value
    0.23
    <
    0.21
    -value
    0.20
    -values
    0.20
     <
    0.19
     range
    0.18
    =.
    0.18
    Act Density 0.009%

    No Known Activations