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

    Neuronpedia

    INDEX
    Explanations

    references to discussions or situations related to public policy and regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vod
    -0.16
     Means
    -0.16
     abbreviated
    -0.16
     bergen
    -0.15
    397
    -0.15
     swath
    -0.15
     populace
    -0.15
    567
    -0.15
    perature
    -0.15
    457
    -0.14
    POSITIVE LOGITS
     quite
    0.24
     somehow
    0.23
     serie
    0.22
    .o
    0.21
    kind
    0.19
     evident
    0.19
    quite
    0.18
     alike
    0.18
     kind
    0.18
     big
    0.17
    Act Density 0.315%

    No Known Activations