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

    Neuronpedia

    INDEX
    Explanations

    references to personal backgrounds or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardi
    -0.14
    [
    -0.14
    ew
    -0.14
    ibel
    -0.14
     thorough
    -0.14
    baz
    -0.14
    ib
    -0.14
    az
    -0.14
    abeth
    -0.14
    pt
    -0.13
    POSITIVE LOGITS
    /background
    0.18
    educt
    0.16
    asser
    0.16
     lad
    0.16
    ijkstra
    0.15
    475
    0.14
     filmer
    0.14
    åĩºçīĪ社
    0.14
    ÙĥÙĬÙĬÙģ
    0.14
    kus
    0.14
    Act Density 0.013%

    No Known Activations