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

    Neuronpedia

    INDEX
    Explanations

    proper nouns associated with names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĪاÙĦ
    -0.18
    peare
    -0.17
     Heads
    -0.16
    adelphia
    -0.14
     stopwatch
    -0.14
    traits
    -0.14
     Tod
    -0.14
    lia
    -0.14
    ptions
    -0.13
    itive
    -0.13
    POSITIVE LOGITS
    iley
    0.23
     ba
    0.18
    lear
    0.18
    .debugLine
    0.17
    FTA
    0.16
    ically
    0.16
    üml
    0.16
    ground
    0.15
    ixo
    0.15
    ashboard
    0.15
    Act Density 0.010%

    No Known Activations