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

    Neuronpedia

    INDEX
    Explanations

    expressions of time and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     years
    -0.15
     summers
    -0.14
     decades
    -0.13
    eras
    -0.13
    POS
    -0.13
    Years
    -0.13
    years
    -0.13
     giá»Ŀ
    -0.13
     buffet
    -0.13
     dab
    -0.13
    POSITIVE LOGITS
     final
    0.18
     finals
    0.17
     work
    0.17
    -final
    0.16
     finish
    0.16
     finishing
    0.16
    tons
    0.16
     finalize
    0.15
     finally
    0.15
    Finish
    0.15
    Act Density 0.361%

    No Known Activations