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

    Neuronpedia

    INDEX
    Explanations

    occurrences of numbers and their context within statistics or scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Howe
    -0.17
    ergus
    -0.15
     pitchers
    -0.15
    jedn
    -0.15
    еви
    -0.14
    eos
    -0.14
     faiz
    -0.14
    icao
    -0.14
    ettel
    -0.14
    peak
    -0.14
    POSITIVE LOGITS
    ivet
    0.16
    oref
    0.15
    329
    0.15
    ampo
    0.15
     orient
    0.15
     assert
    0.15
     explos
    0.15
     assist
    0.14
    ored
    0.14
     Assist
    0.14
    Act Density 0.108%

    No Known Activations