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

    Neuronpedia

    INDEX
    Explanations

    references to authors and their works, particularly highlighting the latest achievements or characteristics of the authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppo
    -0.15
    getContext
    -0.15
     neutral
    -0.15
    ecided
    -0.15
    iterate
    -0.14
     Neutral
    -0.14
    ernote
    -0.14
    edor
    -0.14
     znam
    -0.14
     Edward
    -0.14
    POSITIVE LOGITS
    azo
    0.16
    ulla
    0.16
    arbeit
    0.14
    uhl
    0.14
     debut
    0.14
    irler
    0.14
    ãĥ«ãĤ¯
    0.14
    panic
    0.14
    yre
    0.13
    folios
    0.13
    Act Density 0.071%

    No Known Activations