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

    Neuronpedia

    INDEX
    Explanations

    references to specific numerical or categorical data typically associated with coding and annotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aste
    -0.17
    MAS
    -0.16
    tik
    -0.15
    alsy
    -0.14
    ifton
    -0.14
    -visible
    -0.14
    fic
    -0.14
    ASTE
    -0.14
    uren
    -0.14
    oth
    -0.14
    POSITIVE LOGITS
    seo
    0.15
    rawl
    0.15
     Balls
    0.15
    alat
    0.15
    даÑĤ
    0.14
    emax
    0.14
    deaux
    0.14
    鹿
    0.13
    dere
    0.13
    guess
    0.13
    Act Density 0.010%

    No Known Activations