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

    Neuronpedia

    INDEX
    Explanations

    terms related to academic publication metrics and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strup
    -0.16
    ergus
    -0.15
    bjerg
    -0.15
    або
    -0.14
    ohon
    -0.14
    µľ
    -0.14
    íĻĢ
    -0.14
     Restoration
    -0.14
    phinx
    -0.14
    ajor
    -0.13
    POSITIVE LOGITS
    ette
    0.16
    aan
    0.14
    ster
    0.14
    avl
    0.14
    ettes
    0.14
    aus
    0.14
    esc
    0.13
    iness
    0.13
     democr
    0.13
    .wp
    0.13
    Act Density 0.032%

    No Known Activations