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

    Neuronpedia

    INDEX
    Explanations

    key-value pairs and configurations in data or code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pem
    -0.47
     Hati
    -0.46
     berta
    -0.46
    kita
    -0.46
    parti
    -0.45
     né
    -0.45
    dades
    -0.44
    IBLES
    -0.44
    ardless
    -0.44
    URS
    -0.43
    POSITIVE LOGITS
    GEBURTSDATUM
    1.04
    GenerationType
    0.89
     ویکی‌پدیا
    0.85
     continúas
    0.75
    Билгалдахарш
    0.75
    NUMX
    0.71
     TestBed
    0.71
     TimeUnit
    0.71
     noqa
    0.71
    +#+
    0.70
    Act Density 5.503%

    No Known Activations