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

    Neuronpedia

    INDEX
    Explanations

    numerical values or quantifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     control
    -0.74
     Бли
    -0.70
    aktery
    -0.67
    istic
    -0.64
    ので
    -0.64
    Бли
    -0.63
    ===============
    -0.63
    bule
    -0.62
    dza
    -0.62
    deli
    -0.62
    POSITIVE LOGITS
    9
    1.90
     NINE
    1.25
     Ninth
    1.20
    nine
    1.14
     Nine
    1.09
    8
    1.09
    ۹
    1.08
     ninth
    1.07
     ninety
    1.06
     NIN
    1.05
    Act Density 0.622%

    No Known Activations