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

    Neuronpedia

    INDEX
    Explanations

    numerical values and sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Бли
    -0.68
     Bue
    -0.65
     control
    -0.64
    dza
    -0.63
    istic
    -0.62
    forma
    -0.62
    vatel
    -0.61
    bule
    -0.61
    گذ
    -0.60
     Тол
    -0.60
    POSITIVE LOGITS
    9
    1.84
     NINE
    1.40
     Ninth
    1.30
    nine
    1.28
     ninth
    1.21
    ninth
    1.21
     Nine
    1.20
    ۹
    1.15
     nine
    1.14
     nueve
    1.14
    Act Density 0.753%

    No Known Activations