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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their related formatting or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsContent
    -0.53
    Stell
    -0.49
     hull
    -0.47
    awan
    -0.47
    rawValue
    -0.47
     télévis
    -0.46
     Willoughby
    -0.46
     Toby
    -0.46
    uerta
    -0.45
    Pol
    -0.45
    POSITIVE LOGITS
    9
    1.15
     Nine
    1.08
     nine
    1.07
     NINE
    0.96
     Ninth
    0.95
    Nine
    0.94
     ninth
    0.93
     nueve
    0.90
    nine
    0.85
    九
    0.84
    Act Density 0.523%

    No Known Activations