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

    Neuronpedia

    INDEX
    Explanations

    numerical data and related statistical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    traveling
    -0.61
    Bibliograf
    -0.60
    cour
    -0.60
     McClure
    -0.58
     ROUT
    -0.57
     Bertram
    -0.56
     rése
    -0.56
    truction
    -0.56
    odule
    -0.56
     Ziegler
    -0.55
    POSITIVE LOGITS
    5
    1.41
    ５
    0.84
     cinquième
    0.83
    five
    0.79
     Five
    0.79
     vijf
    0.78
    Five
    0.77
     cinco
    0.77
     five
    0.75
    ۵
    0.75
    Act Density 0.907%

    No Known Activations