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

    Neuronpedia

    INDEX
    Explanations

    references to dates and time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dics
    -0.58
    gson
    -0.57
    ModelForm
    -0.57
    Pyx
    -0.55
    mannian
    -0.53
    ος
    -0.53
    CharField
    -0.53
    Noun
    -0.52
    shiro
    -0.52
    mphony
    -0.52
    POSITIVE LOGITS
     date
    2.47
     dates
    2.27
     Dates
    2.01
     Date
    2.00
     DATE
    1.92
     dated
    1.91
     dating
    1.88
     DATES
    1.84
    dating
    1.81
    dates
    1.80
    Act Density 0.067%

    No Known Activations