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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical data or references to time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.00
     cauſe
    -0.99
     Efq
    -0.96
     ―――――
    -0.95
     ſtate
    -0.95
    ✨:
    -0.93
     Anſ
    -0.92
     Reſ
    -0.92
     ISNI
    -0.92
     perſon
    -0.91
    POSITIVE LOGITS
    0
    0.76
     years
    0.70
     year
    0.68
     twenty
    0.64
    5
    0.56
    year
    0.55
     
    0.55
    십
    0.55
     Year
    0.55
     five
    0.55
    Act Density 0.168%

    No Known Activations