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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of brevity or shortened duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĵ
    -2.45
    Ħ
    -2.30
    »
    -2.27
    §
    -2.10
    ķ
    -2.05
    ij
    -1.98
    Ľ
    -1.96
    Ĩ
    -1.94
    ¨
    -1.90
    ¿
    -1.87
    POSITIVE LOGITS
     than
    2.85
    Than
    2.77
    than
    2.57
     Than
    2.26
    dated
    1.71
     ($\
    1.70
     times
    1.60
    wise
    1.55
     generations
    1.52
    acting
    1.50
    Act Density 0.012%

    No Known Activations