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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases indicating remaining duration or deadlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Composite
    -0.16
     Composite
    -0.16
    ostel
    -0.15
    317
    -0.14
    åĿĢ
    -0.14
    hest
    -0.14
    905
    -0.14
     ag
    -0.14
     shade
    -0.14
     Stam
    -0.14
    POSITIVE LOGITS
     till
    0.40
     until
    0.37
     Until
    0.33
    until
    0.32
    Until
    0.30
     Till
    0.27
     til
    0.27
    _until
    0.26
     remaining
    0.23
     jusqu
    0.23
    Act Density 0.058%

    No Known Activations