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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases expressing duration or continuity

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing duration or the extent of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gall
    -0.68
     Caption
    -0.64
     assemblies
    -0.64
    ering
    -0.63
     respect
    -0.57
     envy
    -0.57
     Kirin
    -0.56
    erers
    -0.56
     mockery
    -0.55
     FT
    -0.54
    POSITIVE LOGITS
     long
    1.32
     LONG
    1.19
     awhile
    1.18
    long
    1.14
    short
    0.99
     eternity
    0.98
     longer
    0.93
    years
    0.92
     longest
    0.91
    Long
    0.90
    Act Density 0.055%

    No Known Activations