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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases or sequences

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the phrase "day after" or variations of "after" indicating a sequence or recurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ducks
    -0.66
    enegger
    -0.65
    oak
    -0.62
     Flavoring
    -0.62
    cia
    -0.60
    :[
    -0.59
    OWS
    -0.57
    ?:
    -0.56
    iband
    -0.56
     Stain
    -0.55
    POSITIVE LOGITS
    oard
    0.69
    wards
    0.61
    ims
    0.60
     hemisphere
    0.60
     province
    0.58
     continent
    0.58
    ctors
    0.58
     diplomat
    0.57
    etheless
    0.57
     region
    0.56
    Act Density 0.123%

    No Known Activations