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

    Neuronpedia

    INDEX
    Explanations

    time-related adverbs or phrases such as "shortly"

    oai_token-act-pair · gpt-3.5-turbo

    the word "shortly" and its variations in temporal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elson
    -0.74
    GA
    -0.67
    CHQ
    -0.66
    ammy
    -0.65
    lace
    -0.65
    elsen
    -0.64
    ortium
    -0.63
    initely
    -0.62
    smanship
    -0.62
    imm
    -0.61
    POSITIVE LOGITS
     thereafter
    1.21
    mares
    0.95
    aneously
    0.81
     afterward
    0.79
     afterwards
    0.79
     followed
    0.77
    entimes
    0.77
    teenth
    0.74
     aft
    0.73
     preced
    0.71
    Act Density 0.022%

    No Known Activations