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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the timing of events, specifically looking for instances of "anytime soon" or "soon"

    oai_token-act-pair · gpt-3.5-turbo

    references to time-related phrases indicating something will happen shortly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     brim
    -0.72
    severe
    -0.66
    gebra
    -0.66
    pel
    -0.66
    BIP
    -0.65
    acus
    -0.64
    ativity
    -0.64
    cipline
    -0.63
    milo
    -0.62
    tein
    -0.61
    POSITIVE LOGITS
     thereafter
    1.01
    aneously
    0.98
     afterwards
    0.80
     enough
    0.77
    2019
    0.72
     afterward
    0.71
     soon
    0.67
     after
    0.65
     extinct
    0.65
     ago
    0.65
    Act Density 0.026%

    No Known Activations