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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a future event that will happen soon

    oai_token-act-pair · gpt-3.5-turbo

    the word "Soon" indicating upcoming events or future occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atively
    -0.67
    ocker
    -0.66
    effic
    -0.66
     curated
    -0.65
    inf
    -0.64
    acus
    -0.64
    pat
    -0.63
     fault
    -0.62
     flu
    -0.61
    avid
    -0.59
    POSITIVE LOGITS
     Soon
    1.17
    Soon
    0.99
     thereafter
    0.89
    Later
    0.83
    theless
    0.79
    mares
    0.77
     afterward
    0.73
     Meter
    0.73
    ishers
    0.73
    nown
    0.72
    Act Density 0.007%

    No Known Activations