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

    Neuronpedia

    INDEX
    Explanations

    dates and time-related terms such as months and years

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocker
    -0.64
     lately
    -0.62
    ector
    -0.61
    egal
    -0.59
     recent
    -0.59
     expression
    -0.58
    leeve
    -0.58
    iked
    -0.58
    olated
    -0.58
     recently
    -0.57
    POSITIVE LOGITS
     hopefully
    0.95
    morrow
    0.88
     will
    0.85
     tomorrow
    0.84
    will
    0.81
    'll
    0.79
     onwards
    0.77
     SHALL
    0.75
    soon
    0.74
    izons
    0.74
    Act Density 0.149%

    No Known Activations