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

    Neuronpedia

    INDEX
    Explanations

    time-related words and durations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    emale
    -0.82
    Reviewer
    -0.80
    acus
    -0.77
    liction
    -0.73
    acted
    -0.73
    obook
    -0.68
    ocaly
    -0.68
    nels
    -0.67
    type
    -0.64
    duct
    -0.64
    POSITIVE LOGITS
     ago
    1.45
     Ago
    1.41
     elapsed
    1.00
     later
    0.97
     Later
    0.89
     Ahead
    0.88
     shy
    0.87
     ahead
    0.85
     transpired
    0.77
     Away
    0.77
    Act Density 0.067%

    No Known Activations