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

    Neuronpedia

    INDEX
    Explanations

    time-related events or activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ICAN
    -0.68
    elson
    -0.67
    ajo
    -0.67
    neys
    -0.65
     Responsibility
    -0.62
    egal
    -0.62
    acus
    -0.59
    ahime
    -0.59
     freely
    -0.59
    olutely
    -0.58
    POSITIVE LOGITS
     thereafter
    1.48
     afterward
    1.05
     afterwards
    1.04
    aneously
    0.98
    mares
    0.89
    eteenth
    0.87
     aft
    0.83
     followed
    0.82
     ago
    0.80
    aneous
    0.79
    Act Density 0.019%

    No Known Activations