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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions or measurements

    oai_token-act-pair · gpt-3.5-turbo

    temporal expressions indicating a passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lict
    -0.74
    inite
    -0.66
    roid
    -0.65
    olis
    -0.63
    roth
    -0.62
     elimination
    -0.61
    aze
    -0.60
    atche
    -0.60
    atic
    -0.60
    licts
    -0.59
    POSITIVE LOGITS
     ago
    1.33
     Ago
    1.13
    long
    0.81
     overdue
    0.79
    ãĥ¼ãĥĨ
    0.75
    oldown
    0.75
     apiece
    0.72
     ahead
    0.71
     earthqu
    0.71
     hence
    0.71
    Act Density 0.087%

    No Known Activations