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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time and events occurring after specific periods

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time elapsed or duration following events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uci
    -0.78
    =-=-=-=-=-=-=-=-
    -0.76
    nce
    -0.73
    ac
    -0.72
    cin
    -0.71
    uv
    -0.71
    aez
    -0.71
    ctive
    -0.71
    ãĤ¤ãĥĪ
    -0.70
    ace
    -0.70
    POSITIVE LOGITS
     completing
    0.97
     completion
    0.91
     quitting
    0.82
     encountering
    0.82
     graduation
    0.82
     arriving
    0.81
     graduating
    0.81
     announcing
    0.80
     retiring
    0.79
     receipt
    0.79
    Act Density 0.049%

    No Known Activations