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

    Neuronpedia

    INDEX
    Explanations

    references to events or actions that occurred a specific number of years "after" a past event

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a passage of time or events occurring after a specific point

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uci
    -0.76
    ace
    -0.72
    atic
    -0.71
    ctive
    -0.70
    atically
    -0.70
    owed
    -0.68
    cin
    -0.68
    ac
    -0.67
    cue
    -0.67
    chio
    -0.66
    POSITIVE LOGITS
     completing
    0.93
     encountering
    0.86
     completion
    0.83
     arriving
    0.81
     rejecting
    0.78
     receipt
    0.78
     quitting
    0.77
     acquiring
    0.77
     launching
    0.75
     receiving
    0.74
    Act Density 0.042%

    No Known Activations