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

    Neuronpedia

    INDEX
    Explanations

    time-related events or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time sequences or events occurring soon after a particular point

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acles
    -0.76
    aez
    -0.74
    kept
    -0.73
    enberg
    -0.72
    atically
    -0.72
    oS
    -0.71
     unfocusedRange
    -0.70
    utenberg
    -0.69
    owed
    -0.68
    oret
    -0.67
    POSITIVE LOGITS
    noon
    0.92
     midnight
    0.82
     quitting
    0.79
     noon
    0.77
    aneously
    0.77
     encountering
    0.75
    imester
    0.73
     arriving
    0.73
     completion
    0.72
     completing
    0.72
    Act Density 0.037%

    No Known Activations