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

    Neuronpedia

    INDEX
    Explanations

    words related to future events or plans

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "tomorrow."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ordes
    -0.84
    rosse
    -0.76
    inventoryQuantity
    -0.76
    leeve
    -0.75
    este
    -0.75
    hips
    -0.74
    ocal
    -0.70
    lee
    -0.70
    ochet
    -0.69
    artney
    -0.69
    POSITIVE LOGITS
     morning
    1.34
     afternoon
    1.17
     night
    1.06
     evening
    1.04
     tomorrow
    0.97
     NIGHT
    0.96
     mornings
    0.94
     nights
    0.92
    morrow
    0.92
    morning
    0.87
    Act Density 0.005%

    No Known Activations