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

    Neuronpedia

    INDEX
    Explanations

    references to events or topics to be further addressed or explored later

    oai_token-act-pair · gpt-3.5-turbo

    references to future events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pwr
    -0.84
    washing
    -0.72
    HY
    -0.71
    eping
    -0.69
    cking
    -0.68
    Ped
    -0.66
    Ble
    -0.66
    bal
    -0.65
    tick
    -0.65
    mad
    -0.64
    POSITIVE LOGITS
     generations
    0.97
     iterations
    0.87
     versions
    0.87
    noon
    0.84
     batches
    0.79
     phases
    0.79
     stages
    0.79
     installments
    0.78
    iations
    0.75
    ally
    0.73
    Act Density 0.033%

    No Known Activations