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

    Neuronpedia

    INDEX
    Explanations

    numerical measurements and comparisons

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating age and duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dickinson
    -0.84
     Arabian
    -0.79
     saga
    -0.73
     hack
    -0.68
     Paradox
    -0.68
     pause
    -0.67
     chain
    -0.67
     table
    -0.66
     Kafka
    -0.65
     Doom
    -0.65
    POSITIVE LOGITS
    eyed
    1.06
    years
    1.06
    year
    0.99
    degree
    0.99
    sized
    0.97
    enough
    0.97
    bodied
    0.95
    thirds
    0.95
    based
    0.94
    pointers
    0.94
    Act Density 0.204%

    No Known Activations