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

    Neuronpedia

    INDEX
    Explanations

    We're sorry, we made a mistake in understanding the neuron's behavior. Based on the activations provided, the neuron is primarily looking for terms related to the Google company

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Google."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mble
    -0.94
    alid
    -0.77
    ivari
    -0.77
    quez
    -0.74
    swing
    -0.73
    iotic
    -0.73
    rone
    -0.72
    odic
    -0.71
    philis
    -0.70
    iosis
    -0.69
    POSITIVE LOGITS
    plex
    0.97
     Maps
    0.90
     Doodle
    0.90
     Scholar
    0.85
     Fiber
    0.85
     Glass
    0.83
     Chrome
    0.83
    Maps
    0.77
     Ventures
    0.76
     Nexus
    0.76
    Act Density 0.025%

    No Known Activations