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

    Neuronpedia

    INDEX
    Explanations

    words related to visual or auditory perception

    oai_token-act-pair · gpt-3.5-turbo

    actions of seeing or hearing events occurring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Topic
    -0.90
    fact
    -0.80
    Fact
    -0.73
    ignore
    -0.73
    topic
    -0.73
    enthal
    -0.72
    esan
    -0.72
    utical
    -0.72
    necessary
    -0.71
    pdf
    -0.70
    POSITIVE LOGITS
     someone
    1.02
     footsteps
    1.01
     ambul
    0.99
     footprints
    0.99
     headlights
    0.98
     gunfire
    0.95
     gunshots
    0.94
     helicopters
    0.94
     smoke
    0.92
     gunmen
    0.91
    Act Density 0.143%

    No Known Activations