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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating importance or value

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    baugh
    -0.74
    thumbnails
    -0.72
    oslov
    -0.70
    gdala
    -0.67
    rete
    -0.67
    viol
    -0.64
    ally
    -0.62
     Gazette
    -0.61
     Graphics
    -0.60
     Cats
    -0.58
    POSITIVE LOGITS
     noting
    0.95
     remembering
    0.95
     consideration
    0.93
     mentioning
    0.90
     careful
    0.79
     precaution
    0.78
    velength
    0.75
     considering
    0.75
    ogh
    0.75
     investing
    0.74
    Act Density 0.012%

    No Known Activations