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

    Neuronpedia

    INDEX
    Explanations

    items or actions related to technology and appliances

    oai_token-act-pair · gpt-3.5-turbo

    specific technology and internet-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.90
     Eag
    -0.72
     McDonnell
    -0.70
    witz
    -0.70
     Turks
    -0.67
    hig
    -0.67
     Ramos
    -0.67
     Kinn
    -0.64
    baugh
    -0.64
     Democr
    -0.64
    POSITIVE LOGITS
     selves
    1.06
     mates
    0.85
     spouse
    0.80
     buddies
    0.78
     counterparts
    0.77
     wardrobe
    0.74
    mates
    0.73
     microbiome
    0.73
     wisely
    0.72
     cursor
    0.71
    Act Density 0.362%

    No Known Activations