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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names that contain the substring 'Kat'

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Kat" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffff
    -0.86
    CLASSIFIED
    -0.82
    uploads
    -0.76
    LEASE
    -0.71
    interstitial
    -0.70
    lict
    -0.69
    GBT
    -0.69
     contraceptives
    -0.69
     confir
    -0.67
     fielded
    -0.65
    POSITIVE LOGITS
    anas
    1.13
    usha
    1.01
     Kat
    1.01
    kat
    0.97
    rina
    0.97
    apesh
    0.89
    Kat
    0.88
    chens
    0.87
    chen
    0.87
    oshi
    0.86
    Act Density 0.016%

    No Known Activations