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

    Neuronpedia

    INDEX
    Explanations

    references to a specific place starting with the letters "Ur"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or entity related to Urbana

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sins
    -0.76
    iculty
    -0.75
    washer
    -0.75
    女
    -0.75
     Dickinson
    -0.68
    sylvania
    -0.66
     Misc
    -0.66
    ãģ¦
    -0.66
    æ³
    -0.65
     Scarlet
    -0.64
    POSITIVE LOGITS
    gent
    1.13
    gencies
    1.00
    du
    0.92
    gery
    0.91
    pose
    0.90
    ulence
    0.86
    pee
    0.86
    gur
    0.86
    vey
    0.84
    seless
    0.84
    Act Density 0.022%

    No Known Activations