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

    Neuronpedia

    INDEX
    Explanations

    locations or physical places

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icer
    -0.77
    quel
    -0.72
    xtap
    -0.69
    archives
    -0.69
    CHAT
    -0.68
    onder
    -0.66
    irst
    -0.65
    asted
    -0.64
    ernand
    -0.64
    uster
    -0.63
    POSITIVE LOGITS
    bos
    1.20
    holders
    1.15
    holder
    1.03
     where
    1.00
    abouts
    0.90
    upon
    0.90
     else
    0.84
     holder
    0.84
     frequ
    0.82
    where
    0.78
    Act Density 0.056%

    No Known Activations