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

    Neuronpedia

    INDEX
    Explanations

    specific references to individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "who."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MER
    -0.74
    BACK
    -0.70
     Glob
    -0.64
    emin
    -0.63
    urb
    -0.62
    alam
    -0.62
     rinse
    -0.62
    eme
    -0.62
    OOL
    -0.61
    namese
    -0.61
    POSITIVE LOGITS
    soever
    1.16
     else
    1.05
    abouts
    0.87
     exactly
    0.84
    afort
    0.83
     owns
    0.83
     cares
    0.82
     cared
    0.81
     redes
    0.77
     owes
    0.75
    Act Density 0.041%

    No Known Activations