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

    Neuronpedia

    INDEX
    Explanations

    websites or links

    oai_token-act-pair · gpt-3.5-turbo

    references to URLs or web addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oral
    -0.74
     Scouting
    -0.72
     brackets
    -0.70
     graffiti
    -0.70
     intercept
    -0.69
     whims
    -0.69
     voting
    -0.68
     sneak
    -0.66
     expansion
    -0.64
     summ
    -0.64
    POSITIVE LOGITS
    edu
    1.82
    org
    1.66
    gov
    1.48
    nih
    1.47
    nl
    1.43
    jp
    1.43
    kr
    1.37
    com
    1.36
    net
    1.36
    uni
    1.29
    Act Density 0.039%

    No Known Activations