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

    Neuronpedia

    INDEX
    Explanations

    names and titles related to specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    specific names or terms related to individuals and their contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     toget
    -0.64
     envy
    -0.61
     unequ
    -0.61
     increment
    -0.60
    manship
    -0.60
     profiling
    -0.60
     lapse
    -0.57
    icles
    -0.56
    ALLY
    -0.56
     tails
    -0.55
    POSITIVE LOGITS
    tein
    0.83
    eele
    0.79
    arde
    0.74
    pta
    0.74
    schild
    0.73
    uve
    0.72
     Meadows
    0.72
    eve
    0.72
    enegger
    0.71
    arson
    0.70
    Act Density 0.227%

    No Known Activations