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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions or comparisons related to computer processors

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications and performance metrics related to computer hardware

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    archives
    -0.70
    azine
    -0.69
     formation
    -0.68
    oleon
    -0.67
     disband
    -0.66
     puppet
    -0.66
    letters
    -0.66
     Volunteer
    -0.64
    iatus
    -0.64
    prison
    -0.63
    POSITIVE LOGITS
     outper
    1.45
     superior
    1.20
     overcl
    1.14
     surpass
    1.13
     comparable
    1.10
     performance
    1.09
     benchmarks
    1.08
     speeds
    1.05
     benchmark
    1.05
     1080
    1.03
    Act Density 0.506%

    No Known Activations