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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to hardware and software

    oai_token-act-pair · gpt-3.5-turbo

    references to hardware and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neut
    -0.75
     satire
    -0.69
     poop
    -0.68
     trans
    -0.68
     cens
    -0.65
    enta
    -0.63
     tamp
    -0.63
     pacing
    -0.62
     plains
    -0.62
     hindsight
    -0.62
    POSITIVE LOGITS
     Hardware
    2.19
    Hardware
    1.44
     Carlo
    1.34
     Barber
    1.10
    supported
    1.10
    boxing
    1.08
     Firm
    1.07
     assumes
    1.04
    Afee
    0.98
    Beer
    0.90
    Act Density 0.079%

    No Known Activations