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

    Neuronpedia

    INDEX
    Explanations

    references to specific brands and trademarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     assembly
    -0.16
     callable
    -0.15
    سÙĪ
    -0.15
    ÑĭÑĪ
    -0.15
    assembly
    -0.14
     Nationwide
    -0.14
     flesh
    -0.14
    ukt
    -0.14
     assemblies
    -0.14
     hor
    -0.13
    POSITIVE LOGITS
     Dow
    0.29
     BAS
    0.25
     pet
    0.23
     feed
    0.22
     Du
    0.21
    Du
    0.21
     Feed
    0.20
     sty
    0.20
     Vinyl
    0.20
     chemicals
    0.20
    Act Density 0.062%

    No Known Activations