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

    Neuronpedia

    INDEX
    Explanations

    references to logos and branding

    oai_token-act-pair · gpt-3.5-turbo

    references to branding and logos

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     throughput
    -0.77
    flows
    -0.77
    alyses
    -0.75
    alysis
    -0.75
    prison
    -0.74
    romy
    -0.73
    intensive
    -0.72
    wage
    -0.72
    lethal
    -0.71
    pressure
    -0.71
    POSITIVE LOGITS
     initials
    1.46
     moniker
    1.46
     trademark
    1.43
     naming
    1.42
     nickname
    1.41
     logo
    1.31
     trademarks
    1.30
     logos
    1.30
     name
    1.30
     names
    1.29
    Act Density 0.853%

    No Known Activations