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

    Neuronpedia

    INDEX
    Explanations

    specific details about products, including their features and manufacturing attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acon
    -0.15
     mdi
    -0.14
    compose
    -0.14
    rote
    -0.13
    _DEFINE
    -0.13
    icot
    -0.13
    USB
    -0.13
     twice
    -0.13
    ôn
    -0.13
     pulver
    -0.12
    POSITIVE LOGITS
     production
    0.29
     Production
    0.27
    Production
    0.25
    production
    0.25
     factory
    0.24
     serial
    0.24
    -production
    0.24
     early
    0.23
     Serial
    0.23
     Transitional
    0.22
    Act Density 0.024%

    No Known Activations