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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and measurements related to products or components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trust
    -0.15
     telling
    -0.14
     authority
    -0.14
     clearly
    -0.14
     truth
    -0.14
     reason
    -0.14
     affirm
    -0.14
    zano
    -0.14
     advocating
    -0.13
     intent
    -0.13
    POSITIVE LOGITS
     exhaust
    0.16
     drain
    0.15
     scoop
    0.15
     Exhaust
    0.14
     isol
    0.14
     pipe
    0.14
     curtain
    0.14
     retaining
    0.14
     stabil
    0.13
     draining
    0.13
    Act Density 2.340%

    No Known Activations