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

    Neuronpedia

    INDEX
    Explanations

    references to traffic and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahan
    -0.17
    ares
    -0.16
    issa
    -0.15
    essen
    -0.15
    endas
    -0.15
    arih
    -0.15
    arend
    -0.15
    iring
    -0.15
    oo
    -0.15
    ish
    -0.15
    POSITIVE LOGITS
     jams
    0.20
     flow
    0.18
    -flow
    0.16
     Lah
    0.16
     patterns
    0.16
     lights
    0.15
     Lights
    0.15
     Patterns
    0.15
     Flow
    0.15
     density
    0.14
    Act Density 0.012%

    No Known Activations