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

    Neuronpedia

    INDEX
    Explanations

    references to traffic conditions and related keywords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essen
    -0.19
    endas
    -0.16
    issa
    -0.16
    ares
    -0.15
    iffe
    -0.15
     風
    -0.15
    мовÑĸÑĢ
    -0.15
    ahan
    -0.15
    ish
    -0.14
    quences
    -0.14
    POSITIVE LOGITS
     jams
    0.23
     lights
    0.19
     flow
    0.19
     Lights
    0.19
    -flow
    0.18
     Lah
    0.17
     patterns
    0.17
     jam
    0.16
    -light
    0.16
     pattern
    0.15
    Act Density 0.011%

    No Known Activations