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

    Neuronpedia

    INDEX
    Explanations

    specific locations mentioned in the text, particularly highways and roads

    oai_token-act-pair · gpt-3.5-turbo

    specific highway and road numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estamp
    -0.74
    orians
    -0.70
    iques
    -0.70
    onic
    -0.68
     nom
    -0.67
    ¨
    -0.62
     Qi
    -0.59
    aning
    -0.58
     term
    -0.56
    onite
    -0.55
    POSITIVE LOGITS
     Revis
    0.88
     corridor
    0.80
     Corridor
    0.76
     Extension
    0.75
    A
    0.74
    afety
    0.74
    RH
    0.73
    VB
    0.72
    BG
    0.71
    llan
    0.70
    Act Density 0.103%

    No Known Activations