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

    Neuronpedia

    INDEX
    Explanations

    specific blocks on city streets or neighborhoods

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations or blocks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Thrust
    -0.65
    emic
    -0.60
    brates
    -0.60
    egal
    -0.58
     Stress
    -0.58
     Akin
    -0.58
     Lect
    -0.58
     Balls
    -0.58
    ISM
    -0.57
     Answers
    -0.57
    POSITIVE LOGITS
    busters
    0.98
    aded
    0.94
    buster
    0.89
    ages
    0.86
    ades
    0.85
    yards
    0.81
    folio
    0.79
    jer
    0.78
     block
    0.77
    quote
    0.75
    Act Density 0.012%

    No Known Activations