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

    Neuronpedia

    INDEX
    Explanations

    mentions of streets, roads, or specific locations

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "calle" (street) in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rador
    -1.00
     Seym
    -0.95
    raints
    -0.92
    ĸļ
    -0.90
    yrinth
    -0.87
    iaries
    -0.87
    raint
    -0.85
    inelli
    -0.84
    dyl
    -0.83
    âĶģ
    -0.80
    POSITIVE LOGITS
    ttes
    1.28
    lla
    1.17
    agues
    1.16
    isure
    0.98
    phant
    0.92
    conom
    0.89
    utenant
    0.89
    ffect
    0.87
    IGH
    0.85
    tto
    0.83
    Act Density 0.032%

    No Known Activations