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

    Neuronpedia

    INDEX
    Explanations

    references to streets or street-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uta
    -0.17
    unce
    -0.17
    hq
    -0.15
    ayas
    -0.15
    ylland
    -0.15
    pcf
    -0.15
    elim
    -0.14
    ÏĦÎŃλε
    -0.14
    desk
    -0.14
    olly
    -0.14
    POSITIVE LOGITS
    lights
    0.19
     cred
    0.18
    ién
    0.17
    ways
    0.16
    ÙĪØŃ
    0.16
    asics
    0.16
    cars
    0.16
    wise
    0.15
    åĨµ
    0.15
     Soph
    0.15
    Act Density 0.040%

    No Known Activations