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

    Neuronpedia

    INDEX
    Explanations

    references to roads and roadways

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uer
    -0.17
    dorf
    -0.16
    wit
    -0.15
    ment
    -0.15
    uada
    -0.15
    erialize
    -0.15
    sek
    -0.15
    quia
    -0.15
    imoto
    -0.14
    Æł
    -0.14
    POSITIVE LOGITS
    ways
    0.23
    stead
    0.19
    оÑĤÑĢеб
    0.18
    ritel
    0.17
    side
    0.17
    ONO
    0.17
    spin
    0.17
    athan
    0.16
    trip
    0.16
    WAYS
    0.16
    Act Density 0.030%

    No Known Activations