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

    Neuronpedia

    INDEX
    Explanations

    formal structures and guidelines within architecture-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nouve
    -0.20
     French
    -0.18
     french
    -0.18
     célib
    -0.17
     Orleans
    -0.16
     franç
    -0.16
     Rou
    -0.15
     parten
    -0.15
    iset
    -0.15
     punt
    -0.15
    POSITIVE LOGITS
    nal
    0.20
     pour
    0.19
    qui
    0.18
    trait
    0.17
    ça
    0.17
    (nombre
    0.17
    .nombre
    0.16
    LIKELY
    0.16
    osph
    0.15
    rique
    0.15
    Act Density 0.745%

    No Known Activations