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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships between entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Référence
    -0.59
    poort
    -0.42
     Kom
    -0.42
     Leaks
    -0.42
     tricks
    -0.40
     treu
    -0.40
     Bend
    -0.39
    FEL
    -0.39
    alama
    -0.39
     dri
    -0.39
    POSITIVE LOGITS
    同士
    1.19
     zweier
    1.16
     two
    1.14
     between
    1.14
     між
    1.11
     pairs
    1.09
     между
    1.07
    between
    1.05
    two
    1.04
     BETWEEN
    1.00
    Act Density 0.889%

    No Known Activations