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

    Neuronpedia

    INDEX
    Explanations

    references to combinations of elements or factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oreille
    -0.46
     autorité
    -0.45
    naissance
    -0.45
     saiba
    -0.44
     Scaffold
    -0.44
    GRANTED
    -0.43
    zieć
    -0.42
    FileNotFound
    -0.42
     escucha
    -0.42
    estatus
    -0.42
    POSITIVE LOGITS
     combination
    1.97
     Combination
    1.80
    Combination
    1.71
    combination
    1.71
     combinations
    1.70
     COMBIN
    1.68
     combine
    1.62
     combined
    1.58
     combina
    1.58
     Kombination
    1.57
    Act Density 0.188%

    No Known Activations