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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating excessive amounts or intensities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swire
    -0.76
    SharedCtor
    -0.68
    énario
    -0.67
    })));
    -0.67
    tableFuture
    -0.66
     trajets
    -0.66
    +#+
    -0.64
    ]){
    -0.63
     {*}
    -0.61
    XmlRootElement
    -0.59
    POSITIVE LOGITS
     Too
    1.30
    Too
    1.28
     too
    1.28
     TOO
    1.18
    too
    1.11
    TOO
    0.97
    troppo
    0.93
     demasi
    0.91
     demasiado
    0.90
     слишком
    0.89
    Act Density 0.110%

    No Known Activations