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

    Neuronpedia

    INDEX
    Explanations

    references to formal agreements and contracts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ECTS
    -0.62
    unked
    -0.59
     Ivo
    -0.58
    extrême
    -0.54
    unhofer
    -0.54
     helst
    -0.54
     GONNA
    -0.54
    Tup
    -0.53
     Poplar
    -0.53
    maxLines
    -0.53
    POSITIVE LOGITS
     agreements
    0.88
     Agreement
    0.88
     agreement
    0.87
     Agreements
    0.82
    apimachinery
    0.79
    ImageContext
    0.78
    ItemBackground
    0.75
    arium
    0.75
    agreement
    0.74
     distanciation
    0.74
    Act Density 0.012%

    No Known Activations