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

    Neuronpedia

    INDEX
    Explanations

    references to metrics or measurements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VERTISEMENT
    -0.86
     Audiodateien
    -0.86
     تضيفلها
    -0.85
    Manbalar
    -0.83
    dafx
    -0.82
     ujednoznacz
    -0.82
    ADRID
    -0.81
     transférez
    -0.80
    `,
    -0.78
    stdafx
    -0.78
    POSITIVE LOGITS
     insulation
    0.98
    metrics
    0.86
     Insulation
    0.74
    uf
    0.67
    selector
    0.63
     metrics
    0.60
    Metrics
    0.60
     Metrics
    0.60
     compartments
    0.58
    Selector
    0.58
    Act Density 0.077%

    No Known Activations