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

    Neuronpedia

    INDEX
    Explanations

    patterns or structures in structured data, such as code or configurations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     &___
    -0.57
    vol
    -0.54
     promising
    -0.53
     partners
    -0.52
     long
    -0.52
    like
    -0.50
     like
    -0.50
    허
    -0.48
    RunWith
    -0.48
    The
    -0.47
    POSITIVE LOGITS
    存于互联网档案馆
    0.80
     Lightboxes
    0.79
    principalColumn
    0.75
     Baillargeon
    0.75
     Penh
    0.73
    Datuak
    0.68
     cherchés
    0.65
    MLLoader
    0.65
    tagHelperRunner
    0.64
    Rè
    0.62
    Act Density 0.062%

    No Known Activations