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

    Neuronpedia

    INDEX
    Explanations

    negative data attributes and related elements in a dataset context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    data-label and data-color attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pouvoit
    -0.65
     pleaſure
    -0.64
     houſe
    -0.61
     auroit
    -0.60
     feroit
    -0.58
     anún
    -0.57
    ambién
    -0.57
     faſt
    -0.56
     Schluß
    -0.55
     ſtand
    -0.55
    POSITIVE LOGITS
     MonoBehaviour
    0.49
    ↵↵
    0.48
    ↵
    0.48
     data
    0.47
      
    0.46
    WebElementEntity
    0.46
    $_['
    0.46
    principalColumn
    0.46
    /******/
    0.45
     elegans
    0.44
    Act Density 0.011%

    No Known Activations