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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of "closure" or "being closed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]--;
    -0.75
     Brandt
    -0.62
    🏼
    -0.57
    velle
    -0.55
     HasFactory
    -0.54
    TypedDataSet
    -0.53
    antism
    -0.52
    󠁿
    -0.51
     Starlight
    -0.51
     TÉCN
    -0.50
    POSITIVE LOGITS
     doors
    0.97
     Closed
    0.96
     closed
    0.95
     shut
    0.94
     closes
    0.93
    Closed
    0.92
    閉
    0.91
     shuts
    0.88
    闭
    0.88
     Shut
    0.88
    Act Density 0.082%

    No Known Activations