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

    Neuronpedia

    INDEX
    Explanations

    terms related to closing or filling gaps and closures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RSpec
    -0.65
    endphp
    -0.64
    ContentAsync
    -0.62
     autorytatywna
    -0.60
    Aiheesta
    -0.59
    colhead
    -0.58
     propOrder
    -0.58
     GenerationType
    -0.57
     Guel
    -0.56
    存于互联网档案馆
    -0.56
    POSITIVE LOGITS
     gap
    0.85
     bridging
    0.83
     closing
    0.82
     gaps
    0.79
     Gaps
    0.73
     fill
    0.73
    gap
    0.72
     Closing
    0.72
    closing
    0.72
    Closing
    0.69
    Act Density 0.458%

    No Known Activations