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

    Neuronpedia

    INDEX
    Explanations

    terms related to interruptions and disruptions in processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     soát
    -0.63
    DeleteBehavior
    -0.59
    CppMethod
    -0.57
    tencent
    -0.56
    resizingMask
    -0.56
    ulipas
    -0.56
    ndes
    -0.55
    findpost
    -0.55
    ollectionView
    -0.53
    árny
    -0.53
    POSITIVE LOGITS
     distractions
    1.47
     interruptions
    1.46
     disruptions
    1.33
     interrupts
    1.33
     distraction
    1.33
     disruption
    1.32
     interrupted
    1.30
     interruption
    1.29
     interrupting
    1.23
     interrupt
    1.19
    Act Density 0.376%

    No Known Activations