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

    Neuronpedia

    INDEX
    Explanations

    actions or movements related to attention and interaction between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Breakdown
    -0.33
     serons
    -0.32
     proche
    -0.30
     plancher
    -0.29
     kø
    -0.29
     provoquer
    -0.28
     pit
    -0.28
     akad
    -0.28
     proches
    -0.27
    저
    -0.27
    POSITIVE LOGITS
    errHandler
    0.75
    styleType
    0.58
     estekak
    0.58
    ➟
    0.56
     AssemblyCompany
    0.56
     Turning
    0.55
     viewType
    0.54
    ScopeManager
    0.54
     glances
    0.53
    SharedCtor
    0.53
    Act Density 0.152%

    No Known Activations