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

    Neuronpedia

    INDEX
    Explanations

    terms related to gates and exit points in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hummel
    -0.86
     socc
    -0.79
     FURN
    -0.69
     Guinness
    -0.68
     Montserrat
    -0.67
     Mahmoud
    -0.66
     Broom
    -0.66
    шан
    -0.65
     Soll
    -0.65
    ChildScrollView
    -0.65
    POSITIVE LOGITS
     gates
    1.16
     gate
    1.12
     Gates
    1.02
     Gate
    0.96
    Gate
    0.90
     gated
    0.88
    Gates
    0.86
     lane
    0.86
     GATE
    0.83
    igate
    0.80
    Act Density 0.100%

    No Known Activations