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

    Neuronpedia

    INDEX
    Explanations

    sequences and relationships of events within a narrative or process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hivat
    -0.58
     perpetuity
    -0.57
    enderror
    -0.56
    endmodule
    -0.55
     asymmetry
    -0.53
     estimés
    -0.50
     OFDb
    -0.49
    BaseAdapter
    -0.48
     uttry
    -0.48
     sustainably
    -0.47
    POSITIVE LOGITS
     steps
    1.26
     events
    1.25
     sequence
    1.11
    events
    1.02
     Events
    1.00
     Steps
    0.98
     EVENTS
    0.97
    steps
    0.97
    sequence
    0.96
     actions
    0.93
    Act Density 0.416%

    No Known Activations