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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future plans or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ltk
    -0.21
    sons
    -0.16
    adium
    -0.16
     Harness
    -0.15
    agna
    -0.15
     Rating
    -0.14
     underlying
    -0.14
    lint
    -0.14
     Julius
    -0.14
     Timing
    -0.14
    POSITIVE LOGITS
     rabbit
    0.27
     aisle
    0.25
     Rabbit
    0.21
     chute
    0.21
     drain
    0.21
    rabbit
    0.20
    river
    0.20
     hall
    0.20
     corridor
    0.19
     alley
    0.19
    Act Density 0.029%

    No Known Activations