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

    Neuronpedia

    INDEX
    Explanations

    references to collaborative projects and initiatives across various domains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     desvan
    -0.33
    detectChanges
    -0.32
     infierno
    -0.32
    福利
    -0.31
     sourire
    -0.30
     MUSEUM
    -0.30
     الرياضيه
    -0.30
    ertale
    -0.29
     âgé
    -0.29
     tebal
    -0.29
    POSITIVE LOGITS
     Task
    1.33
     task
    1.30
    Task
    1.12
     Working
    1.05
    task
    1.02
     TASK
    1.02
     steering
    1.02
     Steering
    1.00
     working
    0.97
     initiative
    0.93
    Act Density 0.590%

    No Known Activations