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

    Neuronpedia

    INDEX
    Explanations

    references to experiences or moments of enjoyment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quæ
    -0.62
     raiſ
    -0.62
     Jefus
    -0.62
     ſch
    -0.60
     ſche
    -0.59
     himſelf
    -0.58
    stdc
    -0.58
     ainfi
    -0.58
     ejus
    -0.58
     AppColors
    -0.57
    POSITIVE LOGITS
     wandered
    0.88
     stroll
    0.86
     strolled
    0.83
     wander
    0.78
     strolling
    0.77
     wanders
    0.74
     explored
    0.71
     wandering
    0.70
     exploring
    0.70
     sightseeing
    0.68
    Act Density 0.207%

    No Known Activations