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

    Neuronpedia

    INDEX
    Explanations

    references to effort, work, and labor-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adaptiveStyles
    -1.19
    yntaxException
    -1.15
     propOrder
    -1.10
     Rossetti
    -1.10
    Datuak
    -1.07
    StoryboardSegue
    -1.05
    Portale
    -1.04
     Ceci
    -1.01
    Viki
    -1.00
     Aquila
    -0.98
    POSITIVE LOGITS
     HARD
    1.18
     hard
    1.09
     Hard
    1.09
    HARD
    1.07
    Hard
    1.02
    hard
    0.98
     Hardin
    0.95
     Harding
    0.88
    硬
    0.86
    -
    0.85
    Act Density 0.036%

    No Known Activations