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

    Neuronpedia

    INDEX
    Explanations

    phrases related to effort or difficulty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :✨
    -1.12
     Rossetti
    -1.12
     propOrder
    -1.10
    DockStyle
    -1.07
     <=",
    -1.01
     toluene
    -0.99
    Datuak
    -0.97
    Portale
    -0.97
    ↺
    -0.97
    sidemargin
    -0.96
    POSITIVE LOGITS
     hard
    2.75
     Hard
    2.44
    Hard
    2.39
     HARD
    2.35
    hard
    2.34
    HARD
    2.23
     harder
    1.76
     hardest
    1.67
    硬
    1.59
     harde
    1.52
    Act Density 0.040%

    No Known Activations