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

    Neuronpedia

    INDEX
    Explanations

    words related to specific tasks or actions like software operations

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles associated with various processes and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    metics
    -0.73
    arag
    -0.67
    minecraft
    -0.66
    addons
    -0.65
    olen
    -0.60
    awan
    -0.60
    ikk
    -0.60
    ika
    -0.60
     Barron
    -0.57
     Aure
    -0.57
    POSITIVE LOGITS
     occurs
    0.98
     initiation
    0.88
    æĸ¹
    0.84
     occurring
    0.83
     occurred
    0.83
     procedure
    0.83
     performed
    0.77
     spree
    0.75
     occur
    0.74
     technique
    0.74
    Act Density 0.413%

    No Known Activations