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

    Neuronpedia

    INDEX
    Explanations

    phrases related to processes, procedures, or steps involved in a particular action

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to processes or methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osponsors
    -0.86
    arling
    -0.73
     allies
    -0.70
    izens
    -0.69
    ervatives
    -0.69
    brand
    -0.69
    olls
    -0.69
    issan
    -0.68
    bel
    -0.67
    ows
    -0.67
    POSITIVE LOGITS
     process
    0.93
     procedure
    0.91
     processes
    0.89
     chore
    0.87
     procedures
    0.86
     motions
    0.85
     diligence
    0.84
     permitting
    0.82
     Process
    0.79
     ACTIONS
    0.78
    Act Density 0.563%

    No Known Activations