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

    Neuronpedia

    INDEX
    Explanations

    terms related to different fields or areas of expertise

    oai_token-act-pair · gpt-3.5-turbo

    specialized jargon or terms associated with various fields or industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernels
    -0.94
    lations
    -0.88
    awatts
    -0.87
    lees
    -0.86
    comings
    -0.85
    ilts
    -0.84
    tops
    -0.84
    scenes
    -0.83
    steps
    -0.82
    votes
    -0.81
    POSITIVE LOGITS
     standpoint
    1.15
     technician
    1.04
     counselor
    1.04
     staffer
    1.01
     outlet
    0.98
     worker
    0.98
     researcher
    0.97
     agent
    0.96
     provider
    0.95
     colleague
    0.95
    Act Density 0.331%

    No Known Activations