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

    Neuronpedia

    INDEX
    Explanations

    quotes from official statements

    oai_token-act-pair · gpt-3.5-turbo

    statements or quotes from official sources or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     distur
    -0.78
     underestimated
    -0.74
    cffffcc
    -0.69
     haun
    -0.68
    âĶĢâĶĢâĶĢâĶĢ
    -0.68
     stim
    -0.68
     impro
    -0.68
     snipers
    -0.67
     halluc
    -0.67
    reality
    -0.66
    POSITIVE LOGITS
     statement
    1.07
    Statement
    0.95
     Statement
    0.89
     emailed
    0.82
     stated
    0.80
     wrote
    0.80
     disclaimer
    0.80
     announcing
    0.78
    wrote
    0.78
     Pledge
    0.77
    Act Density 0.208%

    No Known Activations