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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize the concept of "state of the art"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "
    -1.10
     “
    -0.96
    '],'
    -0.78
     '
    -0.70
     is
    -0.70
     I
    -0.69
     
    -0.68
    ']").
    -0.67
     +
    -0.65
     ”
    -0.64
    POSITIVE LOGITS
     Efq
    1.20
     Cæsar
    1.12
     itſelf
    1.11
     Shakspeare
    1.06
     Diſ
    1.02
     Monfieur
    1.01
     myſelf
    1.01
     houſe
    1.00
     Reſ
    0.99
     pleaſure
    0.98
    Act Density 0.096%

    No Known Activations