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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social, political, and personal interactions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and grammatical structures within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erver
    -0.90
    729
    -0.87
    uliffe
    -0.84
    ongyang
    -0.84
    ŃĶ
    -0.83
     rabbit
    -0.82
    okane
    -0.80
     rabbits
    -0.80
    adelphia
    -0.79
    oultry
    -0.79
    POSITIVE LOGITS
     Sand
    1.29
    Sand
    1.08
     Sard
    1.05
     Sed
    1.00
     Alexand
    1.00
     Piet
    0.99
     Sands
    0.98
     Ast
    0.97
     Spect
    0.97
     Cent
    0.96
    Act Density 0.493%

    No Known Activations