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

    Neuronpedia

    INDEX
    Explanations

    commands to consider something or pay attention to something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that encourage the reader to take action or look at specific information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     advertised
    -0.66
     constitu
    -0.65
    tions
    -0.63
     accompanies
    -0.62
    ambo
    -0.61
    ansas
    -0.59
     wart
    -0.59
     dissatisf
    -0.56
    idding
    -0.56
    Develop
    -0.56
    POSITIVE LOGITS
    aways
    1.31
     advantage
    1.19
     heed
    1.09
    away
    1.02
     aback
    0.98
     away
    0.91
     care
    0.90
     precautions
    0.86
     liberties
    0.86
     Advantage
    0.84
    Act Density 0.069%

    No Known Activations