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

    Neuronpedia

    INDEX
    Explanations

    phrases related to controversy or conflict

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     biograf
    -0.76
     utop
    -0.74
     hek
    -0.69
     ideolog
    -0.67
     boks
    -0.66
     makro
    -0.66
     kandid
    -0.66
     republi
    -0.65
     katastro
    -0.65
     vola
    -0.64
    POSITIVE LOGITS
     spin
    1.29
    spin
    1.19
     spinning
    1.15
     spun
    1.13
     Spin
    1.11
     spins
    1.11
    Spin
    1.05
     spinners
    1.02
     spinner
    0.99
    spinning
    0.94
    Act Density 0.124%

    No Known Activations