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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating dependence or reliance on something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Prestige
    -0.35
     prestige
    -0.34
     spice
    -0.34
    Ɓ
    -0.34
     gift
    -0.34
    sstelle
    -0.32
    InputModule
    -0.32
     Outlet
    -0.31
     drin
    -0.31
    </table>
    -0.31
    POSITIVE LOGITS
     relies
    1.31
     rely
    1.30
     depends
    1.24
     depend
    1.23
     relying
    1.20
     Rely
    1.14
     depended
    1.09
    depends
    1.05
    Depend
    1.05
    depend
    1.05
    Act Density 0.441%

    No Known Activations