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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to control and authority over situations or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     infra
    -0.35
     InputDecoration
    -0.31
     practice
    -0.30
     fellow
    -0.30
     fac
    -0.29
     notable
    -0.29
     ανά
    -0.29
    fsch
    -0.28
     additional
    -0.28
    res
    -0.27
    POSITIVE LOGITS
     control
    1.12
     controllable
    1.09
     contrôler
    1.09
    controlling
    1.05
     Control
    1.05
    Controlling
    1.05
    control
    1.04
     CONTROL
    1.03
     Kontrolle
    1.03
     controlling
    1.02
    Act Density 0.412%

    No Known Activations