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

    Neuronpedia

    INDEX
    Explanations

    instructions related to turning devices on and off

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anou
    -0.17
     Kore
    -0.15
    jer
    -0.14
    odable
    -0.14
    ucid
    -0.14
     addAction
    -0.14
    chnitt
    -0.14
    lili
    -0.14
    ActivityIndicatorView
    -0.13
    Mount
    -0.13
    POSITIVE LOGITS
     switches
    0.29
     switch
    0.29
     turned
    0.28
     switched
    0.27
    switch
    0.27
     lights
    0.26
    -switch
    0.25
     turn
    0.24
     ON
    0.24
     Turn
    0.24
    Act Density 0.090%

    No Known Activations