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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "shut."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.61
    msgSender
    -0.48
     suiv
    -0.44
     extré
    -0.38
     ddelweddau
    -0.38
    🏻
    -0.37
     Skin
    -0.37
     Ly
    -0.37
     gäller
    -0.35
    îtra
    -0.35
    POSITIVE LOGITS
     shut
    0.89
    shut
    0.82
    preference
    0.78
     shuts
    0.73
     preference
    0.71
     Shut
    0.71
    Preference
    0.69
    Shut
    0.68
     Preference
    0.67
     shutting
    0.66
    Act Density 0.086%

    No Known Activations