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

    Neuronpedia

    INDEX
    Explanations

    words related to addition or enhancement

    oai_token-act-pair · gpt-3.5-turbo

    passive voice constructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.75
    =-=-=-=-
    -0.69
    é¾įå¥ij士
    -0.68
    ovember
    -0.67
     Ends
    -0.67
     Lessons
    -0.67
    zan
    -0.66
    anto
    -0.66
     Legislation
    -0.66
     Ago
    -0.65
    POSITIVE LOGITS
     bluff
    0.73
     gradually
    0.71
     mute
    0.70
     unmist
    0.69
     safely
    0.67
     itself
    0.66
     upd
    0.66
    nt
    0.66
     oxid
    0.65
     automatically
    0.65
    Act Density 0.910%

    No Known Activations