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

    Neuronpedia

    INDEX
    Explanations

    capital letter acronyms or abbreviations ending with 'I'

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "MI," likely indicating a focus on Michigan or related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ding
    -0.75
    sword
    -0.73
    modules
    -0.72
    lift
    -0.70
    comes
    -0.70
    lich
    -0.70
    Merit
    -0.70
    holder
    -0.69
     Ragnarok
    -0.69
    size
    -0.68
    POSITIVE LOGITS
    AMI
    1.10
    HAEL
    1.03
    MI
    1.03
    PS
    0.99
    ovember
    0.96
    uppet
    0.96
    FU
    0.85
    OSH
    0.82
     MI
    0.80
    XT
    0.77
    Act Density 0.006%

    No Known Activations