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

    Neuronpedia

    INDEX
    Explanations

    phrases and actions related to instructions and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    595
    -0.15
    ampus
    -0.15
     cham
    -0.14
    fleet
    -0.14
    erton
    -0.14
     DISPATCH
    -0.14
    ifest
    -0.14
     nex
    -0.14
    ensis
    -0.14
     stump
    -0.14
    POSITIVE LOGITS
    uron
    0.15
    stown
    0.14
     misd
    0.14
    aggi
    0.13
     Morton
    0.13
    íĮĮ
    0.13
    .Unsupported
    0.13
    .ManyToMany
    0.13
    è¡
    0.13
     Stefan
    0.13
    Act Density 0.271%

    No Known Activations