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

    Neuronpedia

    INDEX
    Explanations

    structured data formats and library dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opa
    -0.17
    arry
    -0.17
    idd
    -0.16
    errat
    -0.15
    dds
    -0.15
     Hust
    -0.15
    agit
    -0.14
    olics
    -0.14
    /autoload
    -0.14
    ewis
    -0.14
    POSITIVE LOGITS
     Discipline
    0.15
     SHIFT
    0.14
     Shift
    0.14
    0.14
     Academ
    0.14
     discipline
    0.14
    berapa
    0.14
     Ministry
    0.14
     Mog
    0.13
    .freeze
    0.13
    Act Density 0.010%

    No Known Activations