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

    Neuronpedia

    INDEX
    Explanations

    references to variables and their attributes in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plant
    -0.16
    ister
    -0.15
    arily
    -0.15
    ì°©
    -0.15
     Jersey
    -0.14
    erton
    -0.14
    ISED
    -0.14
    uary
    -0.14
    war
    -0.14
    ams
    -0.14
    POSITIVE LOGITS
    iances
    0.23
    _dump
    0.21
    iants
    0.19
    iously
    0.19
    iations
    0.19
    ieties
    0.18
    argout
    0.17
    nish
    0.16
    .Var
    0.16
    asaki
    0.16
    Act Density 0.075%

    No Known Activations