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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibold
    -0.15
    EDIA
    -0.15
    yst
    -0.14
    _gettime
    -0.14
    esk
    -0.14
    cin
    -0.14
    imm
    -0.14
     cin
    -0.14
    ivity
    -0.14
    159
    -0.14
    POSITIVE LOGITS
    heck
    0.17
    RefCount
    0.15
    Concrete
    0.15
    Purpose
    0.15
    оÑıн
    0.14
    ivor
    0.14
    "';
    0.14
    _done
    0.14
    ?}",
    0.14
    erville
    0.14
    Act Density 0.035%

    No Known Activations