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

    Neuronpedia

    INDEX
    Explanations

    instances of specific administrative or regulatory terms and keywords related to policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     clone
    -0.16
     Fare
    -0.16
    eken
    -0.15
    clone
    -0.15
    esel
    -0.14
     Clone
    -0.14
    leneck
    -0.14
     mouth
    -0.14
    176
    -0.14
     Implementation
    -0.13
    POSITIVE LOGITS
    ocab
    0.15
    ansas
    0.15
    _DECLS
    0.14
    taÅŁ
    0.14
    interp
    0.14
    ropdown
    0.14
    asto
    0.14
    ãĤ¤ãĤº
    0.14
    :focus
    0.14
     FetchType
    0.14
    Act Density 0.001%

    No Known Activations