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

    Neuronpedia

    INDEX
    Explanations

    phrases related to limitations or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     specialised
    -0.15
     conven
    -0.15
    tb
    -0.14
    gay
    -0.14
     Clem
    -0.14
    enk
    -0.14
    ekten
    -0.14
    tek
    -0.14
    rray
    -0.13
    ợi
    -0.13
    POSITIVE LOGITS
    erence
    0.17
    vetica
    0.17
    DEX
    0.16
     depletion
    0.15
    tica
    0.15
     Watts
    0.14
    scriptId
    0.14
     пеÑĢеп
    0.14
    enders
    0.14
    olet
    0.14
    Act Density 0.127%

    No Known Activations