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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "referral" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eny
    -0.16
    edd
    -0.15
    idal
    -0.14
    ConverterFactory
    -0.14
     supply
    -0.14
    ahir
    -0.14
    iren
    -0.14
    ete
    -0.13
     Mature
    -0.13
    izons
    -0.13
    POSITIVE LOGITS
    amage
    0.17
    ailable
    0.16
    erez
    0.15
    orners
    0.15
    rana
    0.14
    UBE
    0.14
     wakeup
    0.14
    ATAR
    0.14
    _cum
    0.14
    867
    0.13
    Act Density 0.002%

    No Known Activations