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

    Neuronpedia

    INDEX
    Explanations

    conjunctions or phrases suggesting contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osaic
    -0.18
    ines
    -0.17
    mage
    -0.17
    iyas
    -0.14
    ises
    -0.14
    uries
    -0.13
     Becker
    -0.13
    204
    -0.13
    afs
    -0.13
     Colon
    -0.13
    POSITIVE LOGITS
    icare
    0.15
    uml
    0.15
    ipeg
    0.15
    ovit
    0.15
     neither
    0.15
    ãģ®æĸ¹
    0.14
    ENCHMARK
    0.14
     nowhere
    0.14
    ToEnd
    0.14
    ç¬
    0.14
    Act Density 0.093%

    No Known Activations