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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "or" and related conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /or
    -0.21
    ìĿ´íĦ°
    -0.17
    ey
    -0.17
    رÙĪس
    -0.16
    flix
    -0.15
    arella
    -0.15
    291
    -0.14
    rogen
    -0.14
    .mapbox
    -0.14
    ValuePair
    -0.14
    POSITIVE LOGITS
     perhaps
    0.20
    chest
    0.20
    ourke
    0.19
     maybe
    0.19
    dn
    0.18
    perhaps
    0.18
    maybe
    0.17
    uds
    0.17
    phan
    0.17
    Maybe
    0.17
    Act Density 0.057%

    No Known Activations