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

    Neuronpedia

    INDEX
    Explanations

    phrases introducing contrasting ideas or situations

    oai_token-act-pair · gpt-3.5-turbo

    coordinating conjunctions and phrases that indicate comparison or contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AMI
    -0.70
    iors
    -0.64
     COVER
    -0.63
    idi
    -0.62
    bsp
    -0.61
    aley
    -0.61
    enge
    -0.60
    ury
    -0.60
    auri
    -0.60
    AGES
    -0.60
    POSITIVE LOGITS
    hedral
    0.72
     moder
    0.68
    olson
    0.68
     rightly
    0.67
    Ü
    0.64
     sensing
    0.63
    ensibly
    0.61
     bearer
    0.59
    cussion
    0.59
     Luck
    0.59
    Act Density 0.244%

    No Known Activations