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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "but" in conjunction with contrasting statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Backing
    -0.15
    rippling
    -0.15
    arring
    -0.14
    ãĤĮãģ°
    -0.14
     Vital
    -0.14
     sparking
    -0.14
    oling
    -0.14
    evi
    -0.14
    ноÑģи
    -0.13
     Filtering
    -0.13
    POSITIVE LOGITS
     becoming
    0.27
     spending
    0.23
     being
    0.20
     having
    0.19
     making
    0.19
     resulting
    0.18
     eventually
    0.18
     finding
    0.17
     leaving
    0.17
     remaining
    0.17
    Act Density 0.340%

    No Known Activations