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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong recommendations or endorsements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elry
    -0.52
    ριά
    -0.50
    וכר
    -0.49
    ած
    -0.49
    toggler
    -0.48
    calientes
    -0.48
     dibat
    -0.48
    StructEnd
    -0.48
    ătă
    -0.48
     Yaw
    -0.47
    POSITIVE LOGITS
     recommend
    1.80
     recommended
    1.55
     recommends
    1.50
     recommendation
    1.50
     Recommend
    1.46
     recommending
    1.40
    recommended
    1.39
    recommend
    1.39
     Recommended
    1.36
     RECOMMEND
    1.36
    Act Density 0.115%

    No Known Activations