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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating extremes or significant limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uisse
    -0.17
    ulings
    -0.16
     chung
    -0.15
     lã
    -0.15
    andering
    -0.15
    ialis
    -0.15
    bbe
    -0.15
    igan
    -0.14
     thêm
    -0.14
    ulumi
    -0.14
    POSITIVE LOGITS
     mere
    0.28
     reach
    0.25
     bounds
    0.25
     beyond
    0.24
     Beyond
    0.24
     merely
    0.23
     boundaries
    0.23
    Beyond
    0.23
     repro
    0.23
     compare
    0.23
    Act Density 0.032%

    No Known Activations