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

    Neuronpedia

    INDEX
    Explanations

    references to deception or trickery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gratuites
    -0.17
    ibur
    -0.17
    ãĤ¼
    -0.16
    rne
    -0.15
    iferay
    -0.15
    еÑĢин
    -0.15
    /trunk
    -0.14
    inish
    -0.14
     trusted
    -0.14
    ROW
    -0.14
    POSITIVE LOGITS
    ampoline
    0.22
    adol
    0.21
    ulent
    0.20
    itional
    0.18
    ster
    0.17
    worthy
    0.17
     Tr
    0.17
    itionally
    0.17
    dition
    0.16
    jectory
    0.16
    Act Density 0.054%

    No Known Activations